GoogleSearchTool-fix

bonus-unit2/monitoring-and-evaluating-agents-notebook.ipynb

@@ -1,647 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Bonus Unit 1: Observability and Evaluation of Agents\n",
-        "\n",
-        "In this tutorial, we will learn how to **monitor the internal steps (traces) of our AI agent** and **evaluate its performance** using open-source observability tools.\n",
-        "\n",
-        "The ability to observe and evaluate an agent’s behavior is essential for:\n",
-        "- Debugging issues when tasks fail or produce suboptimal results\n",
-        "- Monitoring costs and performance in real-time\n",
-        "- Improving reliability and safety through continuous feedback\n",
-        "\n",
-        "This notebook is part of the [Hugging Face Agents Course](https://www.hf.co/learn/agents-course/unit1/introduction)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Exercise Prerequisites 🏗️\n",
-        "\n",
-        "Before running this notebook, please be sure you have:\n",
-        "\n",
-        "🔲 📚  **Studied** [Introduction to Agents](https://huggingface.co/learn/agents-course/unit1/introduction)\n",
-        "\n",
-        "🔲 📚  **Studied** [The smolagents framework](https://huggingface.co/learn/agents-course/unit2/smolagents/introduction)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Step 0: Install the Required Libraries\n",
-        "\n",
-        "We will need a few libraries that allow us to run, monitor, and evaluate our agents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%pip install 'smolagents[telemetry]'\n",
-        "%pip install opentelemetry-sdk opentelemetry-exporter-otlp openinference-instrumentation-smolagents\n",
-        "%pip install langfuse datasets 'smolagents[gradio]' gradio"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Step 1: Instrument Your Agent\n",
-        "\n",
-        "In this notebook, we will use [Langfuse](https://langfuse.com/) as our observability tool, but you can use **any other OpenTelemetry-compatible service**. The code below shows how to set environment variables for Langfuse (or any OTel endpoint) and how to instrument your smolagent.\n",
-        "\n",
-        "**Note:** If you are using LlamaIndex or LangGraph, you can find documentation on instrumenting them [here](https://langfuse.com/docs/integrations/llama-index/workflows) and [here](https://langfuse.com/docs/integrations/langchain/example-python-langgraph). "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import base64\n",
-        "\n",
-        "# Get your own keys from https://cloud.langfuse.com\n",
-        "os.environ[\"LANGFUSE_PUBLIC_KEY\"] = \"pk-lf-...\" \n",
-        "os.environ[\"LANGFUSE_SECRET_KEY\"] = \"sk-lf-...\" \n",
-        "os.environ[\"LANGFUSE_HOST\"] = \"https://cloud.langfuse.com\"  # 🇪🇺 EU region example\n",
-        "# os.environ[\"LANGFUSE_HOST\"] = \"https://us.cloud.langfuse.com\"  # 🇺🇸 US region example\n",
-        "\n",
-        "LANGFUSE_AUTH = base64.b64encode(\n",
-        "    f\"{os.environ.get('LANGFUSE_PUBLIC_KEY')}:{os.environ.get('LANGFUSE_SECRET_KEY')}\".encode()\n",
-        ").decode()\n",
-        "\n",
-        "os.environ[\"OTEL_EXPORTER_OTLP_ENDPOINT\"] = os.environ.get(\"LANGFUSE_HOST\") + \"/api/public/otel\"\n",
-        "os.environ[\"OTEL_EXPORTER_OTLP_HEADERS\"] = f\"Authorization=Basic {LANGFUSE_AUTH}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Set your Hugging Face and other tokens/secrets as environment variable\n",
-        "os.environ[\"HF_TOKEN\"] = \"hf_...\" "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from opentelemetry.sdk.trace import TracerProvider\n",
-        "from openinference.instrumentation.smolagents import SmolagentsInstrumentor\n",
-        "from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter\n",
-        "from opentelemetry.sdk.trace.export import SimpleSpanProcessor\n",
-        " \n",
-        "# Create a TracerProvider for OpenTelemetry\n",
-        "trace_provider = TracerProvider()\n",
-        "\n",
-        "# Add a SimpleSpanProcessor with the OTLPSpanExporter to send traces\n",
-        "trace_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter()))\n",
-        "\n",
-        "# Set the global default tracer provider\n",
-        "from opentelemetry import trace\n",
-        "trace.set_tracer_provider(trace_provider)\n",
-        "tracer = trace.get_tracer(__name__)\n",
-        "\n",
-        "# Instrument smolagents with the configured provider\n",
-        "SmolagentsInstrumentor().instrument(tracer_provider=trace_provider)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Step 2: Test Your Instrumentation\n",
-        "\n",
-        "Here is a simple CodeAgent from smolagents that calculates `1+1`. We run it to confirm that the instrumentation is working correctly. If everything is set up correctly, you will see logs/spans in your observability dashboard."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from smolagents import HfApiModel, CodeAgent\n",
-        "\n",
-        "# Create a simple agent to test instrumentation\n",
-        "agent = CodeAgent(\n",
-        "    tools=[],\n",
-        "    model=HfApiModel()\n",
-        ")\n",
-        "\n",
-        "agent.run(\"1+1=\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Check your [Langfuse Traces Dashboard](https://cloud.langfuse.com/traces) (or your chosen observability tool) to confirm that the spans and logs have been recorded.\n",
-        "\n",
-        "Example screenshot from Langfuse:\n",
-        "\n",
-        "![Example trace in Langfuse](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/first-example-trace.png)\n",
-        "\n",
-        "_[Link to the trace](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/1b94d6888258e0998329cdb72a371155?timestamp=2025-03-10T11%3A59%3A41.743Z)_"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Step 3: Observe and Evaluate a More Complex Agent\n",
-        "\n",
-        "Now that you have confirmed your instrumentation works, let's try a more complex query so we can see how advanced metrics (token usage, latency, costs, etc.) are tracked."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from smolagents import (CodeAgent, DuckDuckGoSearchTool, HfApiModel)\n",
-        "\n",
-        "search_tool = DuckDuckGoSearchTool()\n",
-        "agent = CodeAgent(tools=[search_tool], model=HfApiModel())\n",
-        "\n",
-        "agent.run(\"How many Rubik's Cubes could you fit inside the Notre Dame Cathedral?\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Trace Structure\n",
-        "\n",
-        "Most observability tools record a **trace** that contains **spans**, which represent each step of your agent’s logic. Here, the trace contains the overall agent run and sub-spans for:\n",
-        "- The tool calls (DuckDuckGoSearchTool)\n",
-        "- The LLM calls (HfApiModel)\n",
-        "\n",
-        "You can inspect these to see precisely where time is spent, how many tokens are used, and so on:\n",
-        "\n",
-        "![Trace tree in Langfuse](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/trace-tree.png)\n",
-        "\n",
-        "_[Link to the trace](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/1ac33b89ffd5e75d4265b62900c348ed?timestamp=2025-03-07T13%3A45%3A09.149Z&display=preview)_"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Online Evaluation\n",
-        "\n",
-        "In the previous section, we learned about the difference between online and offline evaluation. Now, we will see how to monitor your agent in production and evaluate it live.\n",
-        "\n",
-        "### Common Metrics to Track in Production\n",
-        "\n",
-        "1. **Costs** — The smolagents instrumentation captures token usage, which you can transform into approximate costs by assigning a price per token.\n",
-        "2. **Latency** — Observe the time it takes to complete each step, or the entire run.\n",
-        "3. **User Feedback** — Users can provide direct feedback (thumbs up/down) to help refine or correct the agent.\n",
-        "4. **LLM-as-a-Judge** — Use a separate LLM to evaluate your agent’s output in near real-time (e.g., checking for toxicity or correctness).\n",
-        "\n",
-        "Below, we show examples of these metrics."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 1. Costs\n",
-        "\n",
-        "Below is a screenshot showing usage for `Qwen2.5-Coder-32B-Instruct` calls. This is useful to see costly steps and optimize your agent. \n",
-        "\n",
-        "![Costs](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/smolagents-costs.png)\n",
-        "\n",
-        "_[Link to the trace](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/1ac33b89ffd5e75d4265b62900c348ed?timestamp=2025-03-07T13%3A45%3A09.149Z&display=preview)_"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 2. Latency\n",
-        "\n",
-        "We can also see how long it took to complete each step. In the example below, the entire conversation took 32 seconds, which you can break down by step. This helps you identify bottlenecks and optimize your agent.\n",
-        "\n",
-        "![Latency](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/smolagents-latency.png)\n",
-        "\n",
-        "_[Link to the trace](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/1ac33b89ffd5e75d4265b62900c348ed?timestamp=2025-03-07T13%3A45%3A09.149Z&display=preview)_"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 3. Additional Attributes\n",
-        "\n",
