## Summary
Closes#14921.
Reconfiguring an existing LLM provider to enable **tool call** or
**vision** fails with `Your API key is invalid. Fail to access model.`
even when the saved API key is correct. The most visible report is
VLLM ("Cannot add vllm model" once `--enable-auto-tool-choice` /
vision is toggled on), but the bug applies to every provider whose
api_key field stays blank in edit mode.
## Root cause
PR #14885 ("Fix: llm add api key overridden") removed the existing-key
lookup in `api/apps/llm_app.py::add_llm`. The intent was correct —
stop the saved key from clobbering a user-provided new one — but the
removal was unconditional, so the edit path now has no fallback at all:
1. `web/src/pages/user-setting/setting-model/hooks.tsx:230` sets the
initial `api_key` form value to `''` in edit mode (the real key is
never returned to the browser).
2. The user toggles `is_tools` / `vision` without retyping the key.
3. `hooks.tsx:183-185` strips the empty `api_key` from the payload.
4. `add_llm` defaults to the placeholder `"x"`
(`api/apps/llm_app.py:182`).
5. The upstream provider rejects `"x"` with `Your API key is invalid`.
## Fix
Restore the fallback **narrowly**, before any factory-specific handler
runs:
- If `req.get("api_key") is None`, look up the tenant's existing record
(using the correctly suffixed `llm_name` for VLLM /
OpenAI-API-Compatible / LocalAI / HuggingFace).
- Decode the saved blob with `_decode_api_key_config` and write **only
the decoded `api_key` string** back into `req["api_key"]`. Never use
the raw JSON payload — that was the exact thing PR #14885 was trying
to avoid.
- When the user **does** type a new key, `req.get("api_key")` is not
`None` and the fallback is skipped, so PR #14885's fix is preserved.
| Scenario | Before this PR | After this PR |
|---|---|---|
| Plain factory (VLLM, Ollama, …), retype key | OK | OK |
| Plain factory, blank key in edit (the bug) | Fails with "API key is
invalid" | Recovers saved key, validates against the real one |
| OpenRouter / Bedrock, change `provider_order` only | Fails |
`apikey_json([...])` rebuilds the JSON with saved `api_key` + new field
|
| User clears the form and types a brand-new key | OK (key replaced) |
OK (key replaced — fallback skipped) |
## Files changed
- `api/apps/llm_app.py` — restored fallback in `add_llm` (no other call
sites touched).
## Test plan
- [ ] Add a VLLM chat model with a valid api_key, no toggles → save
succeeds.
- [ ] Edit the same model, toggle **tool call** on, leave api_key blank
→ save succeeds, validation runs against the saved key.
- [ ] Edit again, toggle **vision** on (model_type → `image2text`),
leave api_key blank → save succeeds.
- [ ] Edit again and **type a new api_key** → the new key replaces the
saved one (`is None` check skips the fallback). Verify via the DB
row or by deliberately typing a wrong key and observing the
validation failure.
- [ ] Repeat the blank-key edit with **OpenRouter**, changing only
`provider_order` → resulting api_key JSON contains the saved
`api_key` and the new `provider_order`.
- [ ] First-time add of a new model name → no existing record, fallback
no-ops, behaves as before.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Refactor: speed up ragflow server, save startup memory, saved 200MiB,
and 5-9 seconds start time.
##### Before
1241292 | | \_ python3 api/ragflow_server.py
RAGFlow server is ready after 25.61845850944519s initialization.
##### After
1019968 | | \_ python3 api/ragflow_server.py
RAGFlow server is ready after 16.205134391784668s initialization.
### Type of change
- [x] Refactoring
### 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>
