2026-06-03 16:33:58 +08:00
|
|
|
//
|
|
|
|
|
// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
|
|
|
|
|
//
|
|
|
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
|
|
|
// you may not use this file except in compliance with the License.
|
|
|
|
|
// You may obtain a copy of the License at
|
|
|
|
|
//
|
|
|
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
|
//
|
|
|
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
|
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
|
// See the License for the specific language governing permissions and
|
|
|
|
|
// limitations under the License.
|
|
|
|
|
//
|
|
|
|
|
|
2026-05-06 12:03:58 +08:00
|
|
|
package models
|
|
|
|
|
|
|
|
|
|
import (
|
|
|
|
|
"bufio"
|
|
|
|
|
"bytes"
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
"context"
|
2026-05-06 12:03:58 +08:00
|
|
|
"encoding/json"
|
|
|
|
|
"fmt"
|
|
|
|
|
"io"
|
|
|
|
|
"net/http"
|
|
|
|
|
"strings"
|
|
|
|
|
"time"
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
// OllamaModel implements ModelDriver for Ollama AI
|
|
|
|
|
type OllamaModel struct {
|
2026-06-04 17:50:22 +08:00
|
|
|
baseModel BaseModel
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// NewOllamaModel creates a new Ollama AI model instance
|
|
|
|
|
func NewOllamaModel(baseURL map[string]string, urlSuffix URLSuffix) *OllamaModel {
|
|
|
|
|
return &OllamaModel{
|
2026-06-04 17:50:22 +08:00
|
|
|
baseModel: BaseModel{
|
|
|
|
|
BaseURL: baseURL,
|
|
|
|
|
URLSuffix: urlSuffix,
|
|
|
|
|
httpClient: &http.Client{
|
|
|
|
|
Transport: &http.Transport{
|
|
|
|
|
MaxIdleConns: 100,
|
|
|
|
|
MaxIdleConnsPerHost: 10,
|
|
|
|
|
IdleConnTimeout: 90 * time.Second,
|
|
|
|
|
DisableCompression: false,
|
|
|
|
|
},
|
2026-05-06 12:03:58 +08:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) NewInstance(baseURL map[string]string) ModelDriver {
|
2026-06-04 17:50:22 +08:00
|
|
|
return NewOllamaModel(baseURL, o.baseModel.URLSuffix)
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) Name() string {
|
2026-05-06 12:03:58 +08:00
|
|
|
return "ollama"
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) ChatWithMessages(modelName string, messages []Message, apiConfig *APIConfig, chatModelConfig *ChatConfig) (*ChatResponse, error) {
|
2026-05-06 12:03:58 +08:00
|
|
|
if len(messages) == 0 {
|
|
|
|
|
return nil, fmt.Errorf("message is nil")
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resolvedBaseURL, err := o.baseModel.GetBaseURL(apiConfig)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, err
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
2026-06-04 17:50:22 +08:00
|
|
|
url := fmt.Sprintf("%s/%s", resolvedBaseURL, o.baseModel.URLSuffix.Chat)
|
2026-05-06 12:03:58 +08:00
|
|
|
|
|
|
|
|
// For qwen/glm models, use async chat endpoint
|
|
|
|
|
modelType := strings.Split(modelName, "_")[0]
|
|
|
|
|
if modelType == "qwen" || modelType == "glm" {
|
2026-06-04 17:50:22 +08:00
|
|
|
url = fmt.Sprintf("%s/%s", resolvedBaseURL, o.baseModel.URLSuffix.AsyncChat)
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Convert messages to API format
|
|
|
|
|
apiMessages := make([]map[string]interface{}, len(messages))
|
|
|
|
|
for i, msg := range messages {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
arr, _ := msg.Content.([]interface{})
|
|
|
|
|
|
|
|
|
|
first, _ := arr[0].(map[string]interface{})
|
|
|
|
|
|
|
|
|
|
text, _ := first["text"].(string)
|
|
|
|
|
|
2026-05-06 12:03:58 +08:00
|
|
|
apiMessages[i] = map[string]interface{}{
|
|
|
|
|
"role": msg.Role,
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
"content": text,
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Build request body
|
|
|
|
|
reqBody := map[string]interface{}{
|
|
|
|
|
"model": modelName,
|
|
|
|
|
"messages": apiMessages,
|
|
|
|
|
"stream": false,
|
|
|
|
|
"temperature": 1,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if chatModelConfig != nil {
|
|
|
|
|
if chatModelConfig.Stream != nil {
|
|
|
|
|
reqBody["stream"] = *chatModelConfig.Stream
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if chatModelConfig.MaxTokens != nil {
|
|
|
|
|
reqBody["max_tokens"] = *chatModelConfig.MaxTokens
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if chatModelConfig.Temperature != nil {
|
|
|
|
|
reqBody["temperature"] = *chatModelConfig.Temperature