-        "You may also pass additional attributes—such as user IDs, session IDs, or tags—by setting them on the spans. For example, smolagents instrumentation uses OpenTelemetry to attach attributes like `langfuse.user.id` or custom tags."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from smolagents import (CodeAgent, DuckDuckGoSearchTool, HfApiModel)\n",
-        "from opentelemetry import trace\n",
-        "\n",
-        "search_tool = DuckDuckGoSearchTool()\n",
-        "agent = CodeAgent(\n",
-        "    tools=[search_tool],\n",
-        "    model=HfApiModel()\n",
-        ")\n",
-        "\n",
-        "with tracer.start_as_current_span(\"Smolagent-Trace\") as span:\n",
-        "    span.set_attribute(\"langfuse.user.id\", \"smolagent-user-123\")\n",
-        "    span.set_attribute(\"langfuse.session.id\", \"smolagent-session-123456789\")\n",
-        "    span.set_attribute(\"langfuse.tags\", [\"city-question\", \"testing-agents\"])\n",
-        "\n",
-        "    agent.run(\"What is the capital of Germany?\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Enhancing agent runs with additional metrics](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/smolagents-attributes.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 4. User Feedback\n",
-        "\n",
-        "If your agent is embedded into a user interface, you can record direct user feedback (like a thumbs-up/down in a chat UI). Below is an example using [Gradio](https://gradio.app/) to embed a chat with a simple feedback mechanism.\n",
-        "\n",
-        "In the code snippet below, when a user sends a chat message, we capture the OpenTelemetry trace ID. If the user likes/dislikes the last answer, we attach a score to the trace."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import gradio as gr\n",
-        "from opentelemetry.trace import format_trace_id\n",
-        "from smolagents import (CodeAgent, HfApiModel)\n",
-        "from langfuse import Langfuse\n",
-        "\n",
-        "langfuse = Langfuse()\n",
-        "model = HfApiModel()\n",
-        "agent = CodeAgent(tools=[], model=model, add_base_tools=True)\n",
-        "\n",
-        "formatted_trace_id = None  # We'll store the current trace_id globally for demonstration\n",
-        "\n",
-        "def respond(prompt, history):\n",
-        "    with trace.get_tracer(__name__).start_as_current_span(\"Smolagent-Trace\") as span:\n",
-        "        output = agent.run(prompt)\n",
-        "\n",
-        "        current_span = trace.get_current_span()\n",
-        "        span_context = current_span.get_span_context()\n",
-        "        trace_id = span_context.trace_id\n",
-        "        global formatted_trace_id\n",
-        "        formatted_trace_id = str(format_trace_id(trace_id))\n",
-        "        langfuse.trace(id=formatted_trace_id, input=prompt, output=output)\n",
-        "\n",
-        "    history.append({\"role\": \"assistant\", \"content\": str(output)})\n",
-        "    return history\n",
-        "\n",
-        "def handle_like(data: gr.LikeData):\n",
-        "    # For demonstration, we map user feedback to a 1 (like) or 0 (dislike)\n",
-        "    if data.liked:\n",
-        "        langfuse.score(\n",
-        "            value=1,\n",
-        "            name=\"user-feedback\",\n",
-        "            trace_id=formatted_trace_id\n",
-        "        )\n",
-        "    else:\n",
-        "        langfuse.score(\n",
-        "            value=0,\n",
-        "            name=\"user-feedback\",\n",
-        "            trace_id=formatted_trace_id\n",
-        "        )\n",
-        "\n",
-        "with gr.Blocks() as demo:\n",
-        "    chatbot = gr.Chatbot(label=\"Chat\", type=\"messages\")\n",
-        "    prompt_box = gr.Textbox(placeholder=\"Type your message...\", label=\"Your message\")\n",
-        "\n",
-        "    # When the user presses 'Enter' on the prompt, we run 'respond'\n",
-        "    prompt_box.submit(\n",
-        "        fn=respond,\n",
-        "        inputs=[prompt_box, chatbot],\n",
-        "        outputs=chatbot\n",
-        "    )\n",
-        "\n",
-        "    # When the user clicks a 'like' button on a message, we run 'handle_like'\n",
-        "    chatbot.like(handle_like, None, None)\n",
-        "\n",
-        "demo.launch()\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "User feedback is then captured in your observability tool:\n",
-        "\n",
-        "![User feedback is being captured in Langfuse](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/user-feedback-gradio.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 5. LLM-as-a-Judge\n",
-        "\n",
-        "LLM-as-a-Judge is another way to automatically evaluate your agent's output. You can set up a separate LLM call to gauge the output’s correctness, toxicity, style, or any other criteria you care about.\n",
-        "\n",
-        "**Workflow**:\n",
-        "1. You define an **Evaluation Template**, e.g., \"Check if the text is toxic.\"\n",
-        "2. Each time your agent generates output, you pass that output to your \"judge\" LLM with the template.\n",
-        "3. The judge LLM responds with a rating or label that you log to your observability tool.\n",
-        "\n",
-        "Example from Langfuse:\n",
-        "\n",
-        "![LLM-as-a-Judge Evaluation Template](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/evaluator-template.png)\n",
-        "![LLM-as-a-Judge Evaluator](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/evaluator.png)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Example: Checking if the agent’s output is toxic or not.\n",
-        "from smolagents import (CodeAgent, DuckDuckGoSearchTool, HfApiModel)\n",
-        "\n",
-        "search_tool = DuckDuckGoSearchTool()\n",
-        "agent = CodeAgent(tools=[search_tool], model=HfApiModel())\n",
-        "\n",
-        "agent.run(\"Can eating carrots improve your vision?\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can see that the answer of this example is judged as \"not toxic\".\n",
-        "\n",
-        "![LLM-as-a-Judge Evaluation Score](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/llm-as-a-judge-score.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### 6. Observability Metrics Overview\n",
-        "\n",
-        "All of these metrics can be visualized together in dashboards. This enables you to quickly see how your agent performs across many sessions and helps you to track quality metrics over time.\n",
-        "\n",
-        "![Observability metrics overview](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/langfuse-dashboard.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Offline Evaluation\n",
-        "\n",
-        "Online evaluation is essential for live feedback, but you also need **offline evaluation**—systematic checks before or during development. This helps maintain quality and reliability before rolling changes into production."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Dataset Evaluation\n",
-        "\n",
-        "In offline evaluation, you typically:\n",
-        "1. Have a benchmark dataset (with prompt and expected output pairs)\n",
-        "2. Run your agent on that dataset\n",
-        "3. Compare outputs to the expected results or use an additional scoring mechanism\n",
-        "\n",
-        "Below, we demonstrate this approach with the [GSM8K dataset](https://huggingface.co/datasets/gsm8k), which contains math questions and solutions."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import pandas as pd\n",
-        "from datasets import load_dataset\n",
-        "\n",
-        "# Fetch GSM8K from Hugging Face\n",
-        "dataset = load_dataset(\"openai/gsm8k\", 'main', split='train')\n",
-        "df = pd.DataFrame(dataset)\n",
-        "print(\"First few rows of GSM8K dataset:\")\n",
-        "print(df.head())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Next, we create a dataset entity in Langfuse to track the runs. Then, we add each item from the dataset to the system. (If you’re not using Langfuse, you might simply store these in your own database or local file for analysis.)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from langfuse import Langfuse\n",
-        "langfuse = Langfuse()\n",
-        "\n",
-        "langfuse_dataset_name = \"gsm8k_dataset_huggingface\"\n",
-        "\n",
-        "# Create a dataset in Langfuse\n",
-        "langfuse.create_dataset(\n",
-        "    name=langfuse_dataset_name,\n",
-        "    description=\"GSM8K benchmark dataset uploaded from Huggingface\",\n",
-        "    metadata={\n",
-        "        \"date\": \"2025-03-10\", \n",
-        "        \"type\": \"benchmark\"\n",
-        "    }\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "for idx, row in df.iterrows():\n",
-        "    langfuse.create_dataset_item(\n",
-        "        dataset_name=langfuse_dataset_name,\n",
-        "        input={\"text\": row[\"question\"]},\n",
-        "        expected_output={\"text\": row[\"answer\"]},\n",
-        "        metadata={\"source_index\": idx}\n",
-        "    )\n",
-        "    if idx >= 9: # Upload only the first 10 items for demonstration\n",
-        "        break"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Dataset items in Langfuse](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/example-dataset.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Running the Agent on the Dataset\n",
-        "\n",
-        "We define a helper function `run_smolagent()` that:\n",
-        "1. Starts an OpenTelemetry span\n",
