Update main.py

main.py

@@ -10,34 +10,37 @@ from dotenv import load_dotenv
 from PIL import Image
 import pytesseract
 import whisper
-import traceback  # for detailed error logging
 
-# Load environment variables
-load_dotenv()
-
-# Tesseract path
-pytesseract.pytesseract.tesseract_cmd = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
-
-# FFmpeg path
-ffmpeg_path = os.getenv("FFMPEG_PATH", "/usr/bin")
-os.environ["PATH"] += os.pathsep + ffmpeg_path
-
-# File reading
 from docx import Document
 import pandas as pd
 import PyPDF2
 
+# Load .env
+load_dotenv()
+
+# Initialize FastAPI
 app = FastAPI()
 
-# Groq client
-client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+# Tesseract and FFmpeg setup
+pytesseract.pytesseract.tesseract_cmd = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
+ffmpeg_path = os.getenv("FFMPEG_PATH", "/usr/bin")
+os.environ["PATH"] += os.pathsep + ffmpeg_path
 
+# Upload directory
 UPLOAD_DIR = "uploaded_files"
 os.makedirs(UPLOAD_DIR, exist_ok=True)
 
+# Groq Client
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
+# File limit
 MAX_FILE_SIZE_MB = 10
 
-# --- Helper: Extract Text from File ---
+
+def safe_response(text):
+    return text.encode("utf-8", "replace").decode("utf-8")
+
+
 def extract_text_from_file(file_path):
     ext = os.path.splitext(file_path)[-1].lower()
     try:
@@ -46,27 +49,24 @@ def extract_text_from_file(file_path):
                 return f.read()
         elif ext == ".docx":
             doc = Document(file_path)
-            return "\n".join([para.text for para in doc.paragraphs])
+            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 "\n".join([p.extract_text() for p in reader.pages if p.extract_text()])
         else:
             return "❌ Unsupported file type."
     except Exception as e:
-        print("❌ File parsing error:", str(e))
-        traceback.print_exc()
-        return "⚠️ Failed to extract text."
+        return f"⚠️ Error while reading file: {str(e)}"
+
 
-# --- 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) > MAX_FILE_SIZE_MB * 1024 * 1024:
             return JSONResponse(status_code=400, content={"error": "❌ File too large. Max size is 10MB."})
 
@@ -75,61 +75,58 @@ async def chat_with_file(file: UploadFile = File(...), question: str = Form(...)
             f.write(contents)
 
         file_content = extract_text_from_file(file_path)
+        prompt = f"{file_content}\n\nQuestion: {question}"
 
         response = client.chat.completions.create(
             model="llama3-8b-8192",
             messages=[
                 {"role": "system", "content": "You are a helpful assistant. Use the uploaded file content to answer questions."},
-                {"role": "user", "content": f"{file_content}\n\nQuestion: {question}"}
+                {"role": "user", "content": prompt}
             ]
         )
-
-        return {"answer": response.choices[0].message.content}
+        return {"answer": safe_response(response.choices[0].message.content)}
     except Exception as e:
-        print("❌ Chat with file error:", str(e))
-        traceback.print_exc()
-        return JSONResponse(status_code=500, content={"error": str(e)})
+        return JSONResponse(status_code=500, content={"error": safe_response(str(e))})
+
 
-# --- Endpoint: Chat with URL ---
 class URLQuery(BaseModel):
     url: str
     question: str
 
+
 @app.post("/chat-with-url")
 async def chat_with_url(data: URLQuery):
     try:
-        os.environ["USER_AGENT"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
+        os.environ["USER_AGENT"] = "Mozilla/5.0"
         loader = WebBaseLoader(data.url)
         documents = loader.load()
         web_content = "\n".join([doc.page_content for doc in documents])
 
+        prompt = f"Website Content:\n{web_content}\n\nNow answer this question:\n{data.question}"
+
         response = client.chat.completions.create(
             model="llama3-8b-8192",
             messages=[
                 {"role": "system", "content": "You are a helpful assistant. Use the website content to answer the user's question."},
-                {"role": "user", "content": f"Website Content:\n{web_content}\n\nNow answer this question:\n{data.question}"}
+                {"role": "user", "content": prompt}
             ]
         )
-        return {"answer": response.choices[0].message.content}
+        return {"answer": safe_response(response.choices[0].message.content)}
     except Exception as e:
-        print("❌ Chat with URL error:", str(e))
-        traceback.print_exc()
-        return JSONResponse(status_code=500, content={"error": str(e)})
+        return JSONResponse(status_code=500, content={"error": safe_response(str(e))})
+
 
-# --- Endpoint: OCR Image ---
 @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))
         text = pytesseract.image_to_string(image)
-        return {"answer": text.strip() or "⚠️ No text extracted."}
+        return {"answer": safe_response(text.strip() or "⚠️ No text extracted.")}
     except Exception as e:
-        print("❌ Image OCR error:", str(e))
-        traceback.print_exc()
-        return JSONResponse(status_code=500, content={"error": str(e)})
+        return JSONResponse(status_code=500, content={"error": safe_response(str(e))})
+
 
-# --- Endpoint: Transcribe Audio ---
 @app.post("/transcribe-audio")
 async def transcribe_audio(file: UploadFile = File(...)):
     try:
@@ -140,8 +137,7 @@ 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.")}
+        text = result.get("text", "⚠️ No transcript returned.")
+        return {"answer": safe_response(text)}
     except Exception as e:
-        print("❌ Audio transcription error:", str(e))
-        traceback.print_exc()
-        return JSONResponse(status_code=500, content={"error": str(e)})
+        return JSONResponse(status_code=500, content={"error": safe_response(str(e))})