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if chatModelConfig.TopP != nil {
|
|
|
|
|
reqBody["top_p"] = *chatModelConfig.TopP
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if chatModelConfig.Stop != nil {
|
|
|
|
|
reqBody["stop"] = *chatModelConfig.Stop
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if chatModelConfig.Effort != nil && *chatModelConfig.Effort != "" {
|
|
|
|
|
if strings.HasPrefix(strings.ToLower(modelName), "gpt-oss") {
|
|
|
|
|
reqBody["think"] = *chatModelConfig.Effort
|
|
|
|
|
}
|
|
|
|
|
} else if chatModelConfig.Thinking != nil {
|
2026-05-06 12:03:58 +08:00
|
|
|
if *chatModelConfig.Thinking {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
reqBody["think"] = true
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
jsonData, err := json.Marshal(reqBody)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to marshal request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-02 03:27:26 -04:00
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), nonStreamCallTimeout)
|
|
|
|
|
defer cancel()
|
|
|
|
|
|
|
|
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewBuffer(jsonData))
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to create request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
req.Header.Set("Content-Type", "application/json")
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resp, err := o.baseModel.httpClient.Do(req)
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to send request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
defer resp.Body.Close()
|
|
|
|
|
|
|
|
|
|
body, err := io.ReadAll(resp.Body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to read response body: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if resp.StatusCode != http.StatusOK {
|
|
|
|
|
return nil, fmt.Errorf("API request failed with status %d: %s", resp.StatusCode, string(body))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Parse response
|
|
|
|
|
var result map[string]interface{}
|
|
|
|
|
if err = json.Unmarshal(body, &result); err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to parse response: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
message, ok := result["message"].(map[string]interface{})
|
2026-05-06 12:03:58 +08:00
|
|
|
if !ok {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
return nil, fmt.Errorf("failed to parse response: message not found")
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
content, ok := message["content"].(string)
|
2026-05-06 12:03:58 +08:00
|
|
|
if !ok {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
return nil, fmt.Errorf("failed to parse response: content not found")
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
reasonContent, ok := message["thinking"].(string)
|
2026-05-06 12:03:58 +08:00
|
|
|
if !ok {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
return nil, fmt.Errorf("failed to parse response: thinking not found")
|
2026-05-08 12:02:37 +08:00
|
|
|
}
|
2026-05-06 12:03:58 +08:00
|
|
|
|
|
|
|
|
chatResponse := &ChatResponse{
|
2026-05-08 12:02:37 +08:00
|
|
|
Answer: &content,
|
|
|
|
|
ReasonContent: &reasonContent,
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return chatResponse, nil
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) ChatStreamlyWithSender(modelName string, messages []Message, apiConfig *APIConfig, modelConfig *ChatConfig, sender func(*string, *string) error) error {
|
2026-05-06 12:03:58 +08:00
|
|
|
if len(messages) == 0 {
|
|
|
|
|
return fmt.Errorf("messages is empty")
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resolvedBaseURL, err := o.baseModel.GetBaseURL(apiConfig)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return err
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
2026-06-04 17:50:22 +08:00
|
|
|
url := fmt.Sprintf("%s/%s", resolvedBaseURL, o.baseModel.URLSuffix.Chat)
|
2026-05-06 12:03:58 +08:00
|
|
|
modelType := strings.Split(modelName, "-")[0]
|
|
|
|
|
if modelType == "qwen" || modelType == "glm" {
|
2026-06-04 17:50:22 +08:00
|
|
|
url = fmt.Sprintf("%s/%s", resolvedBaseURL, o.baseModel.URLSuffix.AsyncChat)
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Convert messages to API format (supporting multimodal content)
|
|
|
|
|
apiMessages := make([]map[string]interface{}, len(messages))
|
|
|
|
|
for i, msg := range messages {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