-        "2. Runs our agent on the prompt\n",
-        "3. Records the trace ID in Langfuse\n",
-        "\n",
-        "Then, we loop over each dataset item, run the agent, and link the trace to the dataset item. We can also attach a quick evaluation score if desired."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from opentelemetry.trace import format_trace_id\n",
-        "from smolagents import (CodeAgent, HfApiModel, LiteLLMModel)\n",
-        "\n",
-        "# Example: using HfApiModel or LiteLLMModel to access openai, anthropic, gemini, etc. models:\n",
-        "model = HfApiModel()\n",
-        "\n",
-        "agent = CodeAgent(\n",
-        "    tools=[],\n",
-        "    model=model,\n",
-        "    add_base_tools=True\n",
-        ")\n",
-        "\n",
-        "def run_smolagent(question):\n",
-        "    with tracer.start_as_current_span(\"Smolagent-Trace\") as span:\n",
-        "        span.set_attribute(\"langfuse.tag\", \"dataset-run\")\n",
-        "        output = agent.run(question)\n",
-        "\n",
-        "        current_span = trace.get_current_span()\n",
-        "        span_context = current_span.get_span_context()\n",
-        "        trace_id = span_context.trace_id\n",
-        "        formatted_trace_id = format_trace_id(trace_id)\n",
-        "\n",
-        "        langfuse_trace = langfuse.trace(\n",
-        "            id=formatted_trace_id, \n",
-        "            input=question, \n",
-        "            output=output\n",
-        "        )\n",
-        "    return langfuse_trace, output"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "dataset = langfuse.get_dataset(langfuse_dataset_name)\n",
-        "\n",
-        "# Run our agent against each dataset item (limited to first 10 above)\n",
-        "for item in dataset.items:\n",
-        "    langfuse_trace, output = run_smolagent(item.input[\"text\"])\n",
-        "\n",
-        "    # Link the trace to the dataset item for analysis\n",
-        "    item.link(\n",
-        "        langfuse_trace,\n",
-        "        run_name=\"smolagent-notebook-run-01\",\n",
-        "        run_metadata={ \"model\": model.model_id }\n",
-        "    )\n",
-        "\n",
-        "    # Optionally, store a quick evaluation score for demonstration\n",
-        "    langfuse_trace.score(\n",
-        "        name=\"<example_eval>\",\n",
-        "        value=1,\n",
-        "        comment=\"This is a comment\"\n",
-        "    )\n",
-        "\n",
-        "# Flush data to ensure all telemetry is sent\n",
-        "langfuse.flush()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can repeat this process with different:\n",
-        "- Models (OpenAI GPT, local LLM, etc.)\n",
-        "- Tools (search vs. no search)\n",
-        "- Prompts (different system messages)\n",
-        "\n",
-        "Then compare them side-by-side in your observability tool:\n",
-        "\n",
-        "![Dataset run overview](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/dataset_runs.png)\n",
-        "![Dataset run comparison](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/bonus-unit2/dataset-run-comparison.png)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Final Thoughts\n",
-        "\n",
-        "In this notebook, we covered how to:\n",
-        "1. **Set up Observability** using smolagents + OpenTelemetry exporters\n",
-        "2. **Check Instrumentation** by running a simple agent\n",
-        "3. **Capture Detailed Metrics** (cost, latency, etc.) through an observability tools\n",
-        "4. **Collect User Feedback** via a Gradio interface\n",
-        "5. **Use LLM-as-a-Judge** to automatically evaluate outputs\n",
-        "6. **Perform Offline Evaluation** with a benchmark dataset\n",
-        "\n",
-        "🤗 Happy coding!"
-      ]
-    }
-  ],
-  "metadata": {
-    "kernelspec": {
-      "display_name": "Python 3",
-      "language": "python",
-      "name": "python3"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.13.2"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

unit2/langgraph/agent.ipynb

@@ -1,560 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "98f5e36a-da49-4ae2-8c74-b910a2f992fc",
-   "metadata": {},
-   "source": [
-    "# Agent\n",
-    "\n",
-    "In this notebook, **we're going to build a simple agent using using LangGraph**.\n",
-    "\n",
-    "This notebook is part of the <a href=\"https://www.hf.co/learn/agents-course\">Hugging Face Agents Course</a>, a free course from beginner to expert, where you learn to build Agents.\n",
-    "\n",
-    "![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n",
-    "\n",
-    "As seen in the Unit 1, an agent needs 3 steps as introduced in the ReAct architecture :\n",
-    "[ReAct](https://react-lm.github.io/), a general agent architecture.\n",
-    "  \n",
-    "* `act` - let the model call specific tools \n",
-    "* `observe` - pass the tool output back to the model \n",
-    "* `reason` - let the model reason about the tool output to decide what to do next (e.g., call another tool or just respond directly)\n",
-    "\n",
-    "\n",
-    "![Agent](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/unit2/LangGraph/Agent.png)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "63edff5a-724b-474d-9db8-37f0ae936c76",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install -q -U langchain_openai langchain_core langgraph"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "356a6482",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "# Please setp your own key.\n",
-    "os.environ[\"OPENAI_API_KEY\"]=\"sk-xxxxxx\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "id": "71795ff1-d6a7-448d-8b55-88bbd1ed3dbe",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import base64\n",
-    "from typing import List\n",
-    "from langchain.schema import HumanMessage\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "vision_llm = ChatOpenAI(model=\"gpt-4o\")\n",
-    "\n",
-    "def extract_text(img_path: str) -> str:\n",
-    "    \"\"\"\n",
-    "    Extract text from an image file using a multimodal model.\n",
-    "\n",
-    "    Args:\n",
-    "        img_path: A local image file path (strings).\n",
-    "\n",
-    "    Returns:\n",
-    "        A single string containing the concatenated text extracted from each image.\n",
-    "    \"\"\"\n",
-    "    all_text = \"\"\n",
-    "    try:\n",
-    "       \n",
-    "        # Read image and encode as base64\n",
-    "        with open(img_path, \"rb\") as image_file:\n",
-    "            image_bytes = image_file.read()\n",
-    "\n",
-    "        image_base64 = base64.b64encode(image_bytes).decode(\"utf-8\")\n",
-    "\n",
-    "        # Prepare the prompt including the base64 image data\n",
-    "        message = [\n",
-    "            HumanMessage(\n",
-    "                content=[\n",
-    "                    {\n",
-    "                        \"type\": \"text\",\n",
-    "                        \"text\": (\n",
-    "                            \"Extract all the text from this image. \"\n",
-    "                            \"Return only the extracted text, no explanations.\"\n",
-    "                        ),\n",
-    "                    },\n",
-    "                    {\n",
-    "                        \"type\": \"image_url\",\n",
-    "                        \"image_url\": {\n",
-    "                            \"url\": f\"data:image/png;base64,{image_base64}\"\n",
-    "                        },\n",
-    "                    },\n",
-    "                ]\n",
-    "            )\n",
-    "        ]\n",
-    "\n",
-    "        # Call the vision-capable model\n",
-    "        response = vision_llm.invoke(message)\n",
-    "\n",
-    "        # Append extracted text\n",
-    "        all_text += response.content + \"\\n\\n\"\n",
-    "\n",
-    "        return all_text.strip()\n",
-    "    except Exception as e:\n",
-    "        # You can choose whether to raise or just return an empty string / error message\n",
-    "        error_msg = f\"Error extracting text: {str(e)}\"\n",
-    "        print(error_msg)\n",
-    "        return \"\"\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-4o\")\n",
-    "\n",
-    "def divide(a: int, b: int) -> float:\n",
-    "    \"\"\"Divide a and b.\"\"\"\n",
-    "    return a / b\n",
-    "\n",
-    "tools = [\n",
-    "    divide,\n",
-    "    extract_text\n",
-    "]\n",
-    "llm_with_tools = llm.bind_tools(tools, parallel_tool_calls=False)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a2cec014-3023-405c-be79-de8fc7adb346",
-   "metadata": {},
-   "source": [
-    "Let's create our LLM and prompt it with the overall desired agent behavior."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "id": "deb674bc-49b2-485a-b0c3-4d7b05a0bfac",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from typing import TypedDict, Annotated, List, Any, Optional\n",
-    "from langchain_core.messages import AnyMessage\n",
-    "from langgraph.graph.message import add_messages\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input document\n",
-    "    input_file:  Optional[str]  # Contains file path, type (PNG)\n",
-    "    messages: Annotated[list[AnyMessage], add_messages]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 76,
-   "id": "d061813f-ebc0-432c-91ec-3b42b15c30b6",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import HumanMessage, SystemMessage\n",
-    "from langchain_core.utils.function_calling import convert_to_openai_tool\n",
-    "\n",
-    "\n",
-    "# AgentState\n",
