Initial_Commit_05-04-2025

app.py

@@ -0,0 +1,94 @@
+# App Section
+
+import os
+from typing import TypedDict, Annotated
+from langgraph.graph.message import add_messages
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
+from langgraph.prebuilt import ToolNode
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import tools_condition
+from langgraph.checkpoint.memory import MemorySaver
+from tools import search_tool, weather_info_tool, hub_stats_tool
+from retriever import guest_info_tool
+import gradio as gr
+
+from langchain_groq import ChatGroq
+
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+
+# Generate the chat interface, including the tools
+#llm = ChatGroq(model="qwen-2.5-coder-32b")
+llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash")
+
+tools = [search_tool, weather_info_tool, hub_stats_tool, guest_info_tool]
+chat_with_tools = llm.bind_tools(tools)
+
+# System message
+sys_msg = SystemMessage(content="""
+Role:
+You are a helpful agent and hosting a party.
+
+STRICT RULES:
+1. Follow a THINK → TOOL → THINK → RESPOND approach:
+    - THINK: Analyze the request and decide if any tool call is required or if it can be answered without a tool.
+    - TOOL: Perform only the necessary tool calls and collect responses.
+    - THINK: Re-evaluate tool response and determine the next step.
+    - RESPOND: Repeat THINK/TOOL/THINK as many times as required before providing a final answer.
+2. If no relevant tool exists, inform the user and provide guidance instead of making assumptions.
+""")
+
+# Generate the AgentState and Agent graph
+class AgentState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+
+def assistant(state: AgentState):
+    return {
+        "messages": [chat_with_tools.invoke(state["messages"])],
+    }
+
+## The graph
+builder = StateGraph(AgentState)
+
+# Define nodes: these do the work
+builder.add_node("assistant", assistant)
+builder.add_node("tools", ToolNode(tools))
+
+# Define edges: these determine how the control flow moves
+builder.add_edge(START, "assistant")
+builder.add_conditional_edges(
+    "assistant",
+    # If the latest message requires a tool, route to tools
+    # Otherwise, provide a direct response
+    tools_condition,
+)
+builder.add_edge("tools", "assistant")
+memory = MemorySaver()
+alfred = builder.compile(checkpointer=memory)
+
+config = {"configurable": {"thread_id": "7"}}
+#alfred
+
+def alfred_response(question):
+    messages = [HumanMessage(content=question)]
+    response = alfred.invoke({"messages": messages}, config)
+
+    return response['messages'][-1].content
+
+    #print("🎩 Alfred's Response:")
+    #print(response['messages'][-1].content)
+
+# Gradio
+
+input_textbox = gr.Textbox(label="Type your query here:", placeholder="Hi", lines=5)
+output_textbox = gr.Textbox(label="Type your query here:", placeholder="Hi", lines=5)
+gr.Interface(
+    fn=alfred_response, 
+    inputs=input_textbox, 
+    outputs=output_textbox, 
+    title="Party Organizer Helper", 
+    description="Helps you answer with different asks during Party", 
+    theme="peach",
+    examples=[["Whats weather now in Bangalore?"], ["The weather in Bangalore is Rainy with a temperature of 15°C."]],
+    live=True
+).launch(share=False)

retriever.py

@@ -0,0 +1,58 @@
+# Retriever Section
+
+import datasets
+from langchain.docstore.document import Document
+from langchain.tools import Tool
+from transformers import AutoTokenizer, TFAutoModel
+
+# Load the dataset
+guest_dataset = datasets.load_dataset("agents-course/unit3-invitees", split="train")
+
+def concatenate_text(examples):
+    return {
+        "text": "metadata={name:"+examples["name"]+"},"+
+        "page_content=Name:"+examples["name"]+"\n"+
+        "Relation:"+examples["relation"]+"\n"+
+        "Description:"+examples["description"]+"\n"+
+        "Email:"+examples["email"]
+           }
+
+docs = guest_dataset.map(concatenate_text)
+
+model_ckpt = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
+model = TFAutoModel.from_pretrained(model_ckpt, from_pt=True)
+
+def cls_pooling(model_output):
+    return model_output.last_hidden_state[:, 0]
+
+def get_embeddings(text_list):
+    encoded_input = tokenizer(
+        text_list, padding=True, truncation=True, return_tensors="tf"
+    )
+    encoded_input = {k: v for k, v in encoded_input.items()}
+    model_output = model(**encoded_input)
+    return cls_pooling(model_output)
+
+embeddings_dataset = docs.map(
+    lambda x: {"embeddings": get_embeddings(x["text"]).numpy()[0]}
+)
+
+embeddings_dataset.add_faiss_index(column="embeddings")
+
+def extract_text(query: str) -> str:
+    """Retrieves detailed information about gala guests based on their name or relation."""
+    query_embedding = get_embeddings([query]).numpy()
+    scores, samples = embeddings_dataset.get_nearest_examples(
+        "embeddings", query_embedding, k=2
+    )
+    if samples:
+        return "\n\n".join([text for text in samples["text"]])
+    else:
+        return "No matching guest information found."
+
+guest_info_tool = Tool(
+    name="guest_info_retriever",
+    func=extract_text,
+    description="Retrieves detailed information about gala guests based on their name or relation."
+)

tools.py

@@ -0,0 +1,49 @@
+# Tool Section
+
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain.tools import Tool
+from huggingface_hub import list_models
+import random
+
+# Internet Search Tool
+search_tool = DuckDuckGoSearchRun()
+
+def get_weather_info(location: str) -> str:
+    """Fetches dummy weather information for a given location."""
+    # Dummy weather data
+    weather_conditions = [
+        {"condition": "Rainy", "temp_c": 15},
+        {"condition": "Clear", "temp_c": 25},
+        {"condition": "Windy", "temp_c": 20}
+    ]
+    # Randomly select a weather condition
+    data = random.choice(weather_conditions)
+    return f"Weather in {location}: {data['condition']}, {data['temp_c']}°C"
+
+# Initialize the tool
+weather_info_tool = Tool(
+    name="get_weather_info",
+    func=get_weather_info,
+    description="Fetches dummy weather information for a given location."
+)
+
+def get_hub_stats(author: str) -> str:
+    """Fetches the most downloaded model from a specific author on the Hugging Face Hub."""
+    try:
+        # List models from the specified author, sorted by downloads
+        models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))
+
+        if models:
+            model = models[0]
+            return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
+        else:
+            return f"No models found for author {author}."
+    except Exception as e:
+        return f"Error fetching models for {author}: {str(e)}"
+
+# Initialize the tool
+hub_stats_tool = Tool(
+    name="get_hub_stats",
+    func=get_hub_stats,
+    description="Fetches the most downloaded model from a specific author on the Hugging Face Hub."
+)