Basic Llamaindex implementation.

app.py

@@ -1,25 +1,75 @@
 import os
+from pathlib import Path
 import gradio as gr
 import requests
-import inspect
-import pandas as pd
+#from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
+from llama_index.llms.gemini import Gemini
+from llama_index.core.agent.workflow import ReActAgent
+from llama_index.core.tools import FunctionTool
+from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
+from llama_index.tools.wikipedia import WikipediaToolSpec
+from dotenv import load_dotenv
+
+try:
+    import mlflow
+    mlflow.set_experiment("final_handson")
+    mlflow.llama_index.autolog()
+except ImportError:
+    pass
+
+
+load_dotenv()
+# See https://discord.com/channels/879548962464493619/1360558713274109982:
+#For anyone who has run out of free tier, you can switch to a Gemini model in Google Colab:
+#go to https://aistudio.google.com/apikey and create a new API key
+#insert it into Google Colab using 'Secrets' tab on the left pane
+#make sure to grant access to the notebook!
+#in the notebook, use:
+#from google.colab import userdata
+#model = LiteLLMModel(model_id="gemini/gemini-2.0-flash-lite", api_key=userdata.get('GEMINI_API_KEY'))
+#agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+SYSTEM_PROMPT = (Path(__file__).parent / 'system_prompt.txt').read_text()
+GOOGLE_API_KEY = os.environ['GOOGLE_API_KEY']
 
 # --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
+        search_tool = FunctionTool.from_defaults(DuckDuckGoSearchToolSpec().duckduckgo_full_search)
+        wikipedia_load_tool = FunctionTool.from_defaults(WikipediaToolSpec().load_data)
+        wikipedia_search_tool = FunctionTool.from_defaults(WikipediaToolSpec().search_data)
+        self._tools = [search_tool, wikipedia_load_tool, wikipedia_search_tool]
+
+        self._llm = Gemini(api_key=GOOGLE_API_KEY, model="models/gemini-2.0-flash-lite")
+        self._agent = ReActAgent(tools=self._tools, llm=self._llm)
+        # Modify the react prompt.
+        self._agent.update_prompts({"react_header": SYSTEM_PROMPT})
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
+
+    async def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        agent_output = await self._agent.run(user_msg=question)
+        print(f"Agent returning answer: {agent_output}")
+        response_parts = str(agent_output).split('FINAL ANSWER: ')
+        if len(response_parts) > 1:
+            response = response_parts[-1]
+        else:
+            response = str(agent_output)
+        return response.strip()
+
+
+def fetch_questions(api_url: str = DEFAULT_API_URL):
+    questions_url = f"{api_url}/questions"
+    print(f"Fetching questions from: {questions_url}")
+    response = requests.get(questions_url, timeout=15)
+    response.raise_for_status()
+    questions_data = response.json()
+    return questions_data
+
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+async def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
@@ -35,10 +85,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return "Please Login to Hugging Face with the button.", None
 
     api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
     except Exception as e:
@@ -49,22 +98,19 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     print(agent_code)
 
     # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
+        questions_data = fetch_questions()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.JSONDecodeError as e:
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        # print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -80,7 +126,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = await agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:

requirements.txt

@@ -1,2 +1,7 @@
+dotenv
 gradio
-requests
+requests
+llama-index
+llama-index-llms-gemini
+llama-index-tools-duckduckgo
+llama-index-tools-wikipedia

system_prompt.txt

@@ -0,0 +1,41 @@
+You are a general AI assistant. I will ask you a question.
+
+## Tools
+
+You have access to a wide variety of tools. You are responsible for using the tools in any sequence you deem appropriate to complete the task at hand.
+This may require breaking the task into subtasks and using different tools to complete each subtask.
+
+You have access to the following tools:
+{tool_desc}
+
+
+## Output Format
+
+Please answer in the same language as the question and use the following format:
+
+```
+Thought: The current language of the user is: (user's language). I need to use a tool to help me answer the question.
+Action: tool name (one of {tool_names}) if using a tool.
+Action Input: the input to the tool, in a JSON format representing the kwargs (e.g. {{"input": "hello world", "num_beams": 5}})
+```
+
+Please ALWAYS start with a Thought.
+
+NEVER surround your response with markdown code markers. You may use code markers within your response if you need to.
+
+Please use a valid JSON format for the Action Input. Do NOT do this {{'input': 'hello world', 'num_beams': 5}}.
+
+If this format is used, the tool will respond in the following format:
+
+```
+Observation: tool response
+```
+
+You should keep repeating the above format till you have enough information to answer the question without using any more tools. At that point, you MUST respond with the following template:
+
+FINAL ANSWER: [YOUR FINAL ANSWER].
+
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string. don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+## Current Conversation
+
+Below is the current conversation consisting of interleaving human and assistant messages.