Add support for Azure OpenAI, Palm, Replicate, Sagemaker (100+LLMs) - using litellm

[ishaan-jaff]

This PR adds support for the above mentioned LLMs using LiteLLM https://github.com/BerriAI/litellm/
Example

from litellm import completion

## set ENV variables
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]

@rentainhe can you take a look at this PR when you get the chance?

Happy to add more docs/testing if this initial commit looks good😊

[rentainhe]

This PR looks very nice. Would you be willing to add more judgment conditions and documentation? If users have not installed light-llm, they can use the original API provided by OpenAI. @ishaan-jaff

[ishaan-jaff]

yes @rentainhe

can you provide some guidance on what changes you'd like me to add ?

[rentainhe]

yes @rentainhe

can you provide some guidance on what changes you'd like me to add ?

Hello! Maybe you can try to use:

try:
    import lightllm
    HAS_LIGHTLLM = True
except:
    HAS_LIGHTLLM = False

Try to use a flag to control it, which may be better for the users who did not install lightllm, they can use openai original API instead of it

@ishaan-jaff

But I think I can merge this PR first, maybe you can try to update it later if you think this is a better solution~

[rentainhe]

It would be very nice for u to add more documentation (maybe in README) about this update! You can try to update the requirements.txt to inform the users to install litellm