pip install fastapi uvicorn pydantic

python mock_prompt_management_server.py

# Get a prompt
curl "http://localhost:8080/beta/litellm_prompt_management?prompt_id=hello-world-prompt"

# Get a prompt with authentication
curl "http://localhost:8080/beta/litellm_prompt_management?prompt_id=hello-world-prompt" \
  -H "Authorization: Bearer test-token-12345"

# List all prompts
curl "http://localhost:8080/prompts"

# Get prompt variables
curl "http://localhost:8080/prompts/hello-world-prompt/variables"

model_list:
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: openai/gpt-3.5-turbo
      api_key: os.environ/OPENAI_API_KEY

prompts:
  - prompt_id: "hello-world-prompt"
    litellm_params:
      prompt_integration: "generic_prompt_management"
      api_base: http://localhost:8080
      api_key: test-token-12345

litellm --config config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-3.5-turbo",
    "prompt_id": "hello-world-prompt",
    "prompt_variables": {
      "domain": "data science",
      "task": "analyzing customer behavior"
    },
    "messages": [
      {"role": "user", "content": "Please help me get started"}
    ]
  }'

{
  "prompt_id": "hello-world-prompt",
  "prompt_template": [
    {
      "role": "system",
      "content": "You are a helpful assistant specialized in {domain}."
    },
    {
      "role": "user",
      "content": "Help me with: {task}"
    }
  ],
  "prompt_template_model": "gpt-4",
  "prompt_template_optional_params": {
    "temperature": 0.7,
    "max_tokens": 500
  }
}

python mock_prompt_management_server.py

from litellm import completion

# The completion will:
# 1. Fetch the prompt from your API
# 2. Replace {domain} with "machine learning"
# 3. Replace {task} with "building a recommendation system"
# 4. Merge with your messages
# 5. Use the model and params from the prompt

response = completion(
    model="gpt-4",
    prompt_id="hello-world-prompt",
    prompt_variables={
        "domain": "machine learning",
        "task": "building a recommendation system"
    },
    messages=[
        {"role": "user", "content": "I have user behavior data from the past year."}
    ],
    # Configure the generic prompt manager
    generic_prompt_config={
        "api_base": "http://localhost:8080",
        "api_key": "test-token-12345",
    }
)

print(response.choices[0].message.content)

PROMPTS_DB = {
    "my-custom-prompt": {
        "prompt_id": "my-custom-prompt",
        "prompt_template": [
            {
                "role": "system",
                "content": "You are a {role}."
            },
            {
                "role": "user",
                "content": "{user_input}"
            }
        ],
        "prompt_template_model": "gpt-4",
        "prompt_template_optional_params": {
            "temperature": 0.8,
            "max_tokens": 1000
        }
    }
}

@app.get("/beta/litellm_prompt_management")
async def get_prompt(prompt_id: str):
    # Fetch from database
    prompt = await db.prompts.find_one({"prompt_id": prompt_id})
    
    if not prompt:
        raise HTTPException(status_code=404, detail="Prompt not found")
    
    return PromptResponse(**prompt)

@app.get("/beta/litellm_prompt_management")
async def get_prompt(
    prompt_id: str,
    project_name: Optional[str] = None,
    user_id: Optional[str] = None,
    authorization: Optional[str] = Header(None)
):
    token = verify_api_key(authorization)
    
    # Check if user has access to this project
    if not has_project_access(token, project_name):
        raise HTTPException(status_code=403, detail="Access denied")
    
    # Fetch and return prompt
    ...