Update app.py

app.py

@@ -87,7 +87,7 @@ class DocumentRAG:
 
             # Combine text for summary
             combined_text = " ".join([doc.page_content for doc in documents])
-            self.document_summary = combined_text
+            self.document_summary = self.generate_summary(combined_text)
 
             # Create embeddings and initialize retrieval chain
             embeddings = OpenAIEmbeddings(api_key=self.api_key)
@@ -109,8 +109,8 @@ class DocumentRAG:
         except Exception as e:
             return f"Error processing documents: {str(e)}"
 
-    def generate_summary(self, text, language):
-        """Generate a summary of the provided text in the specified language."""
+    def generate_summary(self, text):
+        """Generate a summary of the provided text."""
         if not self.api_key:
             return "API Key not set. Please set it in the environment variables."
         try:
@@ -118,7 +118,7 @@ class DocumentRAG:
             response = client.chat.completions.create(
                 model="gpt-4",
                 messages=[
-                    {"role": "system", "content": f"Summarize the document content concisely in {language}. Provide 3-5 key points for discussion."},
+                    {"role": "system", "content": "Summarize the document content concisely and provide 3-5 key points for discussion."},
                     {"role": "user", "content": text[:4000]}
                 ],
                 temperature=0.3
@@ -127,8 +127,8 @@ class DocumentRAG:
         except Exception as e:
             return f"Error generating summary: {str(e)}"
 
-    def create_podcast(self, language):
-        """Generate a podcast script and audio in the specified language."""
+    def create_podcast(self):
+        """Generate a podcast script and audio based on the document summary."""
         if not self.document_summary:
             return "Please process documents before generating a podcast.", None
 
@@ -142,7 +142,7 @@ class DocumentRAG:
             script_response = client.chat.completions.create(
                 model="gpt-4",
                 messages=[
-                    {"role": "system", "content": f"You are a professional podcast producer. Create a natural dialogue in {language} based on the provided document summary."},
+                    {"role": "system", "content": "You are a professional podcast producer. Create a natural dialogue based on the provided document summary."},
                     {"role": "user", "content": f"""Based on the following document summary, create a 1-2 minute podcast script:
                     1. Clearly label the dialogue as 'Host 1:' and 'Host 2:'
                     2. Keep the content engaging and insightful.
@@ -157,20 +157,76 @@ class DocumentRAG:
             if not script:
                 return "Error: Failed to generate podcast script.", None
 
-            # For now, only return the script
-            return script, None
+            # Convert script to audio
+            final_audio = AudioSegment.empty()
+            is_first_speaker = True
+
+            lines = [line.strip() for line in script.split("\n") if line.strip()]
+            for line in lines:
+                if ":" not in line:
+                    continue
+
+                speaker, text = line.split(":", 1)
+                if not text.strip():
+                    continue
+
+                try:
+                    voice = "nova" if is_first_speaker else "onyx"
+                    audio_response = client.audio.speech.create(
+                        model="tts-1",
+                        voice=voice,
+                        input=text.strip()
+                    )
+
+                    temp_audio_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+                    audio_response.stream_to_file(temp_audio_file.name)
+
+                    segment = AudioSegment.from_file(temp_audio_file.name)
+                    final_audio += segment
+                    final_audio += AudioSegment.silent(duration=300)
+
+                    is_first_speaker = not is_first_speaker
+                except Exception as e:
+                    print(f"Error generating audio for line: {text}")
+                    print(f"Details: {e}")
+                    continue
+
+            if len(final_audio) == 0:
+                return "Error: No audio could be generated.", None
+
+            output_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3").name
+            final_audio.export(output_file, format="mp3")
+            return script, output_file
 
         except Exception as e:
             return f"Error generating podcast: {str(e)}", None
 
-    def handle_query(self, question, history, language):
-        """Handle user queries in the specified language."""
+    def generate_summary(self, text):
+        """Generate a summary of the provided text."""
+        if not self.api_key:
+            return "API Key not set. Please set it in the environment variables."
+        try:
+            client = OpenAI(api_key=self.api_key)
+            response = client.chat.completions.create(
+                model="gpt-4",
+                messages=[
+                    {"role": "system", "content": "Summarize the document content concisely and provide 3-5 key points for discussion."},
+                    {"role": "user", "content": text[:4000]}
+                ],
+                temperature=0.3
+            )
+            return response.choices[0].message.content
+        except Exception as e:
+            return f"Error generating summary: {str(e)}"
+
+    def handle_query(self, question, history):
+        """Handle user queries."""
         if not self.qa_chain:
             return history + [("System", "Please process the documents first.")]
         try:
-            preface = f"""
-            Instruction: Respond in {language}. Be professional and concise, keeping the response under 300 words.
-            If you cannot provide an answer, say: 'I am not sure about this question. Please try asking something else.'
+            preface = """
+            Instruction: Respond in English. Be professional and concise, keeping the response under 300 words.
+            If you cannot provide an answer, say: "I am not sure about this question. Please try asking something else."
             """
             query = f"{preface}\nQuery: {question}"
 
@@ -187,7 +243,6 @@ class DocumentRAG:
         except Exception as e:
             return history + [("System", f"Error: {str(e)}")]
 
-
 # Initialize RAG system in session state
 if "rag_system" not in st.session_state:
     st.session_state.rag_system = DocumentRAG()
@@ -307,4 +362,4 @@ if st.session_state.rag_system.document_summary:
         else:
             st.error(script)
 else:
-    st.info("Please process documents and generate summaries before creating a podcast.")
+    st.info("Please process documents and generate summaries before creating a podcast.")