Closes#14753
## What changed
| File | Change |
|---|---|
| `pyproject.toml` | `requires-python` → `>=3.13,<3.15`; remove
`strenum==0.4.15` |
| `Dockerfile` | `uv python install 3.13`, `uv sync --python 3.13` |
| `.github/workflows/tests.yml` | `uv sync --python 3.13` on both matrix
legs |
| `CLAUDE.md` | dev setup command + requirements note updated |
| `deepdoc/parser/mineru_parser.py` | `from strenum import StrEnum` →
`from enum import StrEnum` |
| `agent/tools/code_exec.py` | same |
`StrEnum` has been in the stdlib since Python 3.11 — the `strenum`
backport package is no longer needed once the floor is 3.13.
## Why uv.lock is not regenerated
`uv lock --python 3.13` fails because:
1. The infiniflow/graspologic fork pins `numpy>=1.26.4,<2.0.0`
2. `tensorflow-cpu>=2.20.0` (the first release with cp313 wheels)
depends on `ml-dtypes>=0.5.1`, which requires `numpy>=2.1.0`
3. These two constraints are irreconcilable on Python 3.13
The lockfile regeneration requires loosening the `numpy` upper bound in
the `infiniflow/graspologic` fork. Once that fork commit is updated and
the SHA in `pyproject.toml:49` is bumped, `uv lock --python 3.13` will
succeed.
## RFC corrections
Two claims in the original RFC (#14753) did not hold up under code
review:
- **"graspologic hard-blocks 3.13"** — the infiniflow fork at the pinned
commit has no `<3.13` Python constraint. The blocker is the transitive
`numpy<2.0.0` conflict with tensorflow-cpu's test dependency, not a
direct Python version cap.
- **"free-threading throughput gains for I/O-bound workload"** — Python
3.13 free-threading requires a special `--disable-gil` build and
provides no benefit for async I/O code (the GIL is already released
during I/O). The real motivation is forward compatibility and improved
error messages.
### What
19 methods across `rag/llm/chat_model.py` and `rag/llm/cv_model.py`
declare `gen_conf={}` (or `gen_conf: dict = {}`) as a parameter default
and then mutate `gen_conf` in place — typically `del
gen_conf["max_tokens"]`, `gen_conf["penalty_score"] = ...`, or
`gen_conf.pop(...)` as part of provider-specific normalization.
### The two bugs in this pattern
**1. Mutable default argument (Python footgun).** Python evaluates
default values **once** at function-definition time, so the single `{}`
dict is *shared* across every caller that doesn't pass `gen_conf`. The
first such call's mutations leak into the default seen by every
subsequent call.
```python
# Before
def chat_streamly(self, system, history, gen_conf={}, **kwargs):
if "max_tokens" in gen_conf:
del gen_conf["max_tokens"] # mutates the SHARED default dict
...
```
After call N with `max_tokens` set, call N+1 that omits `gen_conf` no
longer sees `max_tokens` — even though the caller never touched it.
**2. Caller-dict pollution.** When the caller *does* pass a `gen_conf`
dict, the same in-place mutations modify the caller's dict. A reused
`gen_conf` (very common for chat-loop callers that build the config once
and pass it on every turn) silently loses `max_tokens`,
`presence_penalty`, etc. after the first round.
### The fix
In every affected method:
- Change `gen_conf={}` (or `gen_conf: dict = {}`) → `gen_conf=None`.
- Add `gen_conf = dict(gen_conf or {})` as the first statement of the
body so all subsequent mutations operate on a fresh local copy.
```python
# After
def chat_streamly(self, system, history, gen_conf=None, **kwargs):
gen_conf = dict(gen_conf or {})
if "max_tokens" in gen_conf:
del gen_conf["max_tokens"] # local copy — safe
...
```
This is byte-for-byte identical provider-side behavior for callers that
already pass a fresh `gen_conf` per call. The new `dict(...)` copy is
O(small constant) per call.
