### What problem does this PR solve?
Fix:
- VolcEngine adapt to new api_key format
- Save dict api_key as json
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes the issue where Qwen3.5/Qwen3.6 series models may spend
excessive time on simple document-parsing tasks, such as Auto Metadata
extraction, keyword extraction, question generation, and image
description when using the MinerU parser.
For these tasks, Qwen3.5/Qwen3.6 models may perform unnecessary
reasoning by default, which can lead to very long response times, high
token consumption, and, in some cases, potential infinite output loops.
Since Qwen3.5/Qwen3.6 multimodal models are instantiated as `CvModel`
when configured as `image2text`, the existing `enable_thinking=False`
logic in `chat_model.py` does not apply to them. This PR adds the
corresponding handling for the CV/image-to-text model path as well.
This helps reduce unnecessary thinking time, avoid potential infinite
loops, and improve parsing efficiency without noticeably affecting
output quality for these simple extraction and image-description tasks.
Fixes#15083.
## Summary
Fixes 10 unguarded `response.choices[0]` accesses that cause
`IndexError` or `AttributeError` when the LLM returns an empty `choices`
list — the scenario described in #14711.
- `rag/llm/cv_model.py`
- `rag/llm/chat_model.py`
Each access site is now guarded with:
```python
if not response.choices:
raise ValueError("LLM returned empty response")
```
## Verification
Detected and verified by [pact](https://github.com/qizwiz/pact) — a
sheaf-cohomological LLM contract checker using Z3 as a local theory
solver.
**pact sheaf-cohomological proof status after fix:**
| File | Ȟ¹ (after) | Z3 |
|------|-----------|-----|
| `rag/llm/cv_model.py` | 0 | UNSAT ✓ |
| `rag/llm/chat_model.py` | 0 | UNSAT ✓ |
All access sites proven safe (Z3 UNSAT certificate).
The checker was also used to verify the autogen streaming-None fix in
[microsoft/autogen#7711](https://github.com/microsoft/autogen/pull/7711).
## Test plan
- [ ] Existing test suite passes
- [ ] Manually test with a provider that returns empty `choices` under
load (e.g. Vertex AI)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Signed-off-by: Jonathan Hill <jonathan.f.hill@gmail.com>
### What problem does this PR solve?
Multiple `requests.post()` calls across the LLM integration layer lack a
`timeout` parameter. Without a timeout, a single unresponsive upstream
service can block the calling thread **indefinitely**, eventually
exhausting the thread pool and degrading the entire system.
This is a well-known issue — Python's `requests` library defaults to
`timeout=None` (infinite wait), and [the library docs explicitly
recommend](https://requests.readthedocs.io/en/latest/user/advanced/#timeouts)
always setting a timeout.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Change
Added `timeout` to all `requests.post()` calls missing it:
| File | Calls fixed | Timeout |
|------|-------------|---------|
| `rag/llm/rerank_model.py` | 9 | 30s |
| `rag/llm/embedding_model.py` | 8 | 30s |
| `rag/llm/cv_model.py` | 3 | 60s |
| `rag/llm/tts_model.py` | 2 | 60s |
| `rag/llm/sequence2txt_model.py` | 2 | 60s |
Embedding/rerank calls use 30s (lightweight API calls). Vision, TTS, and
audio transcription use 60s (heavier workloads with file uploads).
Note: other files in the codebase (e.g. `check_minio_alive`,
`check_ragflow_server_alive`) already use `timeout=10`, so this PR
brings the LLM layer in line with existing practice.
Signed-off-by: Ricardo-M-L <Sibyl_Hartmanbnb@webname.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
## Summary
- `CvModel["Bedrock"]` was absent from `rag/llm/cv_model.py`, causing
`model_instance()` to return `None` when a Bedrock model was used as a
PDF parser — even after correct model resolution.
- This PR adds `BedrockCV`, enabling Bedrock vision models (e.g.
`amazon.nova-pro-v1:0`, `anthropic.claude-3-5-sonnet`) to be used as PDF
parsers.
## What problem does this PR solve?
When a Bedrock model is selected as the PDF parser in a knowledge base,
ingestion failed with:
```
'LiteLLMBase' object has no attribute 'describe_with_prompt'
```
The root cause: `LiteLLMBase` (the Bedrock chat implementation) was the
only registered handler for the Bedrock factory. It does not implement
`describe_with_prompt`. `CvModel` had no Bedrock entry, so
`model_instance()` returned `None` for `image2text` requests.
