625 Commits

Author SHA1 Message Date
zhxlp
00c7ddbc9b
Fix: The max tokens defined by the tenant are not used (#4297) (#2817) (#5066)
### What problem does this PR solve?

Fix: The max tokens defined by the tenant are not used (#4297) (#2817)


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-02-18 13:42:22 +08:00
Kevin Hu
84b4b38cbb
Remove <think> for exeSql component. (#5069)
### What problem does this PR solve?

#5061
#5067

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-18 13:39:37 +08:00
flygithub
409310aae9
Update agent session API, to support uploading files while create a new session (#5039)
### What problem does this PR solve?
Update the agent session API "POST /api/v1/agents/{agent_id}/sessions",
to support uploading files while create a new session:
- currently, the API only supports requesting with a json body. If user
wants to upload a doc or image when create session, like what is already
supported on the web client, we need to update the API.
- if upload an image, ragflow will call image2text, and a user_id is
needed for the image2text model. So we need to send user_id in the API
request. As form-data is needed to upload files, not json body, seems we
need to put the user_id in the url as an optional parameter (currently
user_id is an optional in json body).


### Type of change

- [x] Documentation Update
- [x] Other (please describe):
2025-02-18 09:45:40 +08:00
Kevin Hu
9ff825f39d
Ignore exceptions when no index ahead. (#5047)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2025-02-18 09:09:22 +08:00
hy89
7b5d831296
Fix: Starting the source code on Windows, the 'HTTP API' returns 404 (#5042)
Fix: When starting the backend service from source code on Windows, the
"HTTP API" no longer returns 404.
2025-02-17 19:33:49 +08:00
Kevin Hu
e4096fbc33
Add another decrypt function. (#5043)
### What problem does this PR solve?



### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-02-17 18:09:11 +08:00
Kevin Hu
3aa5c2a699
Ignore exception of empty index. (#5030)
### What problem does this PR solve?

### Type of change


- [x] Refactoring
2025-02-17 15:59:55 +08:00
kuschzzp
88daa349f9
Optimize conversation when uploading attachments (#4964)
### What problem does this PR solve?

#4929

### Type of change

- [x] Performance Improvement
2025-02-17 12:03:04 +08:00
zhxlp
194e8ea696
Fix knowledge graph node not found (#4968) (#4970)
### What problem does this PR solve?

Fix knowledge graph node not found (#4968)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-17 11:49:27 +08:00
Kevin Hu
810f997276
Fix <think> in keywords or question auto-generations. (#5021)
### What problem does this PR solve?

**#4983**

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-17 11:20:57 +08:00
Kevin Hu
849d9eb463
Ignore tenant not found error while increasing token usage. (#4950)
### What problem does this PR solve?

#4940

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-14 11:10:49 +08:00
Peterson Alves
042f4c90c6
Fixes KeyError: 'content' when using stream=False (#4944)
### 🛠 Fixes `KeyError: 'content'` when using `stream=False`

#### 🔍 Problem  
When calling the chat API with `stream=False`, the code attempts to
access `msg[-1]["content"]` without verifying if the key exists. This
causes a `KeyError` when the message structure does not contain
`"content"`.

This issue was discussed in
[#4885](https://github.com/infiniflow/ragflow/issues/4885), where we
analyzed the root cause. The error does not occur with `stream=True`, as
the response is processed differently.

####  Solution  
- **Logging Fix:**  
  - Before accessing `msg[-1]["content"]`, we check if the key exists.  
- If it does not exist, a default value (`"[content not available]"`) is
used to prevent errors.

- **Structural Fix in `msg` Construction:**  
- Ensured that every message in `msg` contains the `"content"` key, even
if empty.
- This fixes the issue at its root and ensures consistent behavior
between `stream=True` and `stream=False`.

#### 🔄 Impact  
- Prevents the `KeyError` without affecting normal application flow.  
- Ensures the integrity of the `msg` structure, avoiding future
failures.



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-14 10:27:01 +08:00
Kevin Hu
78982d88e0
Reformat error message. (#4829)
### What problem does this PR solve?

#4828

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-10 16:47:53 +08:00
Kevin Hu
6fa34d5532
Fix KG circle. (#4823)
### What problem does this PR solve?

#4760

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-10 11:02:29 +08:00
davidche
588207d7c1
optimize TenantLLMService.increase_usage for "can't update token usag… (#4755)
…e error " message

### What problem does this PR solve?

optimize TenantLLMService.increase_usage Performance

### Type of change

- [x] Performance Improvement

Co-authored-by: che_shuai <che_shuai@massclouds.com>
2025-02-07 12:16:17 +08:00
Kevin Hu
4b9c4c0705
Update deepseek model provider info. (#4714)
### What problem does this PR solve?


### Type of change

- [x] Refactoring
2025-02-05 13:43:40 +08:00
Kevin Hu
c354239b79
Make infinity adapt to condition exist. (#4657)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-26 18:45:36 +08:00
Kevin Hu
898ae7fa80
Fix missplace for vector sim weight and token sim weight. (#4627)
### What problem does this PR solve?

#4610

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-24 12:41:06 +08:00
Kevin Hu
e9ccba0395
Add timestamp to messages (#4624)
### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-24 11:07:55 +08:00
Kevin Hu
e14d6ae441
Refactor. (#4612)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2025-01-23 18:56:02 +08:00
Kevin Hu
86892959a0
Rebuild graph when it's out of time. (#4607)
### What problem does this PR solve?

#4543

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2025-01-23 17:26:20 +08:00
Zhichang Yu
240e7d7c22
Unified user_service.py (#4606)
### What problem does this PR solve?