### Files changed
- `rag/llm/chat_model.py` — 17 methods
- `rag/llm/cv_model.py` — 2 methods
### Tests
Adds `test/unit_test/rag/llm/test_gen_conf_no_mutable_default.py` — an
`ast`-based regression guard that walks both modules and asserts no
parameter named `gen_conf` ever has a mutable literal (`{}` or `[]`) as
its default. The test caught **five additional `gen_conf: dict = {}`
sites** that an initial `gen_conf={}` text grep had missed (annotated
parameters with whitespace), and would fail again if the pattern is ever
reintroduced.
```
$ pytest test/unit_test/rag/llm/test_gen_conf_no_mutable_default.py -v
============================== 3 passed in 0.04s ===============================
```
`ruff check` passes on all touched files.
### Notes
- This PR is intentionally focused on **just** the `gen_conf` default +
copy fix. There's a related (but separate) `history.insert(0, ...)`
pattern in the same files that mutates the caller's history list in 12
places — left for a follow-up so this PR stays mechanical and easy to
review.
### Latest revision (`700bb54a7`) — addresses CodeRabbit review
- Type annotation: `gen_conf: dict = None` → `gen_conf: dict | None =
None` (5 occurrences in `chat_model.py`). The old annotation was a
static-checker mismatch since `None` isn't a `dict`.
- Regression test: the AST check accessed `default.keys` directly.
`ast.List` has no `.keys` attribute — a future `gen_conf=[]` would crash
with `AttributeError` instead of being caught. Use `getattr` for both
`.keys` (Dict) and `.elts` (List). Manually verified the updated check
correctly catches both `gen_conf={}` and `gen_conf=[]` while ignoring
`gen_conf=None` and non-empty literals.
---------
Co-authored-by: Ricardo <ricardo@example.com>
## Summary
- Add MiniMax provider GroupId query parameter support in `LiteLLMBase`
- Extract `group_id` from key configuration in `__init__`
- Append `GroupId` as query parameter to `api_base` in
`_construct_complete_args`
## Why this change is needed
MiniMax provides an OpenAI-compatible API endpoint
(`/v1/chat/completions`), but `GroupId` is a MiniMax-specific account
identifier required for billing and rate limiting - it is not part of
the OpenAI standard.
Looking at LiteLLM's `MinimaxChatConfig`:
- `get_complete_url()` only constructs the base URL (e.g.,
`https://api.minimaxi.com/v1/chat/completions`)
- LiteLLM does **not** automatically inject `GroupId` into requests
- This must be handled by the caller (ragflow's chat_model.py)
The implementation appends `GroupId` as a query parameter to `api_base`:
```python
api_base = completion_args.get("api_base", self.base_url)
separator = "&" if "?" in api_base else "?"
completion_args["api_base"] = f"{api_base}{separator}GroupId={self.group_id}"
```
This matches MiniMax's official API format (as documented by
LlamaFactory):
```bash
curl --location 'https://api.minimaxi.chat/v1/text/chatcompletion?GroupId=你的GroupId' \
--header 'Authorization: Bearer 你的API_Key'
```
## Test plan
- [ ] Verify MiniMax API calls work with GroupId query parameter
- [ ] Verify backward compatibility for other providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
### What problem does this PR solve?
Fix#14340
## Problem Description
When using an **Agentic Agent** (not Workflow) with one or more
Retrieval tools (e.g., Dataset Retrieval + Memory Retrieval), the agent
silently returns an empty response (`agent_response: ""`) after hanging
for several minutes. The server logs show:
```
AttributeError: 'ChatCompletionMessageToolCall' object has no attribute 'index'
```
This error propagates as a `GENERIC_ERROR`, causing the canvas to return
an empty response. The subsequent Memory save task then receives the
empty `agent_response` and logs:
```
Document for referred_document_id XXXX not found
```
## Reproduction Steps
1. Set `DOC_ENGINE=infinity` (or `elasticsearch` — the engine itself is
not the root cause).
2. Create a blank **Agentic Agent** (not a Workflow).
3. Add **two Retrieval tools** to the Agent node:
- `Retrieval_DS` → Dataset (Knowledge Base)
- `Retrieval_Mem` → Memory component
4. Add a **Message** node with **Save to Memory** enabled.
5. Launch the agent and send any message (e.g., "hola").
6. The agent hangs and returns an empty response.
## Root Cause Analysis
The crash occurs in `_append_history` and `_append_history_batch` inside
`rag/llm/chat_model.py`. These methods directly access `.index` on tool
call objects:
```python
# _append_history_batch
{
"index": tc.index, # <-- crashes here
...
