Upload 3 files

README.md

@@ -1,15 +1,9 @@
 ---
-title: Template Final Assignment
-emoji: 🕵🏻‍♂️
-colorFrom: indigo
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.25.2
-app_file: app.py
-pinned: false
-hf_oauth: true
-# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
-hf_oauth_expiration_minutes: 480
+license: apache-2.0
+title: Search Engine
+sdk: streamlit
+emoji: 😻
+colorFrom: red
+colorTo: yellow
+short_description: Search Engine with LLM
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,196 +1,54 @@
-import os
-import gradio as gr
-import requests
-import inspect
-import pandas as pd
-
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        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)
-    try:
-        agent = BasicAgent()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    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()
-        if not questions_data:
-             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.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
-
-    # 3. Run your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
-        try:
-            submitted_answer = 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:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
-    if not answers_payload:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
-    )
-
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
-
-if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+import streamlit as st
+from langchain_groq import ChatGroq
+from langchain_community.utilities import ArxivAPIWrapper, WikipediaAPIWrapper
+from langchain_community.tools import ArxivQueryRun, WikipediaQueryRun, DuckDuckGoSearchRun
+from langchain.agents import initialize_agent, AgentType
+from langchain.callbacks import StreamlitCallbackHandler
+import os
+from dotenv import load_dotenv
+
+# Used the inbuilt tools of Arxiv and Wikipedia
+api_wrapper_arxiv = ArxivAPIWrapper(top_k_results=1, doc_content_chars_max=250)
+arxiv = ArxivQueryRun(api_wrapper=api_wrapper_arxiv)
+
+api_wrapper_wiki = WikipediaAPIWrapper(top_k_results=1, doc_content_chars_max=250)
+wiki = WikipediaQueryRun(api_wrapper=api_wrapper_wiki)
+
+search = DuckDuckGoSearchRun(name="Search")
+
+st.title("Langchain - Chat with Search")
+"""
+In this example, we're using `StreamlitCallbackHandler` to display the thoughts and actions of an agent in an interactive Streamlit app.
+Try more LangChain 🤝 Streamlit Agent examples at [github.com/langchain-ai/streamlit-agent](https://github.com/langchain-ai/streamlit-agent).
+"""
+
+# Sidebar for settings
+st.sidebar.title("Settings")
+api_key = st.sidebar.text_input("Enter your Groq API Key:", type="password")
+
+if "messages" not in st.session_state:
+    st.session_state["messages"] = [
+        {"role":"assistant", "content":"Hi, I am a Chatbot who can search the web. How can I help you ?"}
+    ]
+
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+if prompt:=st.chat_input(placeholder="What is machine learning ?"):
+    st.session_state.messages.append({"role":"user", "content":prompt})
+    st.chat_message("user").write(prompt)
+
+    llm = ChatGroq(groq_api_key=api_key, model_name="Llama3-8b-8192", streaming=True)
+    tools = [search, arxiv, wiki]
+
+    search_agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, handle_parsing_errors=True)
+
+    with st.chat_message("assistant"):
+        st_cb = StreamlitCallbackHandler(st.container(), expand_new_thoughts=False)
+        response = search_agent.run(st.session_state.messages, callbacks=[st_cb])
+        st.session_state.messages.append({'role':'assistant', "content":response})
+        st.write(response)
+    
+
+
+

requirements.txt

@@ -1,2 +1,63 @@
-gradio
-requests
+langchain
+ipykernel
+python-dotenv
+langchain_community
+langchain-community
+pypdf
+bs4
+beautifulsoup4
+arxiv
+pymupdf
+wikipedia
+langchain-text-splitters
+langchain-openai
+chromadb
+sentence_transformers
+langchain_huggingface
+faiss-cpu
+langchain_chroma
+langchain-chroma
+streamlit
+langchain-ollama
+langchain_groq
+langchain_core
+uvicorn
+fastapi
+pydantic
+langchain
+langserve
+uvicorn
+sse_starlette
+packaging
+langchain-groq 
+pandas 
+duckdb 
+httpx
+openai
+duckduckgo-search
+langchain-google-genai 
+google-generativeai
+mysql-connector-python
+SQLAlchemy
+validators==0.28.1
+youtube_transcript_api
+pytube
+unstructured
+numexpr
+huggingface_hub
+cassio
+datasets
+tiktoken
+PyPDF2
+gradio
+boto3
+botocore
+awscli
+langchain_nvidia_ai_endpoints
+crewai
+crewai_tools
+typing-extensions
+pinecone
+pinecone-client 
+pinecone-text
+pinecone-notebooks