Update app.py

app.py

@@ -5,7 +5,16 @@ import pandas as pd
 from analyzer import combine_repo_files_for_llm, analyze_combined_file, parse_llm_json_response
 from hf_utils import download_space_repo, search_top_spaces
 
-# from hf_utils import download_space_repo
+# Import chatbot logic
+from analyzer import analyze_code
+
+# Chatbot system prompt
+CHATBOT_SYSTEM_PROMPT = (
+    "You are a helpful assistant. Your goal is to help the user describe their ideal open-source repo. "
+    "Ask questions to clarify what they want, their use case, preferred language, features, etc. "
+    "When the user clicks 'End Chat', analyze the conversation and return about 5 keywords for repo search. "
+    "Return only the keywords as a comma-separated list."
+)
 
 def read_csv_as_text(csv_filename):
     return pd.read_csv(csv_filename, dtype=str)
@@ -131,6 +140,36 @@ df_output = gr.Dataframe(headers=["repo id", "strength", "weaknesses", "speciali
     datatype=["str", "str", "str", "str", "str", "str"]
 )
 
+def chat_with_user(user_message, history):
+    from openai import OpenAI
+    client = OpenAI()
+    messages = [
+        {"role": "system", "content": CHATBOT_SYSTEM_PROMPT}
+    ]
+    for msg in history:
+        messages.append({"role": "user", "content": msg[0]})
+        if msg[1]:
+            messages.append({"role": "assistant", "content": msg[1]})
+    messages.append({"role": "user", "content": user_message})
+    response = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=messages,
+        max_tokens=256,
+        temperature=0.7
+    )
+    assistant_reply = response.choices[0].message.content
+    return assistant_reply
+
+def extract_keywords_from_conversation(history):
+    conversation = "\n".join([f"User: {msg[0]}\nAssistant: {msg[1]}" for msg in history if msg[1]])
+    prompt = (
+        "Given the following conversation between a user and an assistant about finding an ideal open-source repo, "
+        "extract about 5 keywords that best represent what the user is looking for. "
+        "Return only the keywords as a comma-separated list.\n\nConversation:\n" + conversation
+    )
+    keywords = analyze_code(prompt)
+    return keywords
+
 with gr.Blocks() as demo:
     page_state = gr.State(0)
 
@@ -164,15 +203,20 @@ with gr.Blocks() as demo:
         back_btn = gr.Button("Back to Input")
         back_to_start_btn2 = gr.Button("Back to Start")
 
-    # --- Page 3: Chatbot Placeholder ---
+    # --- Page 3: Chatbot ---
     with gr.Column(visible=False) as chatbot_page:
-        gr.Markdown("## Chatbot (Coming Soon)")
-        gr.Markdown("This is where you will be able to chat and get repo recommendations!")
+        gr.Markdown("## Repo Recommendation Chatbot")
+        chatbot = gr.Chatbot()
+        state = gr.State([])
+        user_input = gr.Textbox(label="Your message", placeholder="Describe your ideal repo or answer the assistant's questions...")
+        send_btn = gr.Button("Send")
+        end_btn = gr.Button("End Chat and Extract Keywords")
+        keywords_output = gr.Textbox(label="Extracted Keywords for Repo Search", interactive=False)
         back_to_start_btn3 = gr.Button("Back to Start")
 
     # Navigation logic
-    option_a_btn.click(go_to_analysis, inputs=None, outputs=[start_page, analysis_page, chatbot_page])
-    option_b_btn.click(go_to_chatbot, inputs=None, outputs=[start_page, analysis_page, chatbot_page])
+    option_a_btn.click(go_to_input, inputs=None, outputs=[start_page, input_page, chatbot_page])
+    option_b_btn.click(go_to_chatbot, inputs=None, outputs=[start_page, input_page, chatbot_page])
     next_btn.click(go_to_analysis, inputs=None, outputs=[input_page, analysis_page, chatbot_page])
     back_btn.click(go_to_input, inputs=None, outputs=[input_page, analysis_page, chatbot_page])
     back_to_start_btn.click(go_to_start, inputs=None, outputs=[start_page, input_page, chatbot_page])
@@ -186,4 +230,17 @@ with gr.Blocks() as demo:
     # Analysis logic
     combine_btn.click(show_combined_repo_and_llm, inputs=None, outputs=[combined_txt, llm_output_txt, df_display])
 
+    # Chatbot logic
+    def user_send(user_message, history):
+        assistant_reply = chat_with_user(user_message, history)
+        history = history + [[user_message, assistant_reply]]
+        return history, history, ""
+
+    def end_chat(history):
+        keywords = extract_keywords_from_conversation(history)
+        return keywords
+
+    send_btn.click(user_send, inputs=[user_input, state], outputs=[chatbot, state, user_input])
+    end_btn.click(end_chat, inputs=state, outputs=keywords_output)
+
 demo.launch()