}
```
However, **non-streaming** LLM responses (`stream=False`) return
`ChatCompletionMessageToolCall` objects, which **do not have an `index`
field** according to the OpenAI API specification. The `index` field
only exists on `ChoiceDeltaToolCall` objects returned in **streaming**
responses (`stream=True`).
When the agentic agent triggers an internal `full_question` call (used
to compress multi-turn conversation history), the request is incorrectly
routed through `async_chat_with_tools` because `is_tools=True` is set at
the `LLMBundle` level. If the LLM decides to emit `tool_calls` during
this auxiliary request, the code enters the non-streaming tool loop and
crashes when trying to append history.
## Fix
Replaced all direct `.index` accesses with `getattr(..., "index", None)`
for safe, backward-compatible access:
| Method | File | Line | Change |
|--------|------|------|--------|
| `_append_history` | `rag/llm/chat_model.py` | ~L304 |
`tool_call.index` → `getattr(tool_call, "index", None)` |
| `_append_history_batch` | `rag/llm/chat_model.py` | ~L332 | `tc.index`
→ `getattr(tc, "index", None)` |
| `_append_history` | `rag/llm/chat_model.py` | ~L1467 |
`tool_call.index` → `getattr(tool_call, "index", None)` |
| `_append_history_batch` | `rag/llm/chat_model.py` | ~L1496 |
`tc.index` → `getattr(tc, "index", None)` |
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: noob <yixiao121314@outlook.com>
### What problem does this PR solve?
agent toolcall null response & schema validation & DeepSeek think
history
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
### What problem does this PR solve?
fix#13944 where OpenAI-compatible custom endpoints failed verification
when model names contained `gpt-5` becauser of incorrect name-based
handling in the Base/backend=`base` path.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
add a handler for gpt 5 models that do not accept parameters by dropping
them, and centralize all models with specific paramter handling function
into a single helper.
solves issue #13639
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
This PR aims to extend the list of possible providers. Adds new Provider
"RAGcon" within the Ollama Modal. It provides all model types except OCR
via Openai-compatible endpoints.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Jakob <16180662+hauberj@users.noreply.github.com>
### What problem does this PR solve?
Refer to issue: #13236
The base url for GPUStack chat model requires `/v1` suffix. For the
other model type like `Embedding` or `Rerank`, the `/v1` suffix is not
required and will be appended in code.
So keep the same logic for chat model as other model type.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR adds [Avian](https://avian.io) as a new LLM provider to RAGFlow.
Avian provides an OpenAI-compatible API with competitive pricing,
offering access to models like DeepSeek V3.2, Kimi K2.5, GLM-5, and
MiniMax M2.5.
**Provider details:**
- API Base URL: `https://api.avian.io/v1`
- Auth: Bearer token via API key
- OpenAI-compatible (chat completions, streaming, function calling)
- Models:
- `deepseek/deepseek-v3.2` — 164K context, $0.26/$0.38 per 1M tokens
- `moonshotai/kimi-k2.5` — 131K context, $0.45/$2.20 per 1M tokens
- `z-ai/glm-5` — 131K context, $0.30/$2.55 per 1M tokens
- `minimax/minimax-m2.5` — 1M context, $0.30/$1.10 per 1M tokens
**Changes:**
- `rag/llm/chat_model.py` — Add `AvianChat` class extending `Base`
- `rag/llm/__init__.py` — Register in `SupportedLiteLLMProvider`,
`FACTORY_DEFAULT_BASE_URL`, `LITELLM_PROVIDER_PREFIX`
- `conf/llm_factories.json` — Add Avian factory with model definitions
- `web/src/constants/llm.ts` — Add to `LLMFactory` enum, `IconMap`,
`APIMapUrl`
- `web/src/components/svg-icon.tsx` — Register SVG icon
- `web/src/assets/svg/llm/avian.svg` — Provider icon
- `docs/references/supported_models.mdx` — Add to supported models table
This follows the same pattern as other OpenAI-compatible providers
(e.g., n1n #12680, TokenPony).
cc @KevinHuSh @JinHai-CN
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
## What problem does this PR solve?
This PR addresses three specific issues to improve agent reliability and
model support:
1. **`codeExec` Output Limitation**: Previously, the `codeExec` tool was
strictly limited to returning `string` types. I updated the output
constraint to `object` to support structured data (Dicts, Lists, etc.)
required for complex downstream tasks.
