Update interim.py

interim.py

@@ -12,6 +12,7 @@ from langchain_community.document_loaders import (
     CSVLoader
 )
 from datetime import datetime
+from pydub import AudioSegment
 import pytz
 
 from langchain.chains import ConversationalRetrievalChain
@@ -126,6 +127,98 @@ class DocumentRAG:
         except Exception as e:
             return f"Error generating summary: {str(e)}"
 
+    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
+
+        if not self.api_key:
+            return "Please set the OpenAI API key in the environment variables.", None
+
+        try:
+            client = OpenAI(api_key=self.api_key)
+
+            # Generate podcast script
+            script_response = client.chat.completions.create(
+                model="gpt-4",
+                messages=[
+                    {"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.
+                    3. Use conversational language suitable for a podcast.
+                    4. Ensure the script has a clear opening and closing.
+                    Document Summary: {self.document_summary}"""}
+                ],
+                temperature=0.7
+            )
+
+            script = script_response.choices[0].message.content
+            if not script:
+                return "Error: Failed to generate podcast 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 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:
@@ -188,4 +281,18 @@ if st.session_state.rag_system.qa_chain:
             st.chat_message("user").write(question)
             st.chat_message("assistant").write(answer)
 else:
-    st.info("Please process documents before asking questions.")
+    st.info("Please process documents before asking questions.")
+
+# Podcast Generation
+st.subheader("Step 3: Generate Podcast")
+if st.session_state.rag_system.document_summary:
+    if st.button("Generate Podcast"):
+        script, audio_path = st.session_state.rag_system.create_podcast()
+        if audio_path:
+            st.text_area("Generated Podcast Script", script, height=200)
+            st.audio(audio_path, format="audio/mp3")
+            st.success("Podcast generated successfully! You can listen to it above.")
+        else:
+            st.error(script)
+else:
+    st.info("Please process documents to generate a podcast.")