stanford-futuredata / frugalgpt Goto Github PK

messages=[
      {
        "role": "system",
        "content": prompt,
      },
      {
          "role": "assistant",
          "content": "AI: Message"
      },
      {
          "role": "user",
          "content": "CX: Message"
      },
      {
          "role": "assistant",
          "content": "AI: Message"
      },
      {
          "role": "user",
          "content": "CX: Message"
      },
      {
          "role": "assistant",
          "content": "AI: Message"
      },
      {
          "role": "user",
          "content": "CX: Message"
      },
      {
          "role": "assistant",
          "content": "AI: Message"
      },
      {
          "role": "user",
          "content": "CX: Message"
      },
      {
          "role": "assistant",
          "content": "AI: Message"
      },
      {
          "role": "user",
          "content": "CX: Message"
      },
    ],

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["ANTHROPIC_API_KEY"] = "anthropic key"

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

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

# anthropic call
response = completion("claude-v-2", messages)