Update app.py

app.py

@@ -5,14 +5,17 @@ import pinecone
 import qdrant_client
 from openai import OpenAI
 import graphviz
+import requests
 
 # =================== CONFIG ===================
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
 PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
 QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")
+ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY")
 
 client = OpenAI(api_key=OPENAI_API_KEY)
-VECTOR_DB = "qdrant"  # change to "pinecone" if needed
+VECTOR_DB = "qdrant"  # change to "pinecone" if you want Pinecone
+
 
 # =================== HELPERS ===================
 def extract_text_from_pdf(pdf_path):
@@ -22,6 +25,7 @@ def extract_text_from_pdf(pdf_path):
         text += page.get_text()
     return text
 
+
 def ingest_text(text, doc_name="doc"):
     if VECTOR_DB == "qdrant":
         qclient = qdrant_client.QdrantClient(":memory:")
@@ -43,54 +47,84 @@ def ingest_text(text, doc_name="doc"):
         index.upsert([(str(0), [0.0]*1536, {"text": text})])
     return f"Ingested {len(text.split())} words."
 
+
 def summarize_text(text):
     resp = client.chat.completions.create(
         model="gpt-3.5-turbo",
-        messages=[{"role":"system","content":"Summarize clearly."},
-                  {"role":"user","content":text[:4000]}]
+        messages=[{"role": "system", "content": "Summarize clearly."},
+                  {"role": "user", "content": text[:4000]}]
     )
     return resp.choices[0].message.content
 
+
+def generate_audio(summary_text):
+    if not ELEVENLABS_API_KEY:
+        return None
+
+    url = "https://api.elevenlabs.io/v1/text-to-speech/pnYgVoCjYp9s9v1sXlKS"  # default voice
+    headers = {
+        "xi-api-key": ELEVENLABS_API_KEY,
+        "Content-Type": "application/json"
+    }
+    data = {
+        "text": summary_text,
+        "voice_settings": {"stability": 0.5, "similarity_boost": 0.7}
+    }
+    response = requests.post(url, headers=headers, json=data)
+
+    if response.status_code == 200:
+        audio_path = "summary_audio.mp3"
+        with open(audio_path, "wb") as f:
+            f.write(response.content)
+        return audio_path
+    else:
+        return None
+
+
 def generate_diagram(text):
     dot = graphviz.Digraph()
     dot.node("A", "PDF Content")
     dot.node("B", "Summary")
     dot.node("C", "Key Ideas")
-    dot.edges([("A","B"),("B","C")])
+    dot.edges([("A", "B"), ("B", "C")])
     return dot.pipe(format="png")
 
+
 def chat_with_pdf(text, question):
     resp = client.chat.completions.create(
         model="gpt-3.5-turbo",
         messages=[
-            {"role":"system","content":"You are a helpful assistant with access to the document."},
-            {"role":"user","content":f"Document:\n{text[:3000]}\n\nQuestion:{question}"}
+            {"role": "system", "content": "You are a helpful assistant with access to the document."},
+            {"role": "user", "content": f"Document:\n{text[:3000]}\n\nQuestion: {question}"}
         ]
     )
     return resp.choices[0].message.content
 
+
 # =================== GRADIO APP ===================
 with gr.Blocks(theme="soft") as demo:
-    gr.Markdown("# 📚 PDF Assistant — Summarize, Diagram, Chat")
-    
+    gr.Markdown("# 📚 PDF Assistant — Summarize, Diagram, Audio, Chat")
+
     with gr.Row():
         pdf_file = gr.File(label="Upload PDF", file_types=[".pdf"])
         doc_name = gr.Textbox(label="Doc name", value="mydoc")
-    
+
     ingest_btn = gr.Button("🚀 Ingest PDF")
     ingest_status = gr.Markdown("")
-    
+
     summary_btn = gr.Button("📖 Summarize")
     summary_output = gr.Textbox(label="Summary", lines=8)
-    
+
+    audio_output = gr.Audio(label="🔊 Summary Audio")
+
     diagram_btn = gr.Button("📝 Generate Diagram")
     diagram_output = gr.Image(type="numpy", label="Diagram Preview")
-    
+
     with gr.Row():
         question = gr.Textbox(label="Ask the PDF a question")
         answer = gr.Textbox(label="Answer")
         ask_btn = gr.Button("💬 Ask")
-    
+
     pdf_text_state = gr.State("")
 
     def handle_ingest(pdf_file, doc_name):
@@ -98,8 +132,13 @@ with gr.Blocks(theme="soft") as demo:
         status = ingest_text(text, doc_name)
         return text, status
 
+    def handle_summary(text):
+        summary = summarize_text(text)
+        audio = generate_audio(summary)
+        return summary, audio
+
     ingest_btn.click(handle_ingest, [pdf_file, doc_name], [pdf_text_state, ingest_status])
-    summary_btn.click(lambda t: summarize_text(t), pdf_text_state, summary_output)
+    summary_btn.click(handle_summary, pdf_text_state, [summary_output, audio_output])
     diagram_btn.click(lambda t: generate_diagram(t), pdf_text_state, diagram_output)
     ask_btn.click(lambda t, q: chat_with_pdf(t, q), [pdf_text_state, question], answer)