rajib

changed cohere.py to update the default model of embedding

1

# The cohere embedding model do not use large, small. It is deprecated. Changed the modules default model Fixes # 4694 ## Before submitting ## Who can review? Community members...

### Issue you'd like to raise. The embedding models of cohere are 1. embed-english-light-v2.0 2. embed-english-v2.0 3. embed-multilingual-v2.0 The corresponding embedding wrapper in langchain will need to reflect that. Currently...

Created fix for 5475 Currently in PGvector, we do not have any function that returns the instance of an existing store. The from_documents always adds embeddings and then returns the...

The callback module openai_info does not have the correct model name for gpt-35-turbo

1

The openai_info.py does not have the correct model name for Azure Open AI. The model name is gpt-35-turbo. If you pass model name as gpt-3.5-turbo, then the code will fail...

### System Info If we do not pass the model_name in the AzureOpenAI() wrapper, it picks up text-davinci-003 as the default model which in turn makes the cost calculation of...

SelfQueryRetriever fails if lark is not installed, but the failure message is not meaningful

1

- Description: When we execute SelfQueryRetriever, it will fail if lark is not imported. But the failure message is not meaningful. It just says "TypeError: 'NoneType' object is not callable"....

The example was wrong. corrected it

I did not see a way to use models from AWS Bedrock to do the model graded evaluation. Is it possible to add that.

Add support for AzureOpenAI

8

I see that langkit is not supporting Azure Open AI. When can this be supported?

Latest langchain_community is giving an error "No MODULE PWD" while using TEXTLOADER

2

### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the LangChain documentation with the integrated search. - [X] I used...