### What problem does this PR solve?
fix some comments to improve readability
### Type of change
- [x] Documentation Update
---------
Signed-off-by: box4wangjing <box4wangjing@outlook.com>
## Summary
- Adding a Bedrock model from the frontend fails with `Fail to access
model(Bedrock/<model>).Expecting value: line 1 column 1 (char 0)`.
- The assembled Bedrock JSON credentials are silently replaced by `"x"`
before the connection test, causing `json.loads("x")` to raise a
`JSONDecodeError`.
## What problem does this PR solve?
Commit `050113482` introduced a fallback in `add_llm()` that reuses the
existing DB key when `req.get("api_key") is None`:
```python
if req.get("api_key") is None:
api_key = existing_api_key if existing_api_key is not None else "x"
```
For Bedrock, credentials are sent as separate fields (`auth_mode`,
`bedrock_ak`, `bedrock_sk`, `bedrock_region`, `aws_role_arn`) — the
frontend does not send an `api_key` field. The function correctly
assembles the JSON key:
```python
api_key = apikey_json(["auth_mode", "bedrock_ak", "bedrock_sk", "bedrock_region", "aws_role_arn"])
```
But since `req.get("api_key")` is `None`, the override immediately
replaces `api_key` with `"x"` (or a stale DB value). `LiteLLMBase` then
calls `json.loads("x")` for Bedrock auth → `JSONDecodeError`.
## Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Changes
**`api/apps/llm_app.py`**
Write the assembled key into `req["api_key"]` so the `None` check
evaluates to `False` and the override is skipped — consistent with how
`Tencent Cloud` is already handled.
```python
# Before
api_key = apikey_json(["auth_mode", "bedrock_ak", "bedrock_sk", "bedrock_region", "aws_role_arn"])
# After
req["api_key"] = apikey_json(["auth_mode", "bedrock_ak", "bedrock_sk", "bedrock_region", "aws_role_arn"])
api_key = req["api_key"]
```
## Test plan
- [ ] Configure a Bedrock provider in Model Providers with valid AWS
credentials
- [ ] Add a Bedrock chat model — verify no `Expecting value` error
- [ ] Update the same model — verify the existing key is reused
correctly when credentials fields are left empty
🤖 Generated with [Claude Code](https://claude.ai/claude-code)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
Add id for table tenant_llm and apply in LLMBundle.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Improve model verification UX. #13395
### Type of change
- [x] Refactoring
---------
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Add PaddleOCR as a new PDF parser.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. Refactor implementation of add_llm
2. Add speech to text model.
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Treat MinerU as an OCR model.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [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?
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?
Currently we cannot add any models, since factory is a string, and the
return type of get_allowed_llm_factories() is List[object]
https://github.com/infiniflow/ragflow/pull/11003
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Currently, if we want to restrict the allowed factories users can use we
need to delete from the database table manually. The proposal of this PR
is to include a variable to that, if set, will restrict the LLM
factories the users can see and add. This allow us to not touch the
llm_factories.json or the database if the LLM factory is already
inserted.
Obs.: All the lint changes were from the pre-commit hook which I did not
change.
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: the input length exceeds the context length #10750
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This commit removes the Youdao and BAAI entries from the LLM factories
configuration as they are no longer needed or supported.
### Type of change
- [x] Config update
### 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?
Introduced gpu profile in .env
Added Dockerfile_tei
fix datrie
Removed LIGHTEN flag
### Type of change
- [x] Documentation Update
- [x] Refactoring
### 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?
All models pass the mock response tests, which means that if a model can
return the correct response, everything should work as expected.
However, not all models have been fully tested in a real environment,
the real API_KEY. I suggest actively monitoring the refactored models
over the coming period to ensure they work correctly and fixing them
step by step, or waiting to merge until most have been tested in
practical environment.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Improve the logic so that it does not decode base 64 for the test image
each time
### Type of change
- [x] Refactoring
- [x] Performance Improvement
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