2. **`codeExec` Error Handling**: Improved the execution logic so that
when runtime errors occur, the tool captures the exception and returns
the error message as the output instead of causing the process to abort
or fail silently.
3. **Spark Model Configuration**:
- Added support for the `MAX-32k` model variant.
- Fixed the `Spark-Lite` mapping from `general` to `lite` to match the
latest API specifications.
## Type of change
- [x] Bug Fix (fixes execution logic and model mapping)
- [x] New Feature / Enhancement (adds model support and improves tool
flexibility)
## Key Changes
### `agent/tools/code_exec.py`
- Changed the output type definition from `string` to `object`.
- Refactored the execution flow to gracefully catch exceptions and
return error messages as part of the tool output.
### `rag/llm/chat_model.py`
- Added `"Spark-Max-32K": "max-32k"` to the model list.
- Updated `"Spark-Lite"` value from `"general"` to `"lite"`.
## Checklist
- [x] My code follows the style guidelines of this project.
- [x] I have performed a self-review of my own code.
Signed-off-by: evilhero <2278596667@qq.com>
### Issue
When using Qwen3 models (`qwen3-32b`, `qwen3-max`) through the
Tongyi-Qianwen provider for non-streaming calls (e.g., knowledge graph
generation), the API fails with:
Closes#12424
```
parameter.enable_thinking must be set to false for non-streaming calls
```
### Root Cause
In `LiteLLMBase.async_chat()`, the `extra_body={"enable_thinking":
False}` was set in `kwargs` but never forwarded to
`_construct_completion_args()`.
### What problem does this PR solve?
Pass merged kwargs to `_construct_completion_args()` using
`**{**gen_conf, **kwargs}` to safely handle potential duplicate
parameters.
### Changes
- `rag/llm/chat_model.py`: Forward kwargs containing `extra_body` to
`_construct_completion_args()` in `async_chat()`
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=42954461
### What problem does this PR solve?
Feat: bedrock iam authentication #12008
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Asure-OpenAI resource not found. #11750
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: duplicate output by async_chat_streamly
Refact: revert manual modification
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
## What changes were proposed in this pull request?
Added a return statement after the successful completion of the async
for loop in async_chat_streamly.
## Why are the changes needed?
Previously, the code lacked a break/return mechanism inside the try
block. This caused the retry loop (for attempt in range...) to continue
executing even after the LLM response was successfully generated and
yielded, resulting in duplicate requests (up to max_retries times).
## Does this PR introduce any user-facing change?
No (it fixes an internal logic bug).
### What problem does this PR solve?
Migrate CV model chat to Async. #11750
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.
### Type of change
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
Make RAGFlow more asynchronous 2. #11551, #11579, #11619.
### Type of change
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
Make RAGFlow more asynchronous 2. #11551, #11579, #11619.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
Add MiniMax-M2 and remove deprecated models.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
Try to make this more asynchronous. Verified in chat and agent
scenarios, reducing blocking behavior. #11551, #11579.
However, the impact of these changes still requires further
investigation to ensure everything works as expected.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Add fallbacks for MinerU output path. #11613, #11620.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add GPT-5.1, GPT‑5.1 Instant and Claude-Opus-4.5. #11548
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add auth header for Ollama chat model. #11350
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Jason <ggbbddjm@gmail.com>
### What problem does this PR solve?
#10056
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
issue:
[#5787](https://github.com/infiniflow/ragflow/issues/5787)
change:
Support Specifying OpenRouter Model Provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Gemini 2.5 Flash Models use reasoning by default. There is currently no
way to disable this behaviour. This leads to very long response times (>
1min). The default behaviour should be, that reasoning is disabled and
configurable
issue #10474
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Google Cloud model does not work correctly with gemini-2.5 models
Close#10408
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
issue:
[#6193](https://github.com/infiniflow/ragflow/issues/6193)
change:
support qwq reasoning models with non-stream output
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
