Validate Google PaLM integration Using the API key

[Barqawiz]

Intelli-node support Google PaLM through the following test branch: https://github.com/Barqawiz/IntelliNode/tree/google-palm

A call to test Google PaLM model

Google did not release the access to PaLM model except for some users, if you have access to Google generative models please help to test the integration.

1. Clone the repo: https://github.com/Barqawiz/IntelliNode/tree/google-palm
2. Create .env file in the root directory with the following key value: GOOGLE_API_KEY=your-key
3. Run from the root directory: node test/GoogleAIWrapper.test.js

Pre request:

• Node installation.
• Enable Generative AI from google console.
• Generate Google console API key.

Test Expectation:

• add the model response as comment to this issue.

[Barqawiz]

The API key feature is still not accessible for the public.

[ishaan-jaff]

Hi @Barqawiz @intelligentnode - I believe we can make this easier I’m the maintainer of LiteLLM - we allow you to deploy a LLM proxy to call 100+ LLMs in 1 format - PaLM, Bedrock, OpenAI, Anthropic etc https://github.com/BerriAI/litellm/tree/main/openai-proxy.

If this looks useful (we're used in production)- please let me know how we can help.

Usage

PaLM request

curl http://0.0.0.0:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "palm/chat-bison",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'

gpt-3.5-turbo request

curl http://0.0.0.0:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'

claude-2 request

curl http://0.0.0.0:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "claude-2",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'