arr, _ := msg.Content.([]interface{})
|
|
|
|
|
|
|
|
|
|
first, _ := arr[0].(map[string]interface{})
|
|
|
|
|
|
|
|
|
|
text, _ := first["text"].(string)
|
|
|
|
|
|
2026-05-06 12:03:58 +08:00
|
|
|
apiMessages[i] = map[string]interface{}{
|
|
|
|
|
"role": msg.Role,
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
"content": text,
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Build request body with streaming enabled
|
|
|
|
|
reqBody := map[string]interface{}{
|
|
|
|
|
"model": modelName,
|
|
|
|
|
"messages": apiMessages,
|
|
|
|
|
"stream": true,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.Stream != nil {
|
|
|
|
|
reqBody["stream"] = *modelConfig.Stream
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.MaxTokens != nil {
|
|
|
|
|
reqBody["max_tokens"] = *modelConfig.MaxTokens
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.Temperature != nil {
|
|
|
|
|
reqBody["temperature"] = *modelConfig.Temperature
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.DoSample != nil {
|
|
|
|
|
reqBody["do_sample"] = *modelConfig.DoSample
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.TopP != nil {
|
|
|
|
|
reqBody["top_p"] = *modelConfig.TopP
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelConfig.Stop != nil {
|
|
|
|
|
reqBody["stop"] = *modelConfig.Stop
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if modelConfig.Effort != nil && *modelConfig.Effort != "" {
|
|
|
|
|
if strings.HasPrefix(strings.ToLower(modelName), "gpt-oss") {
|
|
|
|
|
reqBody["think"] = *modelConfig.Effort
|
|
|
|
|
}
|
|
|
|
|
} else if modelConfig.Thinking != nil {
|
2026-05-06 12:03:58 +08:00
|
|
|
if *modelConfig.Thinking {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
reqBody["think"] = true
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
jsonData, err := json.Marshal(reqBody)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return fmt.Errorf("failed to marshal request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-02 03:27:26 -04:00
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), streamCallTimeout)
|
|
|
|
|
defer cancel()
|
|
|
|
|
|
|
|
|
|
req, err := http.NewRequestWithContext(ctx, "POST", url, bytes.NewBuffer(jsonData))
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return fmt.Errorf("failed to create request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
req.Header.Set("Content-Type", "application/json")
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resp, err := o.baseModel.httpClient.Do(req)
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return fmt.Errorf("failed to send request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
defer resp.Body.Close()
|
|
|
|
|
|
|
|
|
|
if resp.StatusCode != http.StatusOK {
|
|
|
|
|
body, _ := io.ReadAll(resp.Body)
|
|
|
|
|
return fmt.Errorf("API request failed with status %d: %s", resp.StatusCode, string(body))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// SSE parsing: read line by line
|
|
|
|
|
scanner := bufio.NewScanner(resp.Body)
|
fix(go-models): raise SSE scanner buffer so large stream chunks are not dropped (#15382)
### Summary
Closes #15381
Every provider in `internal/entity/models/` reads its streaming response
with `bufio.NewScanner(resp.Body)` and iterates over `scanner.Scan()`.
The default `bufio.Scanner` maximum token size is 64KB, so when an
upstream sends a single SSE `data:` line larger than 64KB (long content
deltas, large tool or function call argument blobs, bundled
`reasoning_content`, or providers that emit a whole message in one
event) `scanner.Scan()` returns `false` and `scanner.Err()` returns
`bufio.ErrTooLong`. Streaming chat then ends with an error partway
through the response.
This change adds `scanner.Buffer(make([]byte, 64*1024), 1024*1024)`
immediately after every SSE scanner that was still bare, raising the cap
to 1MB. 1MB is the value already used for streaming chat in `openai.go`,
`modelscope.go`, `groq.go`, `mistral.go`, `xai.go` and the other already
patched providers (the 8MB cap in the repo is reserved for TTS and
embedding paths), so this simply converges the remaining providers onto
the established pattern. Nothing else changes: line parsing, `data:`
prefix handling, `[DONE]` detection, JSON unmarshalling, error handling,
and the existing `scanner.Err()` checks all stay the same.
