### What problem does this PR solve?
Refactor embedding batch_size. Close #3657
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
Detect invalid response from api.siliconflow.cn (#3792)
### What problem does this PR solve?
Detect invalid response from api.siliconflow.cn. Close #2643
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
add new models in jinna connector, to allow use models that support
multilingual models
### Type of change
- [X] Other (please describe): new connectors no breaking change
### What problem does this PR solve?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix a bug in VolcEngine #3553
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
when qwen rerank model not return ok, raise exception to notice user (#3593)
### What problem does this PR solve?
When calling the Qwen rerank model, if the model does not return
correctly, an exception should be raised to notify the user, rather than
simply returning a value of 0, as this would be confusing to the user.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Add api for sessions and add max_tokens for tenant_llm (#3472)
### What problem does this PR solve?
Add api for sessions and add max_tokens for tenant_llm
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
### What problem does this PR solve?
Introduced [beartype](https://github.com/beartype/beartype) for runtime
type-checking.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Hi there!
LocalAI added support of rerank models
https://localai.io/features/reranker/
I've implemented LocalAIRerank class (typically copied it from
OpenAI_APIRerank class).
Also, LocalAI model response with 500 error code if len of "documents"
is less than 2 in similarity check.
So I've added the second "document" on RERANK model connection check in
`api/apps/llm_app.py`.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Move settings initialization after module init phase (#3438)
### What problem does this PR solve?
1. Module init won't connect database any more.
2. Config in settings need to be used with settings.CONFIG_NAME
### Type of change
- [x] Refactoring
Signed-off-by: jinhai <haijin.chn@gmail.com>
Use consistent log file names, introduced initLogger (#3403)
### What problem does this PR solve?
Use consistent log file names, introduced initLogger
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
This pull request fixes the issue mentioned in
https://github.com/infiniflow/ragflow/issues/3263.
1. response should be parsed as dict, prevent the following code from
failing to take values:
ans = response["content"][0]["text"]
2. API Model ```claude-instant-1.2``` has retired (by
[model-deprecations](https://docs.anthropic.com/en/docs/resources/model-deprecations)),
it will trigger errors in the code, so I deleted it from the
conf/llm_factories.json file and updated the latest API Model
```claude-3-5-sonnet-20241022```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: chenhaodong <chenhaodong@ctrlvideo.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
When model’s group name contains 0-9，we can't find downloaded
model，because we do not correctly exstract model dir's name from model‘s
full name
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: 王志鹏 <zhipeng3.wang@midea.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
[Bug]: unnecessary auto-increment calculations in the tokens statistics of the chat model (#2969)
### What problem does this PR solve?
the details is shown in
https://github.com/infiniflow/ragflow/issues/2968
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
[Bug]: When use OpenAI chat model , raise ERROR: 'CompletionUsage' object has no attribute 'get' #2948 (#2949)
[Bug]: When use OpenAI chat model , raise ERROR: 'CompletionUsage'
object has no attribute 'get' #2948
### What problem does this PR solve?
the detail of this PR is shown at
https://github.com/infiniflow/ragflow/issues/2948
### 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?
1. fix: mid map show error in knowledge graph, juse because
```@antv/g6```version changed
2. feat: concurrent threads configuration support in graph extractor
3. fix: used tokens update failed for tenant
4. feat: timeout configuration support for llm
5. fix: regex error in graph extractor
6. feat: qwen rerank(```gte-rerank```) support
7. fix: timeout deal in knowledge graph index process. Now chat by
stream output, also, it is configuratable.
8. feat: ```qwen-long``` model configuration
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: chongchuanbing <chongchuanbing@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Resolves #2905 openai compatible model provider add llama.cpp rerank support (#2906)
### What problem does this PR solve?
Resolve #2905
due to the in-consistent of token size, I make it safe to limit 500 in
code, since there is no config param to control
my llama.cpp run set -ub to 1024:
${llama_path}/bin/llama-server --host 0.0.0.0 --port 9901 -ub 1024 -ngl
99 -m $gguf_file --reranking "$@"
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Here is my test Ragflow use llama.cpp
```
lot update_slots: id 0 | task 458 | prompt done, n_past = 416, n_tokens = 416
slot release: id 0 | task 458 | stop processing: n_past = 416, truncated = 0
slot launch_slot_: id 0 | task 459 | processing task
slot update_slots: id 0 | task 459 | tokenizing prompt, len = 2
slot update_slots: id 0 | task 459 | prompt tokenized, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 111
slot update_slots: id 0 | task 459 | kv cache rm [0, end)
slot update_slots: id 0 | task 459 | prompt processing progress, n_past = 111, n_tokens = 111, progress = 1.000000
slot update_slots: id 0 | task 459 | prompt done, n_past = 111, n_tokens = 111
slot release: id 0 | task 459 | stop processing: n_past = 111, truncated = 0
srv update_slots: all slots are idle
request: POST /rerank 172.23.0.4 200
```
Fix keys of Xinference deployed models, especially has the same model name with public hosted models. (#2832)
### What problem does this PR solve?
Fix keys of Xinference deployed models, especially has the same model
name with public hosted models.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: 0000sir <0000sir@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
support api-version and change default-model in adding azure-openai and openai (#2799)
### What problem does this PR solve?
#2701#2712#2749
### Type of change
-[x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Adding a Bedrock API key for Claude Sonnet was broken. I find the issue
came up when trying to test the LLM configuration, the system is a
required parameter in boto3.
As well, there were problems in Bedrock implementation for embeddings
when trying to encode queries.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
Zhichang Yu
Kevin Hu
Jin Hai
devMls
liuhua
liwenju0
shizzgar
shijiefengjun
roc king
ksztone-huanggonghao
Yinquan WANG
chongchuanbing
Ziyu Huang
0000sir
JobSmithManipulation
Sky Blue
Omar Leonardo Sanchez Granados