-    "def assistant(state: AgentState):\n",
-    "    # System message\n",
-    "    textual_description_of_tool=\"\"\"\n",
-    "extract_text(img_path: str) -> str:\n",
-    "    Extract text from an image file using a multimodal model.\n",
-    "\n",
-    "    Args:\n",
-    "        img_path: A local image file path (strings).\n",
-    "\n",
-    "    Returns:\n",
-    "        A single string containing the concatenated text extracted from each image.\n",
-    "divide(a: int, b: int) -> float:\n",
-    "    Divide a and b\n",
-    "\"\"\"\n",
-    "    image=state[\"input_file\"]\n",
-    "    sys_msg = SystemMessage(content=f\"You are an helpful agent that can analyse some images and run some computatio without provided tools :\\n{textual_description_of_tool} \\n You have access to some otpional images. Currently the loaded images is : {image}\")\n",
-    "\n",
-    "\n",
-    "    return {\"messages\": [llm_with_tools.invoke([sys_msg] + state[\"messages\"])],\"input_file\":state[\"input_file\"]}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "4eb43343-9a6f-42cb-86e6-4380f928633c",
-   "metadata": {},
-   "source": [
-    "We define a `Tools` node with our list of tools.\n",
-    "\n",
-    "The `Assistant` node is just our model with bound tools.\n",
-    "\n",
-    "We create a graph with `Assistant` and `Tools` nodes.\n",
-    "\n",
-    "We add `tools_condition` edge, which routes to `End` or to `Tools` based on  whether the `Assistant` calls a tool.\n",
-    "\n",
-    "Now, we add one new step:\n",
-    "\n",
-    "We connect the `Tools` node *back* to the `Assistant`, forming a loop.\n",
-    "\n",
-    "* After the `assistant` node executes, `tools_condition` checks if the model's output is a tool call.\n",
-    "* If it is a tool call, the flow is directed to the `tools` node.\n",
-    "* The `tools` node connects back to `assistant`.\n",
-    "* This loop continues as long as the model decides to call tools.\n",
-    "* If the model response is not a tool call, the flow is directed to END, terminating the process."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "id": "aef13cd4-05a6-4084-a620-2e7b91d9a72f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<IPython.core.display.Image object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from langgraph.graph import START, StateGraph\n",
-    "from langgraph.prebuilt import tools_condition\n",
-    "from langgraph.prebuilt import ToolNode\n",
-    "from IPython.display import Image, display\n",
-    "\n",
-    "# Graph\n",
-    "builder = StateGraph(AgentState)\n",
-    "\n",
-    "# Define nodes: these do the work\n",
-    "builder.add_node(\"assistant\", assistant)\n",
-    "builder.add_node(\"tools\", ToolNode(tools))\n",
-    "\n",
-    "# Define edges: these determine how the control flow moves\n",
-    "builder.add_edge(START, \"assistant\")\n",
-    "builder.add_conditional_edges(\n",
-    "    \"assistant\",\n",
-    "    # If the latest message (result) from assistant is a tool call -> tools_condition routes to tools\n",
-    "    # If the latest message (result) from assistant is a not a tool call -> tools_condition routes to END\n",
-    "    tools_condition,\n",
-    ")\n",
-    "builder.add_edge(\"tools\", \"assistant\")\n",
-    "react_graph = builder.compile()\n",
-    "\n",
-    "# Show\n",
-    "display(Image(react_graph.get_graph(xray=True).draw_mermaid_png()))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 78,
-   "id": "75602459-d8ca-47b4-9518-3f38343ebfe4",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "messages = [HumanMessage(content=\"Divide 6790 by 5\")]\n",
-    "\n",
-    "messages = react_graph.invoke({\"messages\": messages,\"input_file\":None})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 79,
-   "id": "b517142d-c40c-48bf-a5b8-c8409427aa79",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "Divide 6790 by 5\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  divide (call_s0G5ewtIQyHUCOv0fClsCpgh)\n",
-      " Call ID: call_s0G5ewtIQyHUCOv0fClsCpgh\n",
-      "  Args:\n",
-      "    a: 6790\n",
-      "    b: 5\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: divide\n",
-      "\n",
-      "1358.0\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "The result of dividing 6790 by 5 is 1358.0.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in messages['messages']:\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "08386393-c270-43a5-bde2-2b4075238971",
-   "metadata": {},
-   "source": [
-    "## Training program\n",
-    "MR Wayne left a note with his training program for the week. I came up with a recipe for dinner leaft in a note.\n",
-    "\n",
-    "you can find the document [HERE](https://huggingface.co/datasets/agents-course/course-images/blob/main/en/unit2/LangGraph/Batman_training_and_meals.png), so download it and upload it in the local folder.\n",
-    "\n",
-    "![Training](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/unit2/LangGraph/Batman_training_and_meals.png)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 82,
-   "id": "f6e97e84-3b05-4aaf-a38f-1de9b73cd37f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "messages = [HumanMessage(content=\"According the note provided by MR wayne in the provided images. What's the list of items I should buy for the dinner menu ?\")]\n",
-    "\n",
-    "messages = react_graph.invoke({\"messages\": messages,\"input_file\":\"Batman_training_and_meals.png\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 83,
-   "id": "17686d52-c7ba-407b-a13f-f6c37668e5b0",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "According the note provided by MR wayne in the provided images. What's the list of tiems I should buy for the dinner menu ?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "Tool Calls:\n",
-      "  extract_text (call_JalVBOR82hwRknFcplnLoTtG)\n",
-      " Call ID: call_JalVBOR82hwRknFcplnLoTtG\n",
-      "  Args:\n",
-      "    img_path: Batman_training_and_meals.png\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: extract_text\n",
-      "\n",
-      "TRAINING SCHEDULE\n",
-      "For the week of 2/20-2/26\n",
-      "\n",
-      "SUNDAY 2/20\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minute meditation\n",
-      "\n",
-      "EVENING\n",
-      "clean and jerk lifts—3 reps/8 sets. 262 lbs.\n",
-      "5 sets metabolic conditioning:\n",
-      "10 mile run\n",
-      "12 kettlebell swings\n",
-      "12 pull-ups\n",
-      "30 minutes flexibility\n",
-      "30 minutes sparring\n",
-      "\n",
-      "MONDAY 2/21\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minutes traditional kata (focus on Japanese forms)\n",
-      "\n",
-      "EVENING\n",
-      "5 sets 20 foot rope climb\n",
-      "30 minutes gymnastics (work on muscle ups in\n",
-      "particular)\n",
-      "high bar jumps—12 reps/8 sets\n",
-      "crunches—50 reps/5 sets\n",
-      "30 minutes heavy bag\n",
-      "30 minutes flexibility\n",
-      "20 minutes target practice\n",
-      "\n",
-      "TUESDAY 2/22\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minutes yoga\n",
-      "\n",
-      "EVENING\n",
-      "off day\n",
-      "leg heavy dead lift—5 reps/7 sets. 600 lbs.\n",
-      "clean and jerk lift—3 reps/10 sets\n",
-      "30 minutes sparring\n",
-      "\n",
-      "WEDNESDAY 2/23\n",
-      "OFF DAY\n",
-      "\n",
-      "MORNING\n",
-      "20-mile run—last week’s time was 4:50 per mile.\n",
-      "Need to better that time by a half a minute.\n",
-      "\n",
-      "EVENING\n",
-      "skill training only\n",
-      "30 minutes yoga\n",
-      "30 minutes meditation\n",
-      "30 minutes body basics\n",
-      "30 minutes bow basics\n",
-      "30 minutes sword basics\n",
-      "30 minutes observational\n",
-      "exercise\n",
-      "30 minutes kata\n",
-      "30 minutes pressure points\n",
-      "30 minutes modus and pressure points\n",
-      "\n",
-      "THURSDAY 2/24\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minute meditation\n",
-      "30 minutes traditional kata\n",
-      "(focus on Japanese forms)\n",
-      "\n",
-      "EVENING\n",
-      "squats—10 reps/5 sets. 525 lbs.\n",
-      "30 minutes flexibility\n",
-      "crunches—50 reps/5 sets\n",
-      "20 minutes target practice\n",
-      "30 minutes heavy bag\n",
-      "\n",
-      "FRIDAY 2/25\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minute meditation\n",
-      "\n",
-      "EVENING\n",
-      "clean and jerk lifts—3 reps/8 sets. 262 lbs.\n",
-      "5 sets metabolic conditioning:\n",
-      "10 mile run\n",
-      "12 kettlebell swings\n",
-      "12 pull-ups\n",
-      "30 minutes flexibility\n",
-      "30 minutes sparring\n",
-      "\n",
-      "SATURDAY 2/26)\n",
-      "MORNING\n",
-      "30 minute jog\n",
-      "30 minutes yoga\n",
-      "\n",
-      "EVENING\n",
-      "crunches—50 reps/5 sets\n",
-      "squats—(5 reps/10 sets. 525 lbs.\n",
-      "push-ups—60 reps/sets\n",
-      "30 minutes monkey bars\n",
-      "30 minute pommel horse\n",
-      "30 minutes heavy bag\n",
-      "2 mile swim\n",
-      "\n",
-      "In an effort to inspire the all- important Dark Knight to take time out of his busy schedule and actually consume a reasonable amount of sustenance, I have taken the liberty of composing a menu for today's scheduled natal to its my hope that these elegantly prepared courses will not share the fate of their predecessors -mated cold and untouched on a computer console.\n",
-      "-A\n",
-      "\n",
-      "W A Y N E M A N O R\n",
-      "\n",
-      "Tuesday's Menu\n",
-      "\n",
-      "Breakfast\n",