Providers covered (23 scanners across 22 files): 302ai, aliyun,
baichuan, baidu, cohere, deepinfra, deepseek, gitee, huggingface,
lmstudio, minimax (the chat scanner, whose TTS scanner was already
bumped), moonshot, nvidia, ollama, openrouter, orcarouter, paddleocr,
siliconflow, tokenhub, vllm, volcengine, xunfei, zhipu-ai. `jiekouai.go`
is excluded because it is covered by the in flight #15337.
A table driven regression test (`sse_scanner_buffer_test.go`) streams a
single 128KB `data:` content delta followed by `data: [DONE]` through an
`httptest` server and asserts that `ChatStreamlyWithSender` delivers the
full content with no error across a representative subset of providers.
Without the buffer fix the test fails with `bufio.Scanner: token too
long`.
This PR also removes three duplicate declarations of the package level
`roundTripperFunc` test helper that several recently merged provider PRs
each added independently, which had left the `internal/entity/models`
test package unable to compile. The helper now lives in a single place
and is shared.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
2026-05-29 07:34:00 -04:00
|
|
|
scanner.Buffer(make([]byte, 64*1024), 1024*1024)
|
2026-05-06 12:03:58 +08:00
|
|
|
for scanner.Scan() {
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
line := strings.TrimSpace(scanner.Text())
|
2026-05-06 12:03:58 +08:00
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
// ignore the blank
|
|
|
|
|
if line == "" {
|
2026-05-06 12:03:58 +08:00
|
|
|
continue
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Parse the JSON event
|
|
|
|
|
var event map[string]interface{}
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if err = json.Unmarshal([]byte(line), &event); err != nil {
|
2026-05-06 12:03:58 +08:00
|
|
|
continue
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if messageMap, ok := event["message"].(map[string]interface{}); ok {
|
|
|
|
|
if reasoningContent, exists := messageMap["thinking"].(string); exists && reasoningContent != "" {
|
|
|
|
|
if err := sender(nil, &reasoningContent); err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if content, exists := messageMap["content"].(string); exists && content != "" {
|
|
|
|
|
if err := sender(&content, nil); err != nil {
|
|
|
|
|
return err
|
|
|
|
|
}
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if done, ok := event["done"].(bool); ok && done {
|
2026-05-06 12:03:58 +08:00
|
|
|
break
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
// Send [DONE] marker for OpenAI compatibility with RAGFlow frontend
|
2026-05-06 12:03:58 +08:00
|
|
|
endOfStream := "[DONE]"
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if err := sender(&endOfStream, nil); err != nil {
|
2026-05-06 12:03:58 +08:00
|
|
|
return err
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return scanner.Err()
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-11 14:45:30 +08:00
|
|
|
func (o *OllamaModel) Embed(modelName *string, texts []string, apiConfig *APIConfig, embeddingConfig *EmbeddingConfig) ([]EmbeddingData, error) {
|
2026-06-04 17:50:22 +08:00
|
|
|
if err := o.baseModel.APIConfigCheck(apiConfig); err != nil {
|
|
|
|
|
return nil, err
|
|
|
|
|
}
|
|
|
|
|
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
if len(texts) == 0 {
|
2026-05-11 14:45:30 +08:00
|
|
|
return []EmbeddingData{}, nil
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if modelName == nil || *modelName == "" {
|
|
|
|
|
return nil, fmt.Errorf("model name is required")
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resolvedBaseURL, err := o.baseModel.GetBaseURL(apiConfig)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, err
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
}
|
2026-06-04 17:50:22 +08:00
|
|
|
baseURL := resolvedBaseURL
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
if baseURL == "" {
|
2026-06-04 17:50:22 +08:00
|
|
|
baseURL = resolvedBaseURL
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
}
|
|
|
|
|
if baseURL == "" {
|
|
|
|
|
return nil, fmt.Errorf("missing base URL: please configure the local access address for Ollama (e.g., http://127.0.0.1:11434/v1)")
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
url := fmt.Sprintf("%s/%s", strings.TrimSuffix(baseURL, "/"), o.baseModel.URLSuffix.Embedding)
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
|
|
|
|
|
reqBody := map[string]interface{}{
|
|
|
|
|
"model": *modelName,
|
|
|
|
|
"input": texts,
|
|
|
|
|
}
|
|
|
|
|
if embeddingConfig != nil && embeddingConfig.Dimension > 0 {
|
|
|
|
|
reqBody["dimensions"] = embeddingConfig.Dimension
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
jsonData, err := json.Marshal(reqBody)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to marshal request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-02 03:27:26 -04:00
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), nonStreamCallTimeout)
