After upgrading to v0.26.0, the Ollama provider returns an empty model
list because the Go rewrite uses `/api/ps` (only running models) instead
of `/api/tags` (all installed models). This PR changes the endpoint to
`/api/tags`, restoring the ability to list and add Ollama models.
Closes#16000
### 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
### 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
### What problem does this PR solve?
implement `Ollama` provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
