Update app.py

app.py

@@ -12,41 +12,72 @@ from docx_builder import (
     build_obe_docx,
 )
 
-# ---------------------------
-# Utility: Extract PDF text
-# ---------------------------
-def extract_text_from_pdf(file_obj) -> str:
-    try:
-        reader = PdfReader(file_obj.name)
-        pages = [p.extract_text() or "" for p in reader.pages]
-        return "\n".join(pages)
-    except:
-        return ""
-
-# ---------------------------
-# Initialize Clients
-# ---------------------------
+# =====================================================
+#  SAFE FILE TEXT EXTRACTION (TXT, DOCX, PDF Supported)
+# =====================================================
+def extract_text(file_obj):
+    """Reads syllabus from .txt, .docx or .pdf without breaking."""
+    name = file_obj.name.lower()
+
+    # TXT
+    if name.endswith(".txt"):
+        content = file_obj.read()
+        try:
+            return content.decode("utf-8", errors="ignore")
+        except:
+            return content.decode("latin-1", errors="ignore")
+
+    # DOCX
+    if name.endswith(".docx"):
+        try:
+            from docx import Document
+            doc = Document(file_obj.name)
+            return "\n".join([p.text for p in doc.paragraphs])
+        except:
+            return ""
+
+    # PDF
+    if name.endswith(".pdf"):
+        try:
+            reader = PdfReader(file_obj.name)
+            pages = [p.extract_text() or "" for p in reader.pages]
+            return "\n".join(pages)
+        except Exception:
+            return ""
+
+    return ""
+
+
+# =====================================================
+#  INITIALIZE CLIENTS
+# =====================================================
 def init_clients():
     groq_key = os.getenv("GROQ_API_KEY")
     serp_key = os.getenv("SERPAPI_KEY")
+
     groq = GroqClient(api_key=groq_key)
     serp = SerpClient(api_key=serp_key)
+
     return groq, serp
 
+
 groq_client, serp_client = init_clients()
 orchestrator = MultiAgentOrchestrator(groq_client, serp_client)
 
-# ---------------------------
-# Main Pipeline Trigger
-# ---------------------------
+
+# =====================================================
+#  MAIN PIPELINE FUNCTION
+# =====================================================
 def run_system(subject, stream, partA, partB, partC, syl_file, ref_file):
 
     if syl_file is None:
-        return None, None, None, "Upload syllabus first."
+        return None, None, None, "Error: Upload a syllabus file."
 
-    syllabus_text = extract_text_from_pdf(syl_file)
-    ref_text = extract_text_from_pdf(ref_file) if ref_file else ""
+    # Extract text safely
+    syllabus_text = extract_text(syl_file)
+    ref_text = extract_text(ref_file) if ref_file else ""
 
+    # Run multi-agent orchestration
     output = orchestrator.run_pipeline(
         subject=subject,
         stream=stream,
@@ -60,46 +91,52 @@ def run_system(subject, stream, partA, partB, partC, syl_file, ref_file):
     final_json = output.get("final", {})
     generator_raw = output.get("generator_raw", "")
 
+    # Temporary directory for docx exports
     tmpdir = Path(tempfile.mkdtemp())
-    qp_path = tmpdir / f"{subject}_QP.docx"
-    ans_path = tmpdir / f"{subject}_Answers.docx"
-    obe_path = tmpdir / f"{subject}_OBE.docx"
 
+    qp_path = tmpdir / f"{subject}_QuestionPaper.docx"
+    ans_path = tmpdir / f"{subject}_AnswerKey.docx"
+    obe_path = tmpdir / f"{subject}_OBE_Summary.docx"
+
+    # Build all DOCX files
     build_question_paper_docx(qp_path, final_json, generator_raw, subject)
     build_answers_docx(ans_path, final_json, subject)
     build_obe_docx(obe_path, final_json, subject)
 
-    return qp_path, ans_path, obe_path, "Done!"
+    # RETURN FILE PATHS AS STRINGS (required by Gradio)
+    return str(qp_path), str(ans_path), str(obe_path), "Generation Complete!"
+
 
-# ---------------------------
-# Gradio UI
-# ---------------------------
+# =====================================================
+#  GRADIO USER INTERFACE
+# =====================================================
 with gr.Blocks() as app:
-    gr.Markdown("# Multi-Agent Question Paper Generator (Groq + SerpAPI)")
+
+    gr.Markdown("## Multi-Agent Question Paper Generator (Groq + SerpAPI)")
 
     with gr.Row():
-        subject = gr.Textbox(label="Subject Name")
-        stream = gr.Dropdown(["CSE", "Non-CSE"], value="CSE", label="Stream")
+        subject = gr.Textbox(label="Subject Name", placeholder="Cloud Computing")
+        stream = gr.Dropdown(["CSE", "Non-CSE"], label="Stream", value="CSE")
 
     with gr.Row():
-        partA = gr.Number(value=10, precision=0, label="Part A Count")
-        partB = gr.Number(value=5, precision=0, label="Part B Count")
-        partC = gr.Number(value=1, precision=0, label="Part C Count")
+        partA = gr.Number(label="Part A Questions", value=10, precision=0)
+        partB = gr.Number(label="Part B Questions (Either/Or)", value=5, precision=0)
+        partC = gr.Number(label="Part C Questions", value=1, precision=0)
 
-    syllabus = gr.File(label="Upload Syllabus PDF")
+    syllabus = gr.File(label="Upload Syllabus (.pdf / .txt / .docx)")
     ref_qp = gr.File(label="Upload Reference QP (Optional)")
 
-    btn = gr.Button("Generate Question Paper")
+    generate_btn = gr.Button("Generate Question Paper")
 
-    qp_file = gr.File(label="Question Paper")
-    ans_file = gr.File(label="Answer Key")
-    obe_file = gr.File(label="OBE Summary")
-    status = gr.Markdown("Status: Idle")
+    qp_output = gr.File(label="Download Question Paper")
+    ans_output = gr.File(label="Download Answer Key")
+    obe_output = gr.File(label="Download OBE Summary")
+    status = gr.Markdown("Status: Waiting...")
 
-    btn.click(
+    generate_btn.click(
         run_system,
         inputs=[subject, stream, partA, partB, partC, syllabus, ref_qp],
-        outputs=[qp_file, ans_file, obe_file, status]
+        outputs=[qp_output, ans_output, obe_output, status]
     )
 
 app.launch()