app.py

# import os
# import logging
# import requests
# from fastapi import FastAPI, HTTPException
# from fastapi.responses import StreamingResponse
# from pydantic import BaseModel
# from openai import OpenAI

# logging.basicConfig(level=logging.INFO)
# logger = logging.getLogger(__name__)

# app = FastAPI()
# MODEL_NAME = 'llama3.1:8b'

# OLLAMA_URL = "http://localhost:11434"


# # def create_model(query):
# #     message = [
# #         {"role": "system", "content": "You are a general chat bot."},
# #         {"role": "user", "content": f"{query}"}
# #     ]

# #     completion = ollama_client.chat.completions.create(
# #         model="llama3.1:8b",
# #         messages=message
# #         # response_format=base_model,
# #         #temperature = 0.1
# #     )
# #     return completion

# class Question(BaseModel):
#     text: str

# @app.get("/")
# def read_root():
#     return {"Hello": f"Welcome to {MODEL_NAME} FastAPI"}


# # # POST endpoint to query the LLM
# # @app.post("/ask")
# # async def ask_question(question: Question):
# #     try:
# #         response = create_model(question.text)
# #         return {"response": response}
# #     except Exception as e:
# #         raise HTTPException(status_code=500, detail=f"Error querying the model: {str(e)}")


# @app.get("/list_models")
# async def list_models():
#     """List all available models in Ollama."""
#     try:
#         response = requests.get(f"{OLLAMA_URL}/api/tags")
#     except Exception as e:
#         return {"error": str(e)}

#     return response.json()

# @app.post("/pull_model")
# async def pull_model(model_name: str):
#     """Pull a model from Ollama's repository."""
#     response = requests.post(f"{OLLAMA_URL}/api/pull", json={"name": model_name})
#     # print(response)

#     return response.json()


# @app.post("/generate")
# async def generate_text(model: str, prompt: str, system: str = "You are a helpful AI assistant.", stream: bool = False):
#     """Generate text from a given prompt using a specific model."""
#     try:
#         response =  requests.post(
#             f"{OLLAMA_URL}/api/generate",
#             json={"model": model, "prompt": prompt, "system": system, "stream": stream}
#         )
#     except Exception as e:
#         return {"error": str(e)}
#     # print(response)

#     return response.json()

# @app.post("/embed")
# async def get_embedding(model: str, text: str):
#     """Generate embeddings for the given text using a model."""
#     try:
#         response = requests.post(
#             f"{OLLAMA_URL}/api/embeddings",
#             json={"model": model, "prompt": text}
#         )
#     except Exception as e:
#         return {"error": str(e)}
#     # print(response)

#     return response.json()

# @app.post("/chat")
# async def chat(model: str, message: str, system: str = "You are a helpful chatbot."):
#     """Chat with the model while maintaining context."""
#     try:
#         response = requests.post(
#             f"{OLLAMA_URL}/api/chat",
#             json={"model": model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": message}]}
#         )
#     except Exception as e:
#         return {"error": str(e)}
#     # print(response)

#     return response.json()



# @app.on_event("startup")
# async def startup_event():
#     logger.info(f"Starting up with model: {MODEL_NAME}")

# @app.on_event("shutdown")
# async def shutdown_event():
#     logger.info("Shutting down")



# from fastapi import FastAPI
# import httpx

# app = FastAPI()
# TARGET_SERVER = "http://localhost:11434"

# @app.get("/proxy/{path:path}")
# async def get_proxy_request(path: str):
#     async with httpx.AsyncClient() as client:
#         response = await client.get(f"{TARGET_SERVER}/{path}")
#     return response.json()

# @app.post("/proxy/{path:path}")
# async def post_proxy_request(path: str):
#     async with httpx.AsyncClient() as client:
#         response = await client.post(f"{TARGET_SERVER}/{path}")
#     return response.json()


from fastapi import FastAPI
import httpx
from pydantic import BaseModel
from OpenAIClasses import ChatCompletionRequest

class RequestBody(BaseModel):
    data: dict

app = FastAPI()
TARGET_SERVER = "http://localhost:11434"

@app.get("/proxy/{path:path}")
async def proxy_get(path: str):
    """ Forwards GET requests to the target server """
    async with httpx.AsyncClient() as client:
        response = await client.get(f"{TARGET_SERVER}/{path}")
    return response.json()

@app.post("/proxy/{path:path}")
async def proxy_post(path: str, request_body: RequestBody):
    # print(request_body)
    # print(request_body.model_dump())
    """ Forwards POST requests to the target server """
    try:
        data = request_body.model_dump()["data"]
    
        async with httpx.AsyncClient() as client:
            response = await client.post(f"{TARGET_SERVER}/{path}", json=data, timeout=120)
        return response.json()
    except Exception as e:
        print(e)
        return {"error": str(e)}


@app.post("/openai_compatible/chat/completions")
async def openai_compatible(request_body: ChatCompletionRequest):

    """ Forwards POST requests to the target server """
    try:
        data = request_body.model_dump()

        async with httpx.AsyncClient() as client:
            response = await client.post(f"{TARGET_SERVER}/api/chat", json=data, timeout=120)
        print(response.json())
        return {"choices": [response.json()]}
    except Exception as e:
        print(e)
        return {"error": str(e)}