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Changes
**`rag/llm/cv_model.py`**
Adds `BedrockCV(Base)` with `_FACTORY_NAME = "Bedrock"`:
- Uses `litellm.completion` with the `bedrock/` prefix (consistent with
`LiteLLMBase`)
- Parses AWS credentials from the JSON key assembled by `add_llm`
(`auth_mode`, `bedrock_ak`, `bedrock_sk`, `bedrock_region`,
`aws_role_arn`)
- Supports three auth modes: `access_key_secret`, `iam_role` (via STS
`assume_role`), and default credential chain (IRSA, instance profile)
- Implements `describe_with_prompt` and `describe`
## Test plan
- [ ] Configure a Bedrock vision model (e.g. `amazon.nova-pro-v1:0`)
with valid AWS credentials
- [ ] Select it as PDF parser in a knowledge base
- [ ] Verify ingestion of a PDF document completes without errors
- [ ] Verify `CvModel["Bedrock"]` resolves to `BedrockCV`
🤖 Generated with [Claude Code](https://claude.ai/claude-code)
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
### 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>
### 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?
Refact: switch from oogle-generativeai to google-genai #13132
Refact: commnet out unused pywencai.
### Type of change
- [x] Refactoring
### 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?
Add Gemini 3 Pro preview.
Change `GenerativeModel` to `genai`.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: add describe_image_with_prompt for ZHIPU AI #11289
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add kimi-k2-thinking and moonshot-v1-vision-preview.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
change:
wrong describe_with_prompt() in ollama
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Allow initialize Redis without password.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: can't upload image in ollama model #10447
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### Change all `image=[]` to `image = None`
Changing `image=[]` to `images=None` avoids Python’s mutable default
parameter issue.
If you keep `images=[]`, all calls share the same list, so modifying it
(e.g., images.append()) will affect later calls.
Using images=None and creating a new list inside the function ensures
each call is independent.
This change does not affect current behavior — it simply makes the code
safer and more predictable.
把 `images=[]` 改成 `images=None` 是为了避免 Python 默认参数的可变对象问题。
如果保留 `images=[]`，所有调用都会共用同一个列表，一旦修改就会影响后续调用。
改成 None 并在函数内部重新创建列表，可以确保每次调用都是独立的。
这个修改不会影响现有运行结果，只是让代码更安全、更可控。
### What problem does this PR solve?
Qwen-VL series supports video parsing. #10617.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
issue:
[#9004](https://github.com/infiniflow/ragflow/issues/9004)
change:
VolcEngine Model type add IMAGE2TEXT
### Type of change
- [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?
Revert back to chat.completions.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [x] Other (please describe):
Revert back to chat.completions.
### What problem does this PR solve?
Fix broken imports
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix: resolve hash collisions by switching to UUID &correct logic for
always-true statements, solved: #10165
Feat: Update GPT api integration, solved: #10204
Feat: Support qianwen-deepresearch, solved: #10163
### 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?
Fix Gemini parameters error.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
fix: preserve correct MIME & unify data URL handling for vision inputs
(relates #9248)
- Updated image2base64() to return a full data URL
(data:image/<fmt>;base64,...) with accurate MIME
- Removed hardcoded image/jpeg in Base._image_prompt(); pass through
data URLs and default raw base64 to image/png
- Set AnthropicCV._image_prompt() raw base64 media_type default to
image/png
- Ensures MIME type matches actual image content, fixing “cannot process
base64 image” errors on vLLM/OpenAI-compatible backends
### What problem does this PR solve?
This PR fixes a compatibility issue where base64-encoded images sent to
vision models (e.g., vLLM/OpenAI-compatible backends) were rejected due
to mismatched MIME type or incorrect decoding.
Previously, the backend:
- Always converted raw base64 into data:image/jpeg;base64,... even if
the actual content was PNG.
- In some cases, base64 decoding was attempted on the full data URL
string instead of the pure base64 part.
This caused errors like:
```
cannot process base64 image
failed to decode base64 string: illegal base64 data at input byte 0
```
by strict validators such as vLLM.
With this fix, the MIME type in the request now matches the actual image
content, and data URLs are correctly handled or passed through, ensuring
vision models can decode and process images reliably.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
#9082#6365
<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add xAI provider (experimental feature, requires user feedback).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
