### What problem does this PR solve?
Add model provider DeepInfra. This model list comes from our community.
NOTE: most endpoints haven't been tested, but they should work as OpenAI
does.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Based on https://github.com/infiniflow/ragflow/issues/8740
1. A better handle for 'NoneType' object is not subscriptable
2. Add some logs to get the internal message
### Type of change
- [x] Refactoring
fix: retry embedding with Qwen family models when limits temporarily
reached.
APIs of Qwen family models are limited by calling rates. When reached,
the "output" attribute of the "resp" will be None, and in turn cause
TypeError when trying to retrieve "embeddings". Since these limits are
almost temporary, I have added a simple retry mechanism to avoid it.
Besides, if retry_max reached, the error can be early raised, instead of
hidden behind "TypeError".
### What problem does this PR solve?
Sometimes Qwen blocks calling due to rate limits, but it will cause the
whole parsing procedure stops when creating knowledge base. In this
situation, resp["output"] will be None, and resp["output"]["embeddings"]
will cause TypeError. Since the limits are temporary, I apply a simple
retry mechanism to solve it.
### 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?
image_version: v0.19.1
This PR fixes a bug in the HuggingFaceEmBedding API method that was
causing AssertionError: assert len(vects) == len(docs) during the
document embedding process.
#### Problem
The HuggingFaceEmbed.encode() method had an early return statement
inside the for loop, causing it to return after processing only the
first text input instead of processing all texts in the input list.
**Error Messenge**
```python
AssertionError: assert len(vects) == len(docs) # input chunks != embedded vectors from embedding api
File "/ragflow/rag/svr/task_executor.py", line 442, in embedding
```
**Buggy code(/ragflow/rag/llm/embedding_model.py)**
```python
class HuggingFaceEmbed(Base):
def __init__(self, key, model_name, base_url=None):
if not model_name:
raise ValueError("Model name cannot be None")
self.key = key
self.model_name = model_name.split("___")[0]
self.base_url = base_url or "http://127.0.0.1:8080"
def encode(self, texts: list):
embeddings = []
for text in texts:
response = requests.post(...)
if response.status_code == 200:
try:
embedding = response.json()
embeddings.append(embedding[0])
# ❌ Early return
return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])
except Exception as _e:
log_exception(_e, response)
else:
raise Exception(...)
```
**Fixed Code(I just Rollback this function to the v0.19.0 version)**
```python
Class HuggingFaceEmbed(Base):
def __init__(self, key, model_name, base_url=None):
if not model_name:
raise ValueError("Model name cannot be None")
self.key = key
self.model_name = model_name.split("___")[0]
self.base_url = base_url or "http://127.0.0.1:8080"
def encode(self, texts: list):
embeddings = []
for text in texts:
response = requests.post(...)
if response.status_code == 200:
embedding = response.json()
embeddings.append(embedding[0]) # ✅ Only append, no return
else:
raise Exception(...)
return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts]) # ✅ Return after processing all
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Improve robustness of Jina, Nvidia, and SILICONFLOW embedding models by:
1. Adding try-catch blocks for JSON decode errors
2. Logging error details including response content
3. Raising exceptions with meaningful error messages
### Type of change
- [x] Refactoring
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6138
This PR is going to support vision llm for gpustack, modify url path
from `/v1-openai` to `/v1`
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix the error where the Ollama embeddings interface returns a “500
Internal Server Error” when using models such as xiaobu-embedding-v2 for
embedding.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This pull request includes changes to the initialization logic of the
`ChatModel` and `EmbeddingModel` classes to enhance the handling of AWS
credentials.
Use cases:
- Use env variables for credentials instead of managing them on the DB
- Easy connection when deploying on an AWS machine
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
### 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.
### What problem does this PR solve?
1. Change embedding model of knowledge base won't change the default
embedding model.
2. Retrieval test bug
### 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?
Refactor embedding batch_size. Close#3657
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### 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?
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>
### 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?
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>
### 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?
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>
### 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>
### 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)
### What problem does this PR solve?
#2469
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