-      "six poached eggs laid over artichoke bottoms with a sage pesto sauce\n",
-      "thinly sliced baked ham\n",
-      "mixed organic fresh fruit bowl\n",
-      "freshly squeezed orange juice\n",
-      "organic, grass-fed milk\n",
-      "4 grams branched-chain amino acid\n",
-      "2 grams fish oil\n",
-      "\n",
-      "Lunch\n",
-      "local salmon with a ginger glaze\n",
-      "organic asparagus with lemon garlic dusting\n",
-      "Asian yam soup with diced onions\n",
-      "2 grams fish oil\n",
-      "\n",
-      "Dinner\n",
-      "grass-fed local sirloin steak\n",
-      "bed of organic spinach and piquillo peppers\n",
-      "oven-baked golden herb potato\n",
-      "2 grams fish oil\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "For the dinner menu, you should buy the following items:\n",
-      "\n",
-      "1. Grass-fed local sirloin steak\n",
-      "2. Organic spinach\n",
-      "3. Piquillo peppers\n",
-      "4. Potatoes (for oven-baked golden herb potato)\n",
-      "5. Fish oil (2 grams)\n",
-      "\n",
-      "Ensure the steak is grass-fed and the spinach and peppers are organic for the best quality meal.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in messages['messages']:\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b96c8456-4093-4cd6-bc5a-f611967ab709",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

unit2/langgraph/mail_sorting.ipynb

@@ -1 +0,0 @@
-{"cells":[{"cell_type":"markdown","metadata":{},"source":["# Alfred the Mail Sorting Butler: A LangGraph Example\n","\n","In this notebook, **we're going to build a complete email processing workflow using LangGraph**.\n","\n","This notebook is part of the <a href=\"https://www.hf.co/learn/agents-course\">Hugging Face Agents Course</a>, a free course from beginner to expert, where you learn to build Agents.\n","\n","![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n","\n","## What You'll Learn\n","\n","In this notebook, you'll learn how to:\n","1. Set up a LangGraph workflow\n","2. Define state and nodes for email processing\n","3. Create conditional branching in a graph\n","4. Connect an LLM for classification and content generation\n","5. Visualize the workflow graph\n","6. Execute the workflow with example data"]},{"cell_type":"code","execution_count":6,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["\u001b[33m  WARNING: The script isympy is installed in '/Library/Frameworks/Python.framework/Versions/3.11/bin' which is not on PATH.\n","  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n","\u001b[0m\u001b[33m  WARNING: The script huggingface-cli is installed in '/Library/Frameworks/Python.framework/Versions/3.11/bin' which is not on PATH.\n","  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n","\u001b[0m\u001b[33m  WARNING: The scripts torchfrtrace and torchrun are installed in '/Library/Frameworks/Python.framework/Versions/3.11/bin' which is not on PATH.\n","  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n","\u001b[0m\u001b[33m  WARNING: The script transformers-cli is installed in '/Library/Frameworks/Python.framework/Versions/3.11/bin' which is not on PATH.\n","  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\u001b[33m\n","\u001b[0m\n","\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.0.1\u001b[0m\n","\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3 -m pip install --upgrade pip\u001b[0m\n","Note: you may need to restart the kernel to use updated packages.\n"]}],"source":["# Install the required packages\n","%pip install -q langgraph langchain_openai langchain_huggingface"]},{"cell_type":"markdown","metadata":{},"source":["## Setting Up Our Environment\n","\n","First, let's import all the necessary libraries. LangGraph provides the graph structure, while LangChain offers convenient interfaces for working with LLMs."]},{"cell_type":"code","execution_count":41,"metadata":{},"outputs":[],"source":["import os\n","from typing import TypedDict, List, Dict, Any, Optional\n","from langgraph.graph import StateGraph, END\n","from langchain_openai import ChatOpenAI\n","from langchain_core.messages import HumanMessage, AIMessage\n","\n","# Set your OpenAI API key here\n","os.environ[\"OPENAI_API_KEY\"] = \"sk-xxxxx\"  # Replace with your actual API key\n","\n","# Initialize our LLM\n","model = ChatOpenAI(model=\"gpt-4o\", temperature=0)"]},{"cell_type":"markdown","metadata":{},"source":["## Step 1: Define Our State\n","\n","In LangGraph, **State** is the central concept. It represents all the information that flows through our workflow.\n","\n","For Alfred's email processing system, we need to track:\n","- The email being processed\n","- Whether it's spam or not\n","- The draft response (for legitimate emails)\n","- Conversation history with the LLM"]},{"cell_type":"code","execution_count":42,"metadata":{},"outputs":[],"source":["class EmailState(TypedDict):\n","    email: Dict[str, Any]           \n","    is_spam: Optional[bool]         \n","    spam_reason: Optional[str]      \n","    email_category: Optional[str]   \n","    draft_response: Optional[str]   \n","    messages: List[Dict[str, Any]]  "]},{"cell_type":"markdown","metadata":{},"source":["## Step 2: Define Our Nodes"]},{"cell_type":"code","execution_count":43,"metadata":{},"outputs":[{"data":{"text/plain":["<langgraph.graph.state.StateGraph at 0x123332fd0>"]},"execution_count":43,"metadata":{},"output_type":"execute_result"}],"source":["import os\n","from typing import TypedDict, List, Dict, Any, Optional\n","from langgraph.graph import StateGraph, START, END\n","from langchain_openai import ChatOpenAI\n","from langchain_core.messages import HumanMessage, AIMessage\n","from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint\n","\n","\n","\n","# Initialize LLM\n","model = ChatOpenAI( model=\"gpt-4o\",temperature=0)\n","\n","class EmailState(TypedDict):\n","    email: Dict[str, Any]\n","    is_spam: Optional[bool]\n","    draft_response: Optional[str]\n","    messages: List[Dict[str, Any]]\n","\n","# Define nodes\n","def read_email(state: EmailState):\n","    email = state[\"email\"]\n","    print(f\"Alfred is processing an email from {email['sender']} with subject: {email['subject']}\")\n","    return {}\n","\n","def classify_email(state: EmailState):\n","    email = state[\"email\"]\n","    \n","    prompt = f\"\"\"\n","As Alfred the butler of Mr wayne and it's SECRET identity Batman, analyze this email and determine if it is spam or legitimate and should be brought to Mr wayne's attention.\n","\n","Email:\n","From: {email['sender']}\n","Subject: {email['subject']}\n","Body: {email['body']}\n","\n","First, determine if this email is spam.\n","answer with SPAM or HAM if it's legitimate. Only reurn the answer\n","Answer :\n","    \"\"\"\n","    messages = [HumanMessage(content=prompt)]\n","    response = model.invoke(messages)\n","    \n","    response_text = response.content.lower()\n","    print(response_text)\n","    is_spam = \"spam\" in response_text and \"ham\" not in response_text\n","    \n","    if not is_spam:\n","        new_messages = state.get(\"messages\", []) + [\n","            {\"role\": \"user\", \"content\": prompt},\n","            {\"role\": \"assistant\", \"content\": response.content}\n","        ]\n","    else :\n","        new_messages = state.get(\"messages\", [])\n","    \n","    return {\n","        \"is_spam\": is_spam,\n","        \"messages\": new_messages\n","    }\n","\n","def handle_spam(state: EmailState):\n","    print(f\"Alfred has marked the email as spam.\")\n","    print(\"The email has been moved to the spam folder.\")\n","    return {}\n","\n","def drafting_response(state: EmailState):\n","    email = state[\"email\"]\n","    \n","    prompt = f\"\"\"\n","As Alfred the butler, draft a polite preliminary response to this email.\n","\n","Email:\n","From: {email['sender']}\n","Subject: {email['subject']}\n","Body: {email['body']}\n","\n","Draft a brief, professional response that Mr. Wayne can review and personalize before sending.\n","    \"\"\"\n","    \n","    messages = [HumanMessage(content=prompt)]\n","    response = model.invoke(messages)\n","    \n","    new_messages = state.get(\"messages\", []) + [\n","        {\"role\": \"user\", \"content\": prompt},\n","        {\"role\": \"assistant\", \"content\": response.content}\n","    ]\n","    \n","    return {\n","        \"draft_response\": response.content,\n","        \"messages\": new_messages\n","    }\n","\n","def notify_mr_wayne(state: EmailState):\n","    email = state[\"email\"]\n","    \n","    print(\"\\n\" + \"=\"*50)\n","    print(f\"Sir, you've received an email from {email['sender']}.