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
defer cancel()
|
|
|
|
|
|
|
|
|
|
req, err := http.NewRequestWithContext(ctx, "POST", url, bytes.NewBuffer(jsonData))
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to create request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
req.Header.Set("Content-Type", "application/json")
|
2026-06-04 17:50:22 +08:00
|
|
|
req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", *apiConfig.ApiKey))
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resp, err := o.baseModel.httpClient.Do(req)
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to send request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
defer resp.Body.Close()
|
|
|
|
|
|
|
|
|
|
body, err := io.ReadAll(resp.Body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to read response: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if resp.StatusCode != http.StatusOK {
|
|
|
|
|
return nil, fmt.Errorf("Ollama embeddings API error: %s, body: %s", resp.Status, string(body))
|
|
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
var embedResp struct {
|
|
|
|
|
Model string `json:"model"`
|
|
|
|
|
Embeddings [][]float64 `json:"embeddings"`
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
}
|
|
|
|
|
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
if err = json.Unmarshal(body, &embedResp); err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to unmarshal response: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if len(embedResp.Embeddings) == 0 {
|
|
|
|
|
return nil, fmt.Errorf("no embeddings returned")
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
embeddings := make([]EmbeddingData, 0, len(embedResp.Embeddings))
|
|
|
|
|
|
|
|
|
|
for i, emb := range embedResp.Embeddings {
|
|
|
|
|
if len(emb) == 0 {
|
|
|
|
|
return nil, fmt.Errorf("empty embedding at index %d", i)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
embeddings = append(embeddings, EmbeddingData{
|
|
|
|
|
Embedding: emb,
|
|
|
|
|
Index: i,
|
|
|
|
|
})
|
Go: implement Encode (embeddings) in Ollama driver (#14664)
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes #14662
2026-05-11 06:50:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return embeddings, nil
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
|
|
|
|
|
2026-05-09 17:41:54 +08:00
|
|
|
func (o *OllamaModel) Rerank(modelName *string, query string, documents []string, apiConfig *APIConfig, rerankConfig *RerankConfig) (*RerankResponse, error) {
|
2026-05-06 12:03:58 +08:00
|
|
|
return nil, fmt.Errorf("no such method")
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-12 17:17:44 +08:00
|
|
|
// TranscribeAudio transcribe audio
|
|
|
|
|
func (o *OllamaModel) TranscribeAudio(modelName *string, file *string, apiConfig *APIConfig, asrConfig *ASRConfig) (*ASRResponse, error) {
|
|
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) TranscribeAudioWithSender(modelName *string, file *string, apiConfig *APIConfig, asrConfig *ASRConfig, sender func(*string, *string) error) error {
|
|
|
|
|
return fmt.Errorf("%s, no such method", o.Name())
|
2026-05-12 17:17:44 +08:00
|
|
|
}
|
|
|
|
|
|
2026-05-15 18:41:43 +08:00
|
|
|
// AudioSpeech convert text to audio
|
|
|
|
|
func (o *OllamaModel) AudioSpeech(modelName *string, audioContent *string, apiConfig *APIConfig, ttsConfig *TTSConfig) (*TTSResponse, error) {
|
2026-05-12 17:17:44 +08:00
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) AudioSpeechWithSender(modelName *string, audioContent *string, apiConfig *APIConfig, ttsConfig *TTSConfig, sender func(*string, *string) error) error {
|
|
|
|
|
return fmt.Errorf("%s, no such method", o.Name())
|
2026-05-12 17:17:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// OCRFile OCR file
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) OCRFile(modelName *string, content []byte, url *string, apiConfig *APIConfig, ocrConfig *OCRConfig) (*OCRFileResponse, error) {
|
|
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
2026-05-12 17:17:44 +08:00
|
|
|
}
|
|
|
|
|
|
2026-05-15 12:29:52 +08:00
|
|
|
// ParseFile parse file
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) ParseFile(modelName *string, content []byte, url *string, apiConfig *APIConfig, parseFileConfig *ParseFileConfig) (*ParseFileResponse, error) {
|
|
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
2026-05-15 12:29:52 +08:00
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) ListModels(apiConfig *APIConfig) ([]string, error) {
|
2026-05-06 12:03:58 +08:00
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resolvedBaseURL, err := o.baseModel.GetBaseURL(apiConfig)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, err
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
2026-06-04 17:50:22 +08:00
|
|
|
baseURL := resolvedBaseURL
|
fix(go): wire CheckConnection to ListModels in ollama, lm-studio, and vllm (#14614)
