main.py

from fastapi import FastAPI, UploadFile, File, Form
from fastapi.responses import JSONResponse
from pydantic import BaseModel
from groq import Groq
from langchain_community.document_loaders import WebBaseLoader

import os
import io
from dotenv import load_dotenv
from PIL import Image
import pytesseract
import whisper

from docx import Document
import pandas as pd
import PyPDF2

# Load environment variables
load_dotenv()

# Set paths for OCR & audio
pytesseract.pytesseract.tesseract_cmd = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
os.environ["PATH"] += os.pathsep + os.getenv("FFMPEG_PATH", "/usr/bin")

app = FastAPI()
client = Groq(api_key=os.getenv("GROQ_API_KEY"))

UPLOAD_DIR = "uploaded_files"
os.makedirs(UPLOAD_DIR, exist_ok=True)

MAX_FILE_SIZE_MB = 10

def extract_text_from_file(file_path):
    ext = os.path.splitext(file_path)[-1].lower()
    if ext == ".txt":
        with open(file_path, "r", encoding="utf-8") as f:
            return f.read()
    elif ext == ".docx":
        doc = Document(file_path)
        return "\n".join([p.text for p in doc.paragraphs])
    elif ext == ".csv":
        df = pd.read_csv(file_path)
        return df.to_string(index=False)
    elif ext == ".pdf":
        with open(file_path, "rb") as f:
            reader = PyPDF2.PdfReader(f)
            return "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])
    return "❌ Unsupported file type."

@app.post("/chat-with-file")
async def chat_with_file(file: UploadFile = File(...), question: str = Form(...)):
    try:
        contents = await file.read()
        if len(contents) > MAX_FILE_SIZE_MB * 1024 * 1024:
            return JSONResponse(status_code=400, content={"error": "❌ File too large. Max 10MB."})
        path = os.path.join(UPLOAD_DIR, file.filename)
        with open(path, "wb") as f:
            f.write(contents)
        text = extract_text_from_file(path)

        response = client.chat.completions.create(
            model="llama3-8b-8192",
            messages=[
                {"role": "system", "content": "You are a helpful assistant. Answer using the uploaded file."},
                {"role": "user", "content": f"{text}\n\nQuestion: {question}"}
            ]
        )
        return {"answer": response.choices[0].message.content}
    except Exception as e:
        return JSONResponse(status_code=500, content={"error": str(e)})

class URLQuery(BaseModel):
    url: str
    question: str

@app.post("/chat-with-url")
async def chat_with_url(data: URLQuery):
    try:
        loader = WebBaseLoader(data.url, header_template={"User-Agent": "Mozilla/5.0"})
        docs = loader.load()
        content = "\n".join([doc.page_content for doc in docs])

        response = client.chat.completions.create(
            model="llama3-8b-8192",
            messages=[
                {"role": "system", "content": "You are a helpful assistant. Answer using the webpage content."},
                {"role": "user", "content": f"Web Content:\n{content}\n\nQuestion: {data.question}"}
            ]
        )
        return {"answer": response.choices[0].message.content}
    except Exception as e:
        return JSONResponse(status_code=500, content={"error": str(e)})

@app.post("/extract-text-from-image")
async def extract_text_from_image(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        image = Image.open(io.BytesIO(contents)).convert("L")
        image = image.resize((image.width * 2, image.height * 2))
        text = pytesseract.image_to_string(image, lang="eng")
        return {"answer": text.strip() or "⚠️ No text extracted."}
    except Exception as e:
        return JSONResponse(status_code=500, content={"error": str(e)})

@app.post("/transcribe-audio")
async def transcribe_audio(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        path = os.path.join(UPLOAD_DIR, file.filename)
        with open(path, "wb") as f:
            f.write(contents)

        model = whisper.load_model("base")
        result = model.transcribe(path)
        return {"answer": result.get("text", "⚠️ No transcript returned.")}
    except Exception as e:
        return JSONResponse(status_code=500, content={"error": str(e)})