Add support for Azure, OpenAI, Palm, Anthropic, Cohere Models - using litellm

[ishaan-jaff]

I'm the maintainer of litellm https://github.com/BerriAI/litellm - a simple & light package to call OpenAI, Azure, Cohere, Anthropic API Endpoints

This PR adds support for models from all the above mentioned providers

Here's a sample of how it's used:

from litellm import completion

## set ENV variables
# ENV variables can be set in .env file, too. Example in .env.example
os.environ["OPENAI_API_KEY"] = "openai key"
os.environ["COHERE_API_KEY"] = "cohere key"

messages = [{ "content": "Hello, how are you?","role": "user"}]

# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)

# cohere call
response = completion("command-nightly", messages)

# anthropic call
response = completion(model="claude-instant-1", messages=messages)

[ishaan-jaff]

@rmfan would love your feedback on this 😊

[rmfan]

Can you verify that for all the models, the responses are in the format:

({"Relevancy score": "an integer score out of 10", "Reasons for match": "1-2 sentence short reasonings"})

We've only tested this for gpt-3.5-turbo, and before we officially support any other LLM, we need to make sure that it will follow that format given the prompt in src/relevancy_prompt.txt

[ishaan-jaff]

for some lower quality models output is not guaranteed to always be
({"Relevancy score": "an integer score out of 10", "Reasons for match": "1-2 sentence short reasonings"})

perhaps we can add a check in the output text and see if it is
type==dict and ('Relevancy score' in output_dict and 'Reasons for match' in output_dict)

[ishaan-jaff]

this way - you can add support for new models while maintaining ur output guarantees