\")\n","    print(f\"Subject: {email['subject']}\")\n","    print(\"\\nI've prepared a draft response for your review:\")\n","    print(\"-\"*50)\n","    print(state[\"draft_response\"])\n","    print(\"=\"*50 + \"\\n\")\n","    \n","    return {}\n","\n","# Define routing logic\n","def route_email(state: EmailState) -> str:\n","    if state[\"is_spam\"]:\n","        return \"spam\"\n","    else:\n","        return \"legitimate\"\n","\n","# Create the graph\n","email_graph = StateGraph(EmailState)\n","\n","# Add nodes\n","email_graph.add_node(\"read_email\", read_email) # the read_email node executes the read_mail function\n","email_graph.add_node(\"classify_email\", classify_email) # the classify_email node will execute the classify_email function\n","email_graph.add_node(\"handle_spam\", handle_spam) #same logic \n","email_graph.add_node(\"drafting_response\", drafting_response) #same logic\n","email_graph.add_node(\"notify_mr_wayne\", notify_mr_wayne) # same logic\n"]},{"cell_type":"markdown","metadata":{},"source":["## Step 3: Define Our Routing Logic"]},{"cell_type":"code","execution_count":44,"metadata":{},"outputs":[{"data":{"text/plain":["<langgraph.graph.state.StateGraph at 0x123332fd0>"]},"execution_count":44,"metadata":{},"output_type":"execute_result"}],"source":["# Add edges\n","email_graph.add_edge(START, \"read_email\") # After starting we go to the \"read_email\" node\n","\n","email_graph.add_edge(\"read_email\", \"classify_email\") # after_reading we classify\n","\n","# Add conditional edges\n","email_graph.add_conditional_edges(\n","    \"classify_email\", # after classify, we run the \"route_email\" function\"\n","    route_email,\n","    {\n","        \"spam\": \"handle_spam\", # if it return \"Spam\", we go the \"handle_span\" node\n","        \"legitimate\": \"drafting_response\" # and if it's legitimate, we go to the \"drafting response\" node\n","    }\n",")\n","\n","# Add final edges\n","email_graph.add_edge(\"handle_spam\", END) # after handling spam we always end\n","email_graph.add_edge(\"drafting_response\", \"notify_mr_wayne\")\n","email_graph.add_edge(\"notify_mr_wayne\", END) # after notifyinf Me wayne, we can end  too\n"]},{"cell_type":"markdown","metadata":{},"source":["## Step 4: Create the StateGraph and Define Edges"]},{"cell_type":"code","execution_count":45,"metadata":{},"outputs":[],"source":["# Compile the graph\n","compiled_graph = email_graph.compile()"]},{"cell_type":"code","execution_count":46,"metadata":{},"outputs":[{"data":{"image/png":"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","text/plain":["<IPython.core.display.Image object>"]},"metadata":{},"output_type":"display_data"}],"source":["\n","from IPython.display import Image, display\n","\n","display(Image(compiled_graph.get_graph().draw_mermaid_png()))"]},{"cell_type":"code","execution_count":47,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","Processing legitimate email...\n","Alfred is processing an email from Joker with subject: Found you Batman ! \n","ham\n","\n","==================================================\n","Sir, you've received an email from Joker.\n","Subject: Found you Batman ! \n","\n","I've prepared a draft response for your review:\n","--------------------------------------------------\n","Subject: Re: Found you Batman!\n","\n","Dear Mr. Joker,\n","\n","Thank you for reaching out. Your message has been received and noted. Mr. Wayne is currently unavailable, but rest assured, your concerns will be addressed in due course.\n","\n","Kind regards,\n","\n","Alfred Pennyworth  \n","Personal Assistant to Bruce Wayne\n","==================================================\n","\n","\n","Processing spam email...\n","Alfred is processing an email from Crypto bro with subject: The best investment of 2025\n","spam\n","Alfred has marked the email as spam.\n","The email has been moved to the spam folder.\n"]}],"source":[" # Example emails for testing\n","legitimate_email = {\n","    \"sender\": \"Joker\",\n","    \"subject\": \"Found you Batman ! \",\n","    \"body\": \"Mr. Wayne,I found your secret identity ! I know you're batman ! Ther's no denying it, I have proof of that and I'm coming to find you soon. I'll get my revenge. JOKER\"\n","}\n","\n","spam_email = {\n","    \"sender\": \"Crypto bro\",\n","    \"subject\": \"The best investment of 2025\",\n","    \"body\": \"Mr Wayne, I just launched an ALT coin and want you to buy some !\"\n","}\n","# Process legitimate email\n","print(\"\\nProcessing legitimate email...\")\n","legitimate_result = compiled_graph.invoke({\n","    \"email\": legitimate_email,\n","    \"is_spam\": None,\n","    \"draft_response\": None,\n","    \"messages\": []\n","})\n","\n","# Process spam email\n","print(\"\\nProcessing spam email...\")\n","spam_result = compiled_graph.invoke({\n","    \"email\": spam_email,\n","    \"is_spam\": None,\n","    \"draft_response\": None,\n","    \"messages\": []\n","}) "]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.6"}},"nbformat":4,"nbformat_minor":2}

unit2/llama-index/agents.ipynb

@@ -1,334 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
-   "source": [
-    "# Agents in LlamaIndex\n",
-    "\n",
-    "This notebook is part of the [Hugging Face Agents Course](https://www.hf.co/learn/agents-course), a free Course from beginner to expert, where you learn to build Agents.\n",
-    "\n",
-    "![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n",
-    "\n",
-    "## Let's install the dependencies\n",
-    "\n",
-    "We will install the dependencies for this unit."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 43,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install llama-index datasets llama-index-callbacks-arize-phoenix llama-index-vector-stores-chroma llama-index-llms-huggingface-api -U -q"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, let's log in to Hugging Face to use serverless Inference APIs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from huggingface_hub import login\n",
-    "\n",
-    "login()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
-   "source": [
-    "## Initialising agents\n",
-    "\n",
-    "Let's start by initialising an agent. We will use the basic `AgentWorkflow` class to create an agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
-    "from llama_index.core.agent.workflow import AgentWorkflow, ToolCallResult, AgentStream\n",
-    "\n",
-    "\n",
-    "def add(a: int, b: int) -> int:\n",
-    "    \"\"\"Add two numbers\"\"\"\n",
-    "    return a + b\n",
-    "\n",
-    "\n",
-    "def subtract(a: int, b: int) -> int:\n",
-    "    \"\"\"Subtract two numbers\"\"\"\n",
-    "    return a - b\n",
-    "\n",
-    "\n",
-    "def multiply(a: int, b: int) -> int:\n",
-    "    \"\"\"Multiply two numbers\"\"\"\n",
-    "    return a * b\n",
-    "\n",
-    "\n",
-    "def divide(a: int, b: int) -> int:\n",
-    "    \"\"\"Divide two numbers\"\"\"\n",
-    "    return a / b\n",
-    "\n",
-    "\n",
-    "llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
-    "\n",
-    "agent = AgentWorkflow.from_tools_or_functions(\n",
-    "    tools_or_functions=[subtract, multiply, divide, add],\n",
-    "    llm=llm,\n",
-    "    system_prompt=\"You are a math agent that can add, subtract, multiply, and divide numbers using provided tools.\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then, we can run the agent and get the response and reasoning behind the tool calls."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "handler = agent.run(\"What is (2 + 2) * 2?\")\n",
-    "async for ev in handler.stream_events():\n",
-    "    if isinstance(ev, ToolCallResult):\n",
-    "        print(\"\")\n",
-    "        print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n",
-    "    elif isinstance(ev, AgentStream):  # showing the thought process\n",
-    "        print(ev.delta, end=\"\", flush=True)\n",
-    "\n",
-    "resp = await handler\n",
-    "resp"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In a similar fashion, we can pass state and context to the agent.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AgentOutput(response=ChatMessage(role=<MessageRole.ASSISTANT: 'assistant'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='Your name is Bob.')]), tool_calls=[], raw={'id': 'chatcmpl-B5sDHfGpSwsVyzvMVH8EWokYwdIKT', 'choices': [{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': 'stop', 'index': 0, 'logprobs': None}], 'created': 1740739735, 'model': 'gpt-4o-2024-08-06', 'object': 'chat.completion.chunk', 'service_tier': 'default', 'system_fingerprint': 'fp_eb9dce56a8', 'usage': None}, current_agent_name='Agent')"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.core.workflow import Context\n",
-    "\n",
-    "ctx = Context(agent)\n",
-    "\n",
-    "response = await agent.run(\"My name is Bob.\", ctx=ctx)\n",
-    "response = await agent.run(\"What was my name again?\", ctx=ctx)\n",
-    "response"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating RAG Agents with QueryEngineTools\n",
-    "\n",
-    "Let's now re-use the `QueryEngine` we defined in the [previous unit on tools](/tools.ipynb) and convert it into a `QueryEngineTool`. We will pass it to the `AgentWorkflow` class to create a RAG agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import chromadb\n",
-    "\n",
-    "from llama_index.core import VectorStoreIndex\n",
-    "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
-    "from llama_index.embeddings.huggingface_api import HuggingFaceInferenceAPIEmbedding\n",
-    "from llama_index.core.tools import QueryEngineTool\n",
-    "from llama_index.vector_stores.chroma import ChromaVectorStore\n",
-    "\n",
-    "# Create a vector store\n",
-    "db = chromadb.PersistentClient(path=\"./alfred_chroma_db\")\n",
-    "chroma_collection = db.get_or_create_collection(\"alfred\")\n",
-    "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
-    "\n",
-    "# Create a query engine\n",
-    "embed_model = HuggingFaceInferenceAPIEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n",
-    "llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
-    "index = VectorStoreIndex.from_vector_store(\n",
-    "    vector_store=vector_store, embed_model=embed_model\n",
-    ")\n",
-    "query_engine = index.as_query_engine(llm=llm)\n",
-    "query_engine_tool = QueryEngineTool.from_defaults(\n",
-    "    query_engine=query_engine,\n",
-    "    name=\"personas\",\n",
-    "    description=\"descriptions for various types of personas\",\n",
-    "    return_direct=False,\n",