### What problem does this PR solve?
Three Go drivers had `CheckConnection` returning a hardcoded `no such
method` error, even though each one already has a working `ListModels`
that hits the configured base URL with the configured API key. So the
"Check connection" button in the model provider UI always failed for
these three providers, even when the underlying setup was fine.
Affected drivers:
- `internal/entity/models/ollama.go`
- `internal/entity/models/lmstudio.go`
- `internal/entity/models/vllm.go`
This is a real user-facing gap because Ollama and LM Studio are two of
the most popular local LLM runners, and vLLM is widely used for
self-hosted deployments.
### What this PR includes
For each of the three drivers, replace the stub with a small
implementation that calls `ListModels` and returns its error:
```go
func (o *OllamaModel) CheckConnection(apiConfig *APIConfig) error {
_, err := o.ListModels(apiConfig)
return err
}
```
This is the exact pattern that xai, moonshot, deepseek, aliyun, and
gitee already use for the same method.
No JSON change. No factory change. No interface change.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### How was this tested?
- `go build ./internal/entity/models/...` in a clean go 1.25 image (the
go.mod minimum) returns exit 0.
- The full ModelDriver interface still resolves on each driver
(NewInstance, Name, ChatWithMessages, ChatStreamlyWithSender, Encode,
Rerank, ListModels, Balance, CheckConnection).
- Pattern parity with the existing xai, moonshot, deepseek, aliyun, and
gitee CheckConnection methods.
Closes #14609
2026-05-08 06:00:10 +02:00
|
|
|
if baseURL == "" {
|
2026-06-04 17:50:22 +08:00
|
|
|
baseURL = resolvedBaseURL
|
fix(go): wire CheckConnection to ListModels in ollama, lm-studio, and vllm (#14614)
### What problem does this PR solve?
Three Go drivers had `CheckConnection` returning a hardcoded `no such
method` error, even though each one already has a working `ListModels`
that hits the configured base URL with the configured API key. So the
"Check connection" button in the model provider UI always failed for
these three providers, even when the underlying setup was fine.
Affected drivers:
- `internal/entity/models/ollama.go`
- `internal/entity/models/lmstudio.go`
- `internal/entity/models/vllm.go`
This is a real user-facing gap because Ollama and LM Studio are two of
the most popular local LLM runners, and vLLM is widely used for
self-hosted deployments.
### What this PR includes
For each of the three drivers, replace the stub with a small
implementation that calls `ListModels` and returns its error:
```go
func (o *OllamaModel) CheckConnection(apiConfig *APIConfig) error {
_, err := o.ListModels(apiConfig)
return err
}
```
This is the exact pattern that xai, moonshot, deepseek, aliyun, and
gitee already use for the same method.
No JSON change. No factory change. No interface change.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### How was this tested?
- `go build ./internal/entity/models/...` in a clean go 1.25 image (the
go.mod minimum) returns exit 0.
- The full ModelDriver interface still resolves on each driver
(NewInstance, Name, ChatWithMessages, ChatStreamlyWithSender, Encode,
Rerank, ListModels, Balance, CheckConnection).
- Pattern parity with the existing xai, moonshot, deepseek, aliyun, and
gitee CheckConnection methods.
