Update app.py

app.py

@@ -1,147 +1,147 @@
-from fastapi import FastAPI, UploadFile, Form, HTTPException
-from pydantic import BaseModel
-import uvicorn
-from fastapi.responses import JSONResponse
-from typing import Dict
-import hashlib
-from pypdf import PdfReader
-from dotenv import load_dotenv, dotenv_values 
-import aiofiles
-from pathlib import Path
-from langchain_community.document_loaders import WebBaseLoader
-import google.generativeai as genai
-import os
-import re
-from fastapi.middleware.cors import CORSMiddleware
-
-# Initialize Gemini LLM
-load_dotenv()
-Google_key = os.getenv("GOOGLE_API_KEY")
-model = genai.GenerativeModel("gemini-1.5-flash")
-print(str(Google_key))
-genai.configure(api_key="AIzaSyC1-QUzA45IlCosX__sKlzNAgVZGEaHc0c")
-
-app = FastAPI()
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-def generate_content(url):
-    loader = WebBaseLoader(str(url))
-    data = loader.load()
-    formatted_text = data[0].page_content.strip().replace("\n\n", "\n")
-    cleaned_text = re.sub(r"\s+", " ", formatted_text)
-    cleaned_text = re.sub(r"\n+", "\n\n", cleaned_text)
-    return cleaned_text
-
-
-# Dictionary to store processed content
-processed_data: Dict[str, str] = {}
-
-
-
-
-def generate_chat_id(content: str) -> str:
-    return hashlib.md5(content.encode()).hexdigest()
-
-
-
-class ProcessURLRequest(BaseModel):
-    url: str
-
-
-@app.post("/process_url")
-async def process_url(request: ProcessURLRequest):
-    # Simulated web scraping for demonstration
-    scraped_content = f"Scraped content from URL: {generate_content(request.url)}"
-    chat_id = generate_chat_id(scraped_content)
-    
-    processed_data[chat_id] = scraped_content
-    
-    return JSONResponse(
-        content={"chat_id": chat_id, "message": "URL content processed and stored successfully."}
-    )
-
-
-# API Endpoint 2: Process PDF Document
-@app.post("/process_pdf")
-async def process_pdf(file: UploadFile):
-    if not file.filename.endswith(".pdf"):
-        raise HTTPException(status_code=400, detail="Only PDF files are supported.")
-
-    # Save uploaded file temporarily
-    temp_file = Path(f"temp_{file.filename}")
-    async with aiofiles.open(temp_file, "wb") as out_file:
-        content = await file.read()
-        await out_file.write(content)
-
-    reader = PdfReader(temp_file)
-    pg_l = len(reader.pages)
-    text = ""
-    for i in range(pg_l
-                   
-                   ):
-        page = reader.pages[i]
-        text += page.extract_text()
-
-    extracted_text = text
-
-
-    chat_id = generate_chat_id(extracted_text)
-
-    processed_data[chat_id] = extracted_text
-
-    temp_file.unlink()
-
-    return JSONResponse(
-        content={"chat_id": chat_id, "message": "PDF content processed and stored successfully."}
-    )
-
-
-# API Endpoint 3: Chat API
-class ChatRequest(BaseModel):
-    chat_id: str
-    question: str
-
-
-@app.post("/chat")
-async def chat(request: ChatRequest):
-    chat_id = request.chat_id
-    question = request.question
-
-    # Retrieve the stored content
-    if chat_id not in processed_data:
-        raise HTTPException(status_code=404, detail="Chat ID not found.")
-
-    stored_content = processed_data[chat_id]
-    response = model.generate_content(f"""You are a highly accurate and context-driven LLM tasked with generating precise responses based solely on the provided context. Your goal is to synthesize information exclusively from the given context to respond directly and comprehensively to the question.
-
-Inputs:
-
-Question: {question}
-Context: {stored_content}
-Task:
-
-Carefully analyze the provided context.
-Construct an accurate and relevant response to the question.
-Ensure that the response strictly adheres to the given context, without introducing external information, assumptions, or unsupported content.
-Evaluation Criteria:
-
-Responses must demonstrate strict adherence to the provided context.
-Focus on clarity, precision, and relevance.
-Avoid any content not explicitly supported by the context..""")