-    ")\n",
-    "\n",
-    "# Create a RAG agent\n",
-    "query_engine_agent = AgentWorkflow.from_tools_or_functions(\n",
-    "    tools_or_functions=[query_engine_tool],\n",
-    "    llm=llm,\n",
-    "    system_prompt=\"You are a helpful assistant that has access to a database containing persona descriptions. \",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, we can once more get the response and reasoning behind the tool calls."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "handler = query_engine_agent.run(\n",
-    "    \"Search the database for 'science fiction' and return some persona descriptions.\"\n",
-    ")\n",
-    "async for ev in handler.stream_events():\n",
-    "    if isinstance(ev, ToolCallResult):\n",
-    "        print(\"\")\n",
-    "        print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n",
-    "    elif isinstance(ev, AgentStream):  # showing the thought process\n",
-    "        print(ev.delta, end=\"\", flush=True)\n",
-    "\n",
-    "resp = await handler\n",
-    "resp"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating multi-agent systems\n",
-    "\n",
-    "We can also create multi-agent systems by passing multiple agents to the `AgentWorkflow` class."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.core.agent.workflow import (\n",
-    "    AgentWorkflow,\n",
-    "    ReActAgent,\n",
-    ")\n",
-    "\n",
-    "\n",
-    "# Define some tools\n",
-    "def add(a: int, b: int) -> int:\n",
-    "    \"\"\"Add two numbers.\"\"\"\n",
-    "    return a + b\n",
-    "\n",
-    "\n",
-    "def subtract(a: int, b: int) -> int:\n",
-    "    \"\"\"Subtract two numbers.\"\"\"\n",
-    "    return a - b\n",
-    "\n",
-    "\n",
-    "# Create agent configs\n",
-    "# NOTE: we can use FunctionAgent or ReActAgent here.\n",
-    "# FunctionAgent works for LLMs with a function calling API.\n",
-    "# ReActAgent works for any LLM.\n",
-    "calculator_agent = ReActAgent(\n",
-    "    name=\"calculator\",\n",
-    "    description=\"Performs basic arithmetic operations\",\n",
-    "    system_prompt=\"You are a calculator assistant. Use your tools for any math operation.\",\n",
-    "    tools=[add, subtract],\n",
-    "    llm=llm,\n",
-    ")\n",
-    "\n",
-    "query_agent = ReActAgent(\n",
-    "    name=\"info_lookup\",\n",
-    "    description=\"Looks up information about XYZ\",\n",
-    "    system_prompt=\"Use your tool to query a RAG system to answer information about XYZ\",\n",
-    "    tools=[query_engine_tool],\n",
-    "    llm=llm,\n",
-    ")\n",
-    "\n",
-    "# Create and run the workflow\n",
-    "agent = AgentWorkflow(agents=[calculator_agent, query_agent], root_agent=\"calculator\")\n",
-    "\n",
-    "# Run the system\n",
-    "handler = agent.run(user_msg=\"Can you add 5 and 3?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "async for ev in handler.stream_events():\n",
-    "    if isinstance(ev, ToolCallResult):\n",
-    "        print(\"\")\n",
-    "        print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n",
-    "    elif isinstance(ev, AgentStream):  # showing the thought process\n",
-    "        print(ev.delta, end=\"\", flush=True)\n",
-    "\n",
-    "resp = await handler\n",
-    "resp"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": ".venv",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.11"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

unit2/llama-index/tools.ipynb

@@ -1,229 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Tools in LlamaIndex\n",
-    "\n",
-    "\n",
-    "This notebook is part of the [Hugging Face Agents Course](https://www.hf.co/learn/agents-course), a free Course from beginner to expert, where you learn to build Agents.\n",
-    "\n",
-    "![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n",
-    "\n",
-    "## Let's install the dependencies\n",
-    "\n",
-    "We will install the dependencies for this unit."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install llama-index datasets llama-index-callbacks-arize-phoenix llama-index-vector-stores-chroma llama-index-llms-huggingface-api -U -q"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, let's log in to Hugging Face to use serverless Inference APIs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from huggingface_hub import login\n",
-    "\n",
-    "login()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating a FunctionTool\n",
-    "\n",
-    "Let's create a basic `FunctionTool` and call it."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.core.tools import FunctionTool\n",
-    "\n",
-    "\n",
-    "def get_weather(location: str) -> str:\n",
-    "    \"\"\"Useful for getting the weather for a given location.\"\"\"\n",
-    "    print(f\"Getting weather for {location}\")\n",
-    "    return f\"The weather in {location} is sunny\"\n",
-    "\n",
-    "\n",
-    "tool = FunctionTool.from_defaults(\n",
-    "    get_weather,\n",
-    "    name=\"my_weather_tool\",\n",
-    "    description=\"Useful for getting the weather for a given location.\",\n",
-    ")\n",
-    "tool.call(\"New York\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating a QueryEngineTool\n",
-    "\n",
-    "Let's now re-use the `QueryEngine` we defined in the [previous unit on tools](/tools.ipynb) and convert it into a `QueryEngineTool`. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ToolOutput(content=' As an anthropologist, I am intrigued by the potential implications of AI on the future of work and society. My research focuses on the cultural and social aspects of technological advancements, and I believe it is essential to understand how AI will shape the lives of Cypriot people and the broader society. I am particularly interested in exploring how AI will impact traditional industries, such as agriculture and tourism, and how it will affect the skills and knowledge required for future employment. As someone who has spent extensive time in Cyprus, I am well-positioned to investigate the unique cultural and historical context of the island and how it will influence the adoption and impact of AI. My research will not only provide valuable insights into the future of work but also contribute to the development of policies and strategies that support the well-being of Cypriot citizens and the broader society. \\n\\nAs an environmental historian or urban planner, I am more focused on the ecological and sustainability aspects of AI, particularly in the context of urban planning and conservation. I believe that AI has the potential to significantly impact the built environment and the natural world, and I am eager to explore how it can be used to create more sustainable and resilient cities. My research will focus on the intersection of AI, urban planning, and environmental conservation, and I', tool_name='some useful name', raw_input={'input': 'Responds about research on the impact of AI on the future of work and society?'}, raw_output=Response(response=' As an anthropologist, I am intrigued by the potential implications of AI on the future of work and society. My research focuses on the cultural and social aspects of technological advancements, and I believe it is essential to understand how AI will shape the lives of Cypriot people and the broader society. I am particularly interested in exploring how AI will impact traditional industries, such as agriculture and tourism, and how it will affect the skills and knowledge required for future employment. As someone who has spent extensive time in Cyprus, I am well-positioned to investigate the unique cultural and historical context of the island and how it will influence the adoption and impact of AI. My research will not only provide valuable insights into the future of work but also contribute to the development of policies and strategies that support the well-being of Cypriot citizens and the broader society. \\n\\nAs an environmental historian or urban planner, I am more focused on the ecological and sustainability aspects of AI, particularly in the context of urban planning and conservation. I believe that AI has the potential to significantly impact the built environment and the natural world, and I am eager to explore how it can be used to create more sustainable and resilient cities. My research will focus on the intersection of AI, urban planning, and environmental conservation, and I', source_nodes=[NodeWithScore(node=TextNode(id_='f0ea24d2-4ed3-4575-a41f-740a3fa8b521', embedding=None, metadata={'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1.txt', 'file_name': 'persona_1.txt', 'file_type': 'text/plain', 'file_size': 266, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}, excluded_embed_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], excluded_llm_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], relationships={<NodeRelationship.SOURCE: '1'>: RelatedNodeInfo(node_id='d5db5bf4-daac-41e5-b5aa-271e8305da25', node_type='4', metadata={'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1.txt', 'file_name': 'persona_1.txt', 'file_type': 'text/plain', 'file_size': 266, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}, hash='e6c87149a97bf9e5dbdf33922a4e5023c6b72550ca0b63472bd5d25103b28e99')}, metadata_template='{key}: {value}', metadata_separator='\\n', text='An anthropologist or a cultural expert interested in the intricacies of Cypriot culture, history, and society, particularly someone who has spent considerable time researching and living in Cyprus to gain a deep understanding of its people, customs, and way of