Upload 3 files

Dockerfile

@@ -1,38 +1,37 @@
-# Use Ubuntu as the base image
-FROM ubuntu:22.04
-
-# Set the working directory in the container
-WORKDIR /app
-
-# Ensure we are running as root
-USER root
-
-# Install system dependencies and Python
-RUN apt-get update && apt-get install -y \
-    python3 \
-    python3-pip \
-    curl \
-    && rm -rf /var/lib/apt/lists/*
-
-# Set Python3 as the default
-RUN ln -s /usr/bin/python3 /usr/bin/python
-
-# Copy the requirements file and install dependencies
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Install Ollama
-RUN curl -fsSL https://ollama.com/install.sh | bash
-
-# Ensure Ollama is in the system path
-ENV PATH="/root/.ollama/bin:$PATH"
-
-
-# Copy the application files
-COPY . .
-
-# Expose the FastAPI default port
-EXPOSE 8000
-
-# Start Ollama and FastAPI as root
-CMD ["sh", "-c", "ollama serve & sleep 5 && ollama pull llama3 && uvicorn main:app --host 0.0.0.0 --port 8000"]
+# Use Ubuntu as the base image
+FROM ubuntu:22.04
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies and Python
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set Python3 as the default
+RUN ln -s /usr/bin/python3 /usr/bin/python
+
+# Install Ollama
+RUN curl -fsSL https://ollama.com/install.sh | bash
+
+# Ensure Ollama is in the system path
+ENV PATH="/root/.ollama/bin:$PATH"
+
+# Pre-download the Llama3 model to avoid downloading it at runtime
+RUN ollama serve & sleep 5 && ollama pull llama3
+
+# Copy the requirements file and install dependencies
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application files
+COPY . .
+
+# Expose the FastAPI default port
+EXPOSE 8000
+
+# Start Ollama and FastAPI
+CMD ["sh", "-c", "ollama serve & uvicorn main:app --host 0.0.0.0 --port 8000"]

main.py

@@ -1,37 +1,14 @@
-from fastapi import FastAPI, HTTPException, Depends, Header, Request
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from langchain_community.llms import Ollama  # Correct Import
-import os
 import logging
 import time  # Import time module
-from dotenv import load_dotenv
-
-# Load environment variables
-load_dotenv()
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 
-# API keys from .env
-API_KEYS = {
-    "user1": os.getenv("API_KEY_USER1"),
-    "user2": os.getenv("API_KEY_USER2"),
-}
-
 app = FastAPI()
 
-# API Key Authentication
-def verify_api_key(request: Request, api_key: str = Header(None, alias="X-API-Key")):
-    logging.info(f"Received Headers: {request.headers}")  # Log headers
-    if not api_key:
-        raise HTTPException(status_code=401, detail="API key is missing")
-
-    api_key = api_key.strip()
-    if api_key not in API_KEYS.values():
-        raise HTTPException(status_code=401, detail="Invalid API key")
-
-    return api_key
-
 # OpenAI-compatible request format
 class OpenAIRequest(BaseModel):
     model: str
@@ -42,12 +19,8 @@ class OpenAIRequest(BaseModel):
 def get_llm(model_name: str):
     return Ollama(model=model_name)
 
-@app.get("/")
-def home():
-    return {"message": "OpenAI-compatible LangChain + Ollama API is running"}
-
 @app.post("/v1/chat/completions")
-def generate_text(request: OpenAIRequest, api_key: str = Depends(verify_api_key)):
+def generate_text(request: OpenAIRequest):
     try:
         llm = get_llm(request.model)
 
@@ -62,7 +35,7 @@ def generate_text(request: OpenAIRequest, api_key: str = Depends(verify_api_key)
         response = {
             "id": "chatcmpl-123",
             "object": "chat.completion",
-            "created": int(time.time()),  # FIXED: Using time.time() instead of os.time()
+            "created": int(time.time()),
             "model": request.model,
             "choices": [
                 {
@@ -82,4 +55,4 @@ def generate_text(request: OpenAIRequest, api_key: str = Depends(verify_api_key)
 
     except Exception as e:
         logging.error(f"Error generating response: {e}")
-        raise HTTPException(status_code=500, detail="Internal server error")
+        raise HTTPException(status_code=500, detail="Internal server error")

requirements.txt

@@ -5,4 +5,4 @@ langchain
 requests
 langchain_community 
 python-dotenv 
-cloudflared
+cloudflared