Update main.py

main.py

@@ -3,36 +3,41 @@ from fastapi.responses import JSONResponse
 from pydantic import BaseModel
 from groq import Groq
 from langchain_community.document_loaders import WebBaseLoader
-from docx import Document
-import pandas as pd
-import PyPDF2
+
+import os
+import io
+from dotenv import load_dotenv
 from PIL import Image
 import pytesseract
 import whisper
-import os
-import io
+import traceback  # for detailed error logging
+
+# Load environment variables
+load_dotenv()
+
+# Tesseract path
+pytesseract.pytesseract.tesseract_cmd = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
 
-# === ENVIRONMENT SETUP ===
-# Hugging Face Spaces inject secrets automatically
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
-TESSERACT_CMD = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
-FFMPEG_PATH = os.getenv("FFMPEG_PATH", "/usr/bin")
+# FFmpeg path
+ffmpeg_path = os.getenv("FFMPEG_PATH", "/usr/bin")
+os.environ["PATH"] += os.pathsep + ffmpeg_path
 
-# Ensure paths
-pytesseract.pytesseract.tesseract_cmd = TESSERACT_CMD
-os.environ["PATH"] += os.pathsep + FFMPEG_PATH
+# File reading
+from docx import Document
+import pandas as pd
+import PyPDF2
 
-# === FastAPI APP INIT ===
 app = FastAPI()
+
+# Groq client
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
 UPLOAD_DIR = "uploaded_files"
 os.makedirs(UPLOAD_DIR, exist_ok=True)
 
-# === Groq API Init ===
-if not GROQ_API_KEY:
-    raise ValueError("GROQ_API_KEY not found in environment.")
-client = Groq(api_key=GROQ_API_KEY)
+MAX_FILE_SIZE_MB = 10
 
-# === Extract text from file ===
+# --- Helper: Extract Text from File ---
 def extract_text_from_file(file_path):
     ext = os.path.splitext(file_path)[-1].lower()
     try:
@@ -40,26 +45,30 @@ def extract_text_from_file(file_path):
             with open(file_path, "r", encoding="utf-8") as f:
                 return f.read()
         elif ext == ".docx":
-            return "\n".join([p.text for p in Document(file_path).paragraphs])
+            doc = Document(file_path)
+            return "\n".join([para.text for para 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([p.extract_text() for p in reader.pages if p.extract_text()])
+                return "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])
         else:
             return "❌ Unsupported file type."
     except Exception as e:
-        return f"❌ Failed to read file: {str(e)}"
+        print("❌ File parsing error:", str(e))
+        traceback.print_exc()
+        return "⚠️ Failed to extract text."
 
-# === Endpoint: Chat with File ===
+# --- Endpoint: Chat with File ---
 @app.post("/chat-with-file")
 async def chat_with_file(file: UploadFile = File(...), question: str = Form(...)):
     try:
         contents = await file.read()
-        if len(contents) > 10 * 1024 * 1024:
-            return JSONResponse(status_code=400, content={"error": "❌ File too large (max 10MB)."})
+
+        if len(contents) > MAX_FILE_SIZE_MB * 1024 * 1024:
+            return JSONResponse(status_code=400, content={"error": "❌ File too large. Max size is 10MB."})
 
         file_path = os.path.join(UPLOAD_DIR, file.filename)
         with open(file_path, "wb") as f:
@@ -74,12 +83,14 @@ async def chat_with_file(file: UploadFile = File(...), question: str = Form(...)
                 {"role": "user", "content": f"{file_content}\n\nQuestion: {question}"}
             ]
         )
-        return {"answer": response.choices[0].message.content}
 
+        return {"answer": response.choices[0].message.content}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"error": f"❌ {str(e)}"})
+        print("❌ Chat with file error:", str(e))
+        traceback.print_exc()
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# === Endpoint: Chat with URL ===
+# --- Endpoint: Chat with URL ---
 class URLQuery(BaseModel):
     url: str
     question: str
@@ -87,7 +98,7 @@ class URLQuery(BaseModel):
 @app.post("/chat-with-url")
 async def chat_with_url(data: URLQuery):
     try:
-        os.environ["USER_AGENT"] = "Mozilla/5.0"
+        os.environ["USER_AGENT"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
         loader = WebBaseLoader(data.url)
         documents = loader.load()
         web_content = "\n".join([doc.page_content for doc in documents])
@@ -100,11 +111,12 @@ async def chat_with_url(data: URLQuery):
             ]
         )
         return {"answer": response.choices[0].message.content}
-
     except Exception as e:
-        return JSONResponse(status_code=500, content={"error": f"❌ {str(e)}"})
+        print("❌ Chat with URL error:", str(e))
+        traceback.print_exc()
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# === Endpoint: OCR from Image ===
+# --- Endpoint: OCR Image ---
 @app.post("/extract-text-from-image")
 async def extract_text_from_image(file: UploadFile = File(...)):
     try:
@@ -113,9 +125,11 @@ async def extract_text_from_image(file: UploadFile = File(...)):
         text = pytesseract.image_to_string(image)
         return {"answer": text.strip() or "⚠️ No text extracted."}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"error": f"❌ {str(e)}"})
+        print("❌ Image OCR error:", str(e))
+        traceback.print_exc()
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# === Endpoint: Transcribe Audio ===
+# --- Endpoint: Transcribe Audio ---
 @app.post("/transcribe-audio")
 async def transcribe_audio(file: UploadFile = File(...)):
     try:
@@ -127,6 +141,7 @@ async def transcribe_audio(file: UploadFile = File(...)):
         model = whisper.load_model("base")
         result = model.transcribe(audio_path)
         return {"answer": result.get("text", "⚠️ No transcript returned.")}
-
     except Exception as e:
-        return JSONResponse(status_code=500, content={"error": f"❌ {str(e)}"})
+        print("❌ Audio transcription error:", str(e))
+        traceback.print_exc()
+        return JSONResponse(status_code=500, content={"error": str(e)})