life.', mimetype='text/plain', start_char_idx=0, end_char_idx=266, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}'), score=0.3761845613489774), NodeWithScore(node=TextNode(id_='cebcd676-3180-4cda-be99-d535babc1b96', embedding=None, metadata={'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1004.txt', 'file_name': 'persona_1004.txt', 'file_type': 'text/plain', 'file_size': 160, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}, excluded_embed_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], excluded_llm_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'], relationships={<NodeRelationship.SOURCE: '1'>: RelatedNodeInfo(node_id='1347651d-7fc8-42d4-865c-a0151a534a1b', node_type='4', metadata={'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1004.txt', 'file_name': 'persona_1004.txt', 'file_type': 'text/plain', 'file_size': 160, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}, hash='19628b0ae4a0f0ebd63b75e13df7d9183f42e8bb84358fdc2c9049c016c4b67d')}, metadata_template='{key}: {value}', metadata_separator='\\n', text='An environmental historian or urban planner focused on ecological conservation and sustainability, likely working in local government or a related organization.', mimetype='text/plain', start_char_idx=0, end_char_idx=160, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}'), score=0.3733060058493167)], metadata={'f0ea24d2-4ed3-4575-a41f-740a3fa8b521': {'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1.txt', 'file_name': 'persona_1.txt', 'file_type': 'text/plain', 'file_size': 266, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}, 'cebcd676-3180-4cda-be99-d535babc1b96': {'file_path': '/Users/davidberenstein/Documents/programming/huggingface/agents-course/notebooks/unit2/llama-index/data/persona_1004.txt', 'file_name': 'persona_1004.txt', 'file_type': 'text/plain', 'file_size': 160, 'creation_date': '2025-02-27', 'last_modified_date': '2025-02-27'}}), is_error=False)"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import chromadb\n",
-    "\n",
-    "from llama_index.core import VectorStoreIndex\n",
-    "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
-    "from llama_index.embeddings.huggingface_api import HuggingFaceInferenceAPIEmbedding\n",
-    "from llama_index.core.tools import QueryEngineTool\n",
-    "from llama_index.vector_stores.chroma import ChromaVectorStore\n",
-    "\n",
-    "db = chromadb.PersistentClient(path=\"./alfred_chroma_db\")\n",
-    "chroma_collection = db.get_or_create_collection(\"alfred\")\n",
-    "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
-    "embed_model = HuggingFaceInferenceAPIEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n",
-    "llm = HuggingFaceInferenceAPI(model_name=\"meta-llama/Llama-3.2-3B-Instruct\")\n",
-    "index = VectorStoreIndex.from_vector_store(\n",
-    "    vector_store=vector_store, embed_model=embed_model\n",
-    ")\n",
-    "query_engine = index.as_query_engine(llm=llm)\n",
-    "tool = QueryEngineTool.from_defaults(\n",
-    "    query_engine=query_engine,\n",
-    "    name=\"some useful name\",\n",
-    "    description=\"some useful description\",\n",
-    ")\n",
-    "await tool.acall(\n",
-    "    \"Responds about research on the impact of AI on the future of work and society?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Creating Toolspecs\n",
-    "\n",
-    "Let's create a `ToolSpec` from the `GmailToolSpec` from the LlamaHub and convert it to a list of tools. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[<llama_index.core.tools.function_tool.FunctionTool at 0x15d638410>,\n",
-       " <llama_index.core.tools.function_tool.FunctionTool at 0x15d64a190>,\n",
-       " <llama_index.core.tools.function_tool.FunctionTool at 0x159cf8050>,\n",
-       " <llama_index.core.tools.function_tool.FunctionTool at 0x15d65b150>,\n",
-       " <llama_index.core.tools.function_tool.FunctionTool at 0x15cef6990>,\n",
-       " <llama_index.core.tools.function_tool.FunctionTool at 0x15d642b10>]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.tools.google import GmailToolSpec\n",
-    "\n",
-    "tool_spec = GmailToolSpec()\n",
-    "tool_spec_list = tool_spec.to_tool_list()\n",
-    "tool_spec_list"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "To get a more detailed view of the tools, we can take a look at the `metadata` of each tool."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[('load_data',\n",
-       "  \"load_data() -> List[llama_index.core.schema.Document]\\nLoad emails from the user's account.\"),\n",
-       " ('search_messages',\n",
-       "  \"search_messages(query: str, max_results: Optional[int] = None)\\nSearches email messages given a query string and the maximum number\\n        of results requested by the user\\n           Returns: List of relevant message objects up to the maximum number of results.\\n\\n        Args:\\n            query[str]: The user's query\\n            max_results (Optional[int]): The maximum number of search results\\n            to return.\\n        \"),\n",
-       " ('create_draft',\n",
-       "  \"create_draft(to: Optional[List[str]] = None, subject: Optional[str] = None, message: Optional[str] = None) -> str\\nCreate and insert a draft email.\\n           Print the returned draft's message and id.\\n           Returns: Draft object, including draft id and message meta data.\\n\\n        Args:\\n            to (Optional[str]): The email addresses to send the message to\\n            subject (Optional[str]): The subject for the event\\n            message (Optional[str]): The message for the event\\n        \"),\n",
-       " ('update_draft',\n",
-       "  \"update_draft(to: Optional[List[str]] = None, subject: Optional[str] = None, message: Optional[str] = None, draft_id: str = None) -> str\\nUpdate a draft email.\\n           Print the returned draft's message and id.\\n           This function is required to be passed a draft_id that is obtained when creating messages\\n           Returns: Draft object, including draft id and message meta data.\\n\\n        Args:\\n            to (Optional[str]): The email addresses to send the message to\\n            subject (Optional[str]): The subject for the event\\n            message (Optional[str]): The message for the event\\n            draft_id (str): the id of the draft to be updated\\n        \"),\n",
-       " ('get_draft',\n",
-       "  \"get_draft(draft_id: str = None) -> str\\nGet a draft email.\\n           Print the returned draft's message and id.\\n           Returns: Draft object, including draft id and message meta data.\\n\\n        Args:\\n            draft_id (str): the id of the draft to be updated\\n        \"),\n",
-       " ('send_draft',\n",
-       "  \"send_draft(draft_id: str = None) -> str\\nSends a draft email.\\n           Print the returned draft's message and id.\\n           Returns: Draft object, including draft id and message meta data.\\n\\n        Args:\\n            draft_id (str): the id of the draft to be updated\\n        \")]"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "[(tool.metadata.name, tool.metadata.description) for tool in tool_spec_list]"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": ".venv",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.11"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

unit2/llama-index/workflows.ipynb

@@ -1,395 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Workflows in LlamaIndex\n",
-    "\n",
-    "\n",
-    "This notebook is part of the [Hugging Face Agents Course](https://www.hf.co/learn/agents-course), a free Course from beginner to expert, where you learn to build Agents.\n",
-    "\n",
-    "![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n",
-    "\n",
-    "## Let's install the dependencies\n",
-    "\n",
-    "We will install the dependencies for this unit."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install llama-index datasets llama-index-callbacks-arize-phoenix llama-index-vector-stores-chroma llama-index-utils-workflow llama-index-llms-huggingface-api pyvis -U -q"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, let's log in to Hugging Face to use serverless Inference APIs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from huggingface_hub import login\n",
-    "\n",
-    "login()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Basic Workflow Creation\n",
-    "\n",
-    "We can start by creating a simple workflow. We use the `StartEvent` and `StopEvent` classes to define the start and stop of the workflow."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Hello, world!'"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.core.workflow import StartEvent, StopEvent, Workflow, step\n",
-    "\n",
-    "\n",
-    "class MyWorkflow(Workflow):\n",
-    "    @step\n",
-    "    async def my_step(self, ev: StartEvent) -> StopEvent:\n",
-    "        # do something here\n",
-    "        return StopEvent(result=\"Hello, world!\")\n",
-    "\n",
-    "\n",
-    "w = MyWorkflow(timeout=10, verbose=False)\n",
-    "result = await w.run()\n",
-    "result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Connecting Multiple Steps\n",
-    "\n",
-    "We can also create multi-step workflows. Here we pass the event information between steps. Note that we can use type hinting to specify the event type and the flow of the workflow."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Finished processing: Step 1 complete'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.core.workflow import Event\n",
-    "\n",
-    "\n",
-    "class ProcessingEvent(Event):\n",