Unified user_service.py

### Type of change

- [x] Refactoring
2025-01-23 15:49:21 +08:00
Kevin Hu
c4b9e903c8
Fix index not found for new user. (#4597)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-23 11:45:22 +08:00
Kevin Hu
dd0ebbea35
Light GraphRAG (#4585)
### What problem does this PR solve?

#4543

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-22 19:43:14 +08:00
Jin Hai
3894de895b
Update comments (#4569)
### What problem does this PR solve?

Add license statement.

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-01-21 20:52:28 +08:00
Kevin Hu
f4d084bcf1
Fix doc progress issue. (#4520)
### What problem does this PR solve?

#4516
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-17 18:28:15 +08:00
Alex Chen
7944aacafa
Feat: add gpustack model provider (#4469)
### What problem does this PR solve?

Add GPUStack as a new model provider.
[GPUStack](https://github.com/gpustack/gpustack) is an open-source GPU
cluster manager for running LLMs. Currently, locally deployed models in
GPUStack cannot integrate well with RAGFlow. GPUStack provides both
OpenAI compatible APIs (Models / Chat Completions / Embeddings /
Speech2Text / TTS) and other APIs like Rerank. We would like to use
GPUStack as a model provider in ragflow.

[GPUStack Docs](https://docs.gpustack.ai/latest/quickstart/)

Related issue: https://github.com/infiniflow/ragflow/issues/4064.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)



### Testing Instructions
1. Install GPUStack and deploy the `llama-3.2-1b-instruct` llm, `bge-m3`
text embedding model, `bge-reranker-v2-m3` rerank model,
`faster-whisper-medium` Speech-to-Text model, `cosyvoice-300m-sft` in
GPUStack.
2. Add provider in ragflow settings.
3. Testing in ragflow.
2025-01-15 14:15:58 +08:00
Kevin Hu
e478586a8e
Refactor. (#4487)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2025-01-15 14:06:46 +08:00
Kevin Hu
f556f0239c
Fix dify retrieval issue. (#4473)
### What problem does this PR solve?

#4464
#4469 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-14 13:16:05 +08:00
Kevin Hu
f318342c8e
Recalling the file uploaded while chatting. (#4472)
### What problem does this PR solve?

#4445

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-14 12:05:20 +08:00
Kevin Hu
c08382099a
Check meta data format in json map (#4461)
### What problem does this PR solve?

#3690

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-13 17:34:50 +08:00
Kevin Hu
46c52d65b7
Add meta data while chatting. (#4455)
### What problem does this PR solve?

#3690

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-13 14:35:24 +08:00
Kevin Hu
7d909d4d1b
Add doc meta data. (#4442)
### What problem does this PR solve?

#3690

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-10 19:06:59 +08:00
Kevin Hu
c5da3cdd97
Tagging (#4426)
### What problem does this PR solve?

#4367

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-09 17:07:21 +08:00
Kevin Hu
f892d7d426
Let the agent talk while there's pre-set param. (#4423)
### What problem does this PR solve?

#4385

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-09 14:07:57 +08:00
Kevin Hu
3d66d78304
Fix API retrieval error. (#4408)
### What problem does this PR solve?

#4403

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-08 11:27:46 +08:00
Kevin Hu
52c20033d7
Fix total number error. (#4339)
### What problem does this PR solve?

#4328

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-03 10:02:30 +08:00
liuhua
8674156d1c
Fix potential SSRF attack vulnerability (#4334)
### What problem does this PR solve?

Fix potential SSRF attack vulnerability

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2025-01-02 18:45:45 +08:00
liuhua
df22ead841
Fix agent_completion bug (#4329)
### What problem does this PR solve?

Fix agent_completion bug  #4320

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-01-02 16:59:54 +08:00
Kevin Hu
5071df9de1
Fix parameter name error. (#4312)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-31 17:38:01 +08:00
liuhua
7c7b7d2689
Update error message for agent name conflict (#4299)
### What problem does this PR solve?

Update error message for agent name conflict

### Type of change

- [x] Refactoring

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-12-31 14:36:23 +08:00
Kevin Hu
4ba4f622a5
Refactor (#4303)
### What problem does this PR solve?

### Type of change
- [x] Refactoring
2024-12-31 14:31:31 +08:00
liuhua
b52b0f68fc
Add top_k for create_chat and update_chat api (#4294)
### What problem does this PR solve?

Add top_k for create_chat and update_chat api #4157

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-12-30 19:22:57 +08:00
liuhua
d42e78bce2
Fix bugs in chunk api (#4293)
### What problem does this PR solve?

Fix bugs in chunk api #4149

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
2024-12-30 19:01:44 +08:00
Kevin Hu
8fb18f37f6
Code refactor. (#4291)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-12-30 18:38:51 +08:00
Kevin Hu
3ba2b8d80f
Fix agent session list by user_id. (#4285)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-30 12:18:16 +08:00
Kevin Hu
798eb3647c
Fix chat listing error. (#4270)
### What problem does this PR solve?

#4220
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-27 16:03:59 +08:00
Kevin Hu
c3e3f0fbb4
Add iteration for agent. (#4258)
### What problem does this PR solve?

#4242
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-12-27 11:38:33 +08:00
Kevin Hu
097aab09a2
Replace image2text model check with internal image. (#4250)
### What problem does this PR solve?

#4243

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-26 19:46:42 +08:00
Jin Hai
722545e5e0
Fix bugs (#4241)
### What problem does this PR solve?

1. Refactor error message
2. Fix knowledges are created on ES and can't be found in Infinity. The
document chunk fetch error.

### Type of change

- [x] Fix bug
- [x] Refactoring

---------

Signed-off-by: jinhai <haijin.chn@gmail.com>
2024-12-26 16:08:17 +08:00