Update main.py

main.py

@@ -15,57 +15,45 @@ from docx import Document
 import pandas as pd
 import PyPDF2
 
-# Load environment variables
 load_dotenv()
 
-# Paths for OCR and FFmpeg
 pytesseract.pytesseract.tesseract_cmd = os.getenv("TESSERACT_CMD", "/usr/bin/tesseract")
-os.environ["PATH"] += os.pathsep + os.getenv("FFMPEG_PATH", "/usr/bin")
+ffmpeg_path = os.getenv("FFMPEG_PATH", "/usr/bin")
+os.environ["PATH"] += os.pathsep + ffmpeg_path
 
-# Initialize FastAPI
 app = FastAPI()
 
-# Load Groq client with key from environment
 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
 
-# --- Helper: Safe Response ---
-def safe_response(text):
-    try:
-        return str(text).encode("utf-8", "replace").decode("utf-8")
-    except Exception:
-        return "⚠️ Unable to process response."
+MAX_FILE_SIZE_MB = 10
 
-# --- Extract text from uploaded file ---
 def extract_text_from_file(file_path):
     ext = os.path.splitext(file_path)[-1].lower()
-    try:
-        if ext == ".txt":
-            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])
-        elif ext == ".csv":
-            return pd.read_csv(file_path).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()])
-        else:
-            return "❌ Unsupported file type."
-    except Exception as e:
-        return f"❌ Failed to extract file: {e}"
+    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([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([page.extract_text() for page in reader.pages if page.extract_text()])
+    else:
+        return "❌ Unsupported file type."
 
-# --- 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(content={"answer": "❌ File too large. Max 10MB."})
+            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:
@@ -76,16 +64,14 @@ async def chat_with_file(file: UploadFile = File(...), question: str = Form(...)
         response = client.chat.completions.create(
             model="llama3-8b-8192",
             messages=[
-                {"role": "system", "content": "You are a helpful assistant. Use the file content to answer questions."},
+                {"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}"}
             ]
         )
-
-        return JSONResponse(content={"answer": safe_response(response.choices[0].message.content)})
+        return {"answer": response.choices[0].message.content}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"answer": f"❌ Error: {e}"})
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# --- Endpoint: Chat with URL ---
 class URLQuery(BaseModel):
     url: str
     question: str
@@ -101,26 +87,24 @@ async def chat_with_url(data: URLQuery):
         response = client.chat.completions.create(
             model="llama3-8b-8192",
             messages=[
-                {"role": "system", "content": "You are a helpful assistant. Use the website content to answer questions."},
-                {"role": "user", "content": f"Website Content:\n{web_content}\n\nNow answer this:\n{data.question}"}
+                {"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}"}
             ]
         )
-        return JSONResponse(content={"answer": safe_response(response.choices[0].message.content)})
+        return {"answer": response.choices[0].message.content}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"answer": f"❌ Error: {e}"})
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# --- Endpoint: OCR from 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 JSONResponse(content={"answer": safe_response(text.strip() or "⚠️ No text extracted.")})
+        return {"answer": text.strip() or "⚠️ No text extracted."}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"answer": f"❌ Error: {e}"})
+        return JSONResponse(status_code=500, content={"error": str(e)})
 
-# --- Endpoint: Transcribe Audio ---
 @app.post("/transcribe-audio")
 async def transcribe_audio(file: UploadFile = File(...)):
     try:
@@ -131,6 +115,6 @@ async def transcribe_audio(file: UploadFile = File(...)):
 
         model = whisper.load_model("base")
         result = model.transcribe(audio_path)
-        return JSONResponse(content={"answer": safe_response(result.get("text", "⚠️ No transcript returned."))})
+        return {"answer": result["text"] if result.get("text") else "⚠️ No transcript returned."}
     except Exception as e:
-        return JSONResponse(status_code=500, content={"answer": f"❌ Error: {e}"})
+        return JSONResponse(status_code=500, content={"error": str(e)})