Closes #14609
2026-05-08 06:00:10 +02:00
|
|
|
}
|
|
|
|
|
if baseURL == "" {
|
|
|
|
|
return nil, fmt.Errorf("missing base URL: please configure the local access address for Ollama (e.g., http://127.0.0.1:11434/v1)")
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
url := fmt.Sprintf("%s/%s", baseURL, o.baseModel.URLSuffix.Models)
|
2026-05-06 12:03:58 +08:00
|
|
|
reqBody := map[string]interface{}{}
|
|
|
|
|
|
|
|
|
|
jsonData, err := json.Marshal(reqBody)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to marshal request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-02 03:27:26 -04:00
|
|
|
ctx, cancel := context.WithTimeout(context.Background(), nonStreamCallTimeout)
|
|
|
|
|
defer cancel()
|
|
|
|
|
|
|
|
|
|
req, err := http.NewRequestWithContext(ctx, "GET", url, bytes.NewBuffer(jsonData))
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to create request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
req.Header.Set("Content-Type", "application/json")
|
|
|
|
|
|
2026-06-04 17:50:22 +08:00
|
|
|
resp, err := o.baseModel.httpClient.Do(req)
|
2026-05-06 12:03:58 +08:00
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to send request: %w", err)
|
|
|
|
|
}
|
|
|
|
|
defer resp.Body.Close()
|
|
|
|
|
|
|
|
|
|
body, err := io.ReadAll(resp.Body)
|
|
|
|
|
if err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to read response: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if resp.StatusCode != http.StatusOK {
|
|
|
|
|
return nil, fmt.Errorf("API request failed with status %d: %s", resp.StatusCode, string(body))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Parse response
|
|
|
|
|
var result map[string]interface{}
|
|
|
|
|
if err = json.Unmarshal(body, &result); err != nil {
|
|
|
|
|
return nil, fmt.Errorf("failed to parse response: %w", err)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// convert result["data"] to []map[string]interface{}
|
|
|
|
|
models := make([]string, 0)
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
for _, model := range result["models"].([]interface{}) {
|
2026-05-06 12:03:58 +08:00
|
|
|
modelMap := model.(map[string]interface{})
|
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213)
### What problem does this PR solve?
IDK how to implement **`Ollama`** on #14580 but it's totally wrong.
This is the rewrite version for **`Ollama`**
**Verified from CLI**
```
# Embed
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 768 | 0 |
| 768 | 1 |
+-----------+-------+
# Chat
RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it.
Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today?
Time: 2.914285
RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u'
Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone.
Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today?
Time: 1.740047
# LisyModels
RAGFlow(user)> list supported models from 'ollama' 'test12'
+-------------------------+
| model_name |
+-------------------------+
| nomic-embed-text:latest |
| qwen3:0.6b |
+-------------------------+
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2026-05-25 18:55:03 +08:00
|
|
|
modelName := modelMap["name"].(string)
|
2026-05-06 12:03:58 +08:00
|
|
|
models = append(models, modelName)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return models, nil
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) Balance(apiConfig *APIConfig) (map[string]interface{}, error) {
|
2026-05-06 12:03:58 +08:00
|
|
|
return nil, fmt.Errorf("no such method")
|
|
|
|
|
}
|
|
|
|
|
|
2026-05-08 15:54:27 +08:00
|
|
|
// CheckConnection verifies that the configured Ollama base URL is reachable
|
2026-05-06 19:23:11 +08:00
|
|
|
func (o *OllamaModel) CheckConnection(apiConfig *APIConfig) error {
|
2026-05-08 15:54:27 +08:00
|
|
|
_, err := o.ListModels(apiConfig)
|
|
|
|
|
return err
|
2026-05-06 12:03:58 +08:00
|
|
|
}
|
2026-05-15 12:29:52 +08:00
|
|
|
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) ListTasks(apiConfig *APIConfig) ([]ListTaskStatus, error) {
|
|
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
2026-05-15 12:29:52 +08:00
|
|
|
}
|
|
|
|
|
|
2026-06-03 14:09:07 +08:00
|
|
|
func (o *OllamaModel) ShowTask(taskID string, apiConfig *APIConfig) (*TaskResponse, error) {
|
|
|
|
|
return nil, fmt.Errorf("%s, no such method", o.Name())
|
2026-05-15 12:29:52 +08:00
|
|
|
}
|