ChatWise Docs

Appearance

LiteLLM ​

LiteLLM gives you a unified API to access multiple LLMs (100+ LLMs)

Running LiteLLM ​

Pull the docker image:

bash
docker pull ghcr.io/berriai/litellm:main-latest

Create a config file in current directory or somewhere else litellm_config.yaml:

yaml
model_list:
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: azure/my_azure_deployment
      api_base: os.environ/AZURE_API_BASE
      api_key: "os.environ/AZURE_API_KEY"
      api_version: "2024-07-01-preview"

Starting the server:

bash
# replace PATH/TO with the path to your config file
docker run \
    -v PATH/TO/litellm_config.yaml:/app/config.yaml \
    -e AZURE_API_KEY=d6*********** \
    -e AZURE_API_BASE=https://openai-***********/ \
    -p 4000:4000 \
    ghcr.io/berriai/litellm:main-latest \
    --config /app/config.yaml --detailed_debug

# RUNNING on http://0.0.0.0:4000

Finally create an OpenAI-compatible provider on ChatWise, and enter the URL: