Create app.py

app.py

@@ -0,0 +1,114 @@
+import gradio as gr
+from transformers import pipeline
+
+"""
+Psychotherapy Session Summarizer (Open-Source Implementation)
+
+This is a Hugging Face Spaces-compatible Gradio app that:
+- Takes psychotherapy session transcripts (as text input).
+- Summarizes key themes, emotional tones, and patterns.
+- Optionally allows custom instructions or focus areas (e.g., "Focus on client's progress since last session").
+- Utilizes open-source models only.
+
+Modular:
+- Summarization model can be swapped easily.
+- Sentiment analysis model can be changed if desired.
+
+Scalable:
+- Can be extended to handle multiple transcripts and clustering by topic.
+
+Note: 
+All used models are open-source and freely available on Hugging Face:
+- Summarization model: "google/flan-t5-small" (FLAN-T5 is open-sourced by Google)
+- Sentiment model: "cardiffnlp/twitter-roberta-base-sentiment-latest" (open-source sentiment analysis)
+
+You can adapt these to different models if needed, as long as they are open-source.
+
+Instructions:
+1. Paste or upload a session transcript (preferably a few paragraphs of conversation).
+2. (Optional) Provide a custom instruction or focus question, e.g., "Highlight moments of cognitive reframing."
+3. Click "Summarize" to generate a concise summary with themes and emotional insights.
+
+"""
+
+# Initialize pipelines
+summarizer = pipeline("text2text-generation", model="google/flan-t5-small", tokenizer="google/flan-t5-small")
+# Note: "text2text-generation" pipeline for FLAN-T5 also works for summarization if we prompt it properly.
+sentiment_analyzer = pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
+
+def analyze_session(transcript, custom_instruction):
+    # Basic input validation
+    if not transcript.strip():
+        return "Please provide a transcript."
+    
+    # Construct a prompt for the summarization model
+    # FLAN-T5 is instruction tuned, so we can give it instructions directly.
+    # For example:
+    prompt = "Summarize the following psychotherapy session transcript, focusing on key themes, emotional shifts, and patterns."
+    if custom_instruction.strip():
+        prompt += " Additionally, " + custom_instruction.strip()
+    prompt += "\n\nTranscript:\n" + transcript.strip()
+    
+    # Generate summary
+    summary_output = summarizer(prompt, max_length=200, do_sample=False)
+    summary = summary_output[0]['generated_text'].strip()
+    
+    # Sentiment analysis: We'll run it on the entire transcript to gauge the overall emotional tone.
+    sentiment_results = sentiment_analyzer(transcript)
+    # The sentiment model returns something like: [{'label': 'positive', 'score': ...}]
+    # We'll aggregate the results (though it's a single input) and just pick the top.
+    main_sentiment = sentiment_results[0]['label']
+    
+    # Construct a more informative result
+    # You could elaborate this logic: detect recurring concerns by simple keyword frequency analysis, etc.
+    # For a simple first iteration, just provide summary and sentiment.
+    
+    # Optional: Identify recurring concerns (simple keyword extraction)
+    # We'll do a naive keyword frequency approach just as a demonstration:
+    words = transcript.lower().split()
+    # Common therapy-related words (just a naive approach, could be replaced by a proper keyword extraction model)
+    # This is a placeholder for demonstration
+    keywords_of_interest = ["anxiety", "depression", "relationship", "stress", "fear", "goals", "progress", "cognitive", "behavior"]
+    recurring_concerns = [word for word in words if word in keywords_of_interest]
+    recurring_concerns = list(set(recurring_concerns))  # unique
+    if not recurring_concerns:
+        recurring_concerns_str = "No specific recurring concerns identified from the predefined list."
+    else:
+        recurring_concerns_str = "Recurring concerns include: " + ", ".join(recurring_concerns)
+    
+    # Recommended follow-up topics (just a heuristic based on summary)
+    # If certain keywords appear in summary, we can suggest follow-up:
+    follow_up_suggestions = []
+    if "progress" in summary.lower():
+        follow_up_suggestions.append("Explore client's perception of progress in more detail.")
+    if "relationship" in summary.lower():
+        follow_up_suggestions.append("Discuss client's relationship dynamics further.")
+    if not follow_up_suggestions:
+        follow_up_suggestions.append("Consider following up on the emotional themes identified in the summary.")
+    
+    follow_up_suggestions_str = " ".join(follow_up_suggestions)
+    
+    # Combine results into a final output
+    final_output = f"**Summary of Session:**\n{summary}\n\n**Overall Sentiment:** {main_sentiment}\n\n**{recurring_concerns_str}**\n\n**Suggested Follow-Up Topics:** {follow_up_suggestions_str}"
+    
+    return final_output
+
+# Build Gradio UI
+description = """# Psychotherapy Session Summarizer
+
+Upload or paste your psychotherapy session transcript and optionally provide a custom instruction (e.g., "Focus on anxiety and coping strategies.").  
+Click 'Summarize' to generate a concise summary of key themes, emotional tones, recurring concerns, and suggested follow-up topics.
+"""
+
+with gr.Blocks() as demo:
+    gr.Markdown(description)
+    with gr.Row():
+        transcript_input = gr.Textbox(label="Session Transcript", lines=10, placeholder="Paste the session transcript here...")
+    custom_instruction_input = gr.Textbox(label="Custom Instruction (Optional)", placeholder="e.g., Focus on how the client describes their feelings about progress.")
+    summarize_button = gr.Button("Summarize")
+    output_box = gr.Markdown()
+    
+    summarize_button.click(fn=analyze_session, inputs=[transcript_input, custom_instruction_input], outputs=output_box)
+
+if __name__ == "__main__":
+    demo.launch()