-
-
-
-    response_text = f"{response.text}"
-
-    return JSONResponse(content={"response": response_text})
-
-
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+from fastapi import FastAPI, UploadFile, Form, HTTPException
+from pydantic import BaseModel
+import uvicorn
+from fastapi.responses import JSONResponse
+from typing import Dict
+import hashlib
+from pypdf import PdfReader
+from dotenv import load_dotenv, dotenv_values 
+import aiofiles
+from pathlib import Path
+from langchain_community.document_loaders import WebBaseLoader
+import google.generativeai as genai
+import os
+import re
+from fastapi.middleware.cors import CORSMiddleware
+
+# Initialize Gemini LLM
+load_dotenv()
+Google_key = os.getenv("GOOGLE_API_KEY")
+model = genai.GenerativeModel("gemini-1.5-flash")
+print(str(Google_key))
+genai.configure(api_key="AIzaSyC1-QUzA45IlCosX__sKlzNAgVZGEaHc0c")
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+def generate_content(url):
+    loader = WebBaseLoader(str(url))
+    data = loader.load()
+    formatted_text = data[0].page_content.strip().replace("\n\n", "\n")
+    cleaned_text = re.sub(r"\s+", " ", formatted_text)
+    cleaned_text = re.sub(r"\n+", "\n\n", cleaned_text)
+    return cleaned_text
+
+
+# Dictionary to store processed content
+processed_data: Dict[str, str] = {}
+
+
+
+
+def generate_chat_id(content: str) -> str:
+    return hashlib.md5(content.encode()).hexdigest()
+
+
+
+class ProcessURLRequest(BaseModel):
+    url: str
+
+
+@app.post("/process_url")
+async def process_url(request: ProcessURLRequest):
+    # Simulated web scraping for demonstration
+    scraped_content = f"Scraped content from URL: {generate_content(request.url)}"
+    chat_id = generate_chat_id(scraped_content)
+    
+    processed_data[chat_id] = scraped_content
+    
+    return JSONResponse(
+        content={"chat_id": chat_id, "message": "URL content processed and stored successfully."}
+    )
+
+
+# API Endpoint 2: Process PDF Document
+@app.post("/process_pdf")
+async def process_pdf(file: UploadFile):
+    if not file.filename.endswith(".pdf"):
+        raise HTTPException(status_code=400, detail="Only PDF files are supported.")
+
+    # Save uploaded file temporarily
+    temp_file = Path(f"temp_{file.filename}")
+    async with aiofiles.open(temp_file, "wb") as out_file:
+        content = await file.read()
+        await out_file.write(content)
+
+    reader = PdfReader(temp_file)
+    pg_l = len(reader.pages)
+    text = ""
+    for i in range(pg_l
+                   
+                   ):
+        page = reader.pages[i]
+        text += page.extract_text()
+
+    extracted_text = text
+
+
+    chat_id = generate_chat_id(extracted_text)
+
+    processed_data[chat_id] = extracted_text
+
+    temp_file.unlink()
+
+    return JSONResponse(
+        content={"chat_id": chat_id, "message": "PDF content processed and stored successfully."}
+    )
+
+
+# API Endpoint 3: Chat API
+class ChatRequest(BaseModel):
+    chat_id: str
+    question: str
+
+
+@app.post("/chat")
+async def chat(request: ChatRequest):
+    chat_id = request.chat_id
+    question = request.question
+
+    # Retrieve the stored content
+    if chat_id not in processed_data:
+        raise HTTPException(status_code=404, detail="Chat ID not found.")
+
+    stored_content = processed_data[chat_id]
+    response = model.generate_content(f"""You are a highly accurate and context-driven LLM tasked with generating precise responses based solely on the provided context. Your goal is to synthesize information exclusively from the given context to respond directly and comprehensively to the question.
+
+Inputs:
+
+Question: {question}
+Context: {stored_content}
+Task:
+
+Carefully analyze the provided context.
+Construct an accurate and relevant response to the question.
+Ensure that the response strictly adheres to the given context, without introducing external information, assumptions, or unsupported content.
+Evaluation Criteria:
+
+Responses must demonstrate strict adherence to the provided context.
+Focus on clarity, precision, and relevance.
+Avoid any content not explicitly supported by the context..""")
+
+
+
+    response_text = f"{response.text}"
+
+    return JSONResponse(content={"response": response_text})
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)