Update app.py

app.py

@@ -209,6 +209,126 @@ def use_keywords_to_search_and_update_csv(keywords):
     df = read_csv_as_text(csv_filename)
     return df
 
+def batch_analyze_and_select_top():
+    csv_filename = "repo_ids.csv"
+    try:
+        df = read_csv_as_text(csv_filename)
+        all_infos = []
+        # Analyze each repo and update CSV
+        for idx, row in df.iterrows():
+            repo_id = row["repo id"]
+            try:
+                download_space_repo(repo_id, local_dir="repo_files")
+                txt_path = combine_repo_files_for_llm()
+                llm_output = analyze_combined_file(txt_path)
+                last_start = llm_output.rfind('{')
+                last_end = llm_output.rfind('}')
+                if last_start != -1 and last_end != -1 and last_end > last_start:
+                    final_json_str = llm_output[last_start:last_end+1]
+                else:
+                    final_json_str = llm_output
+                llm_json = parse_llm_json_response(final_json_str)
+                if isinstance(llm_json, dict) and "error" not in llm_json:
+                    df.at[idx, "strength"] = llm_json.get("strength", "")
+                    df.at[idx, "weaknesses"] = llm_json.get("weaknesses", "")
+                    df.at[idx, "speciality"] = llm_json.get("speciality", "")
+                    df.at[idx, "relevance rating"] = llm_json.get("relevance rating", "")
+                all_infos.append({"repo id": repo_id, **llm_json})
+            except Exception as e:
+                all_infos.append({"repo id": repo_id, "error": str(e)})
+        df.to_csv(csv_filename, index=False)
+        # Display all info
+        all_info_str = "\n\n".join([str(info) for info in all_infos])
+        # Let LLM choose the best 3
+        from openai import OpenAI
+        import os
+        client = OpenAI(api_key=os.getenv("modal_api"))
+        client.base_url = os.getenv("base_url")
+        selection_prompt = (
+            "You are a helpful assistant. You are given a list of repo analyses in JSON format. "
+            "Choose the 3 repos that are the most impressive, relevant, or useful. "
+            "Return ONLY a JSON array of the 3 best repo ids, in order of preference, under the key 'top_repos'. "
+            "Example: {\"top_repos\": [\"repo1\", \"repo2\", \"repo3\"]}"
+        )
+        user_content = "Here are the repo analyses:\n" + all_info_str
+        response = client.chat.completions.create(
+            model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
+            messages=[
+                {"role": "system", "content": selection_prompt},
+                {"role": "user", "content": user_content}
+            ],
+            max_tokens=256,
+            temperature=0.3
+        )
+        selection_json = parse_llm_json_response(response.choices[0].message.content)
+        top_repos = selection_json.get("top_repos", [])
+        return all_info_str, str(top_repos), df
+    except Exception as e:
+        return f"Error in batch analysis: {e}", "", pd.DataFrame()
+
+def batch_analyze_and_select_top_for_chat(state):
+    csv_filename = "repo_ids.csv"
+    try:
+        df = read_csv_as_text(csv_filename)
+        all_infos = []
+        for idx, row in df.iterrows():
+            repo_id = row["repo id"]
+            try:
+                download_space_repo(repo_id, local_dir="repo_files")
+                txt_path = combine_repo_files_for_llm()
+                llm_output = analyze_combined_file(txt_path)
+                last_start = llm_output.rfind('{')
+                last_end = llm_output.rfind('}')
+                if last_start != -1 and last_end != -1 and last_end > last_start:
+                    final_json_str = llm_output[last_start:last_end+1]
+                else:
+                    final_json_str = llm_output
+                llm_json = parse_llm_json_response(final_json_str)
+                if isinstance(llm_json, dict) and "error" not in llm_json:
+                    df.at[idx, "strength"] = llm_json.get("strength", "")
+                    df.at[idx, "weaknesses"] = llm_json.get("weaknesses", "")
+                    df.at[idx, "speciality"] = llm_json.get("speciality", "")
+                    df.at[idx, "relevance rating"] = llm_json.get("relevance rating", "")
+                all_infos.append({"repo id": repo_id, **llm_json})
+            except Exception as e:
+                all_infos.append({"repo id": repo_id, "error": str(e)})
+        df.to_csv(csv_filename, index=False)
+        all_info_str = "\n\n".join([str(info) for info in all_infos])
+        from openai import OpenAI
+        import os
+        client = OpenAI(api_key=os.getenv("modal_api"))
+        client.base_url = os.getenv("base_url")
+        selection_prompt = (
+            "You are a helpful assistant. You are given a list of repo analyses in JSON format. "
+            "Choose the 3 repos that are the most impressive, relevant, or useful. "
+            "Return ONLY a JSON array of the 3 best repo ids, in order of preference, under the key 'top_repos'. "
+            "Example: {\"top_repos\": [\"repo1\", \"repo2\", \"repo3\"]}"
+        )
+        user_content = "Here are the repo analyses:\n" + all_info_str
+        response = client.chat.completions.create(
+            model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
+            messages=[
+                {"role": "system", "content": selection_prompt},
+                {"role": "user", "content": user_content}
+            ],
+            max_tokens=256,
+            temperature=0.3
+        )
+        selection_json = parse_llm_json_response(response.choices[0].message.content)
+        top_repos = selection_json.get("top_repos", [])
+        # Add a new assistant message to the chat state
+        new_message = ("", f"The top 3 repo IDs are: {', '.join(top_repos)}")
+        if state is None:
+            state = []
+        state = state + [list(new_message)]
+        return state
+    except Exception as e:
+        new_message = ("", f"Error in batch analysis: {e}")
+        if state is None:
+            state = []
+        state = state + [list(new_message)]
+        return state
+
 with gr.Blocks() as demo:
     page_state = gr.State(0)
 
@@ -266,6 +386,14 @@ with gr.Blocks() as demo:
         llm_output_txt_results = gr.Textbox(label="LLM Analysis Output", lines=10)
         back_to_start_btn4 = gr.Button("Back to Start")
 
+    # Add at the end, after results_page
+    batch_btn = gr.Button("Batch Analyze All & Select Top 3", visible=True)
+    batch_info_txt = gr.Textbox(label="All Repo Analyses", lines=10)
+    top3_txt = gr.Textbox(label="Top 3 Repo IDs", lines=1)
+
+    # Add a button to show top 3 in chat
+    show_top3_chat_btn = gr.Button("Show Top 3 Repo IDs in Chat", visible=True)
+
     # Navigation logic
     option_a_btn.click(go_to_input, inputs=None, outputs=[start_page, input_page, chatbot_page, results_page])
     option_b_btn.click(go_to_chatbot, inputs=None, outputs=[start_page, input_page, chatbot_page, results_page])
@@ -312,4 +440,10 @@ with gr.Blocks() as demo:
     # Add logic for the new button on results_page
     analyze_next_btn.click(show_combined_repo_and_llm, inputs=None, outputs=[combined_txt_results, llm_output_txt_results, results_df])
 
+    # Add logic for the batch button
+    batch_btn.click(batch_analyze_and_select_top, inputs=None, outputs=[batch_info_txt, top3_txt, df_output])
+
+    # Add logic for showing top 3 in chat
+    show_top3_chat_btn.click(batch_analyze_and_select_top_for_chat, inputs=[state], outputs=[state])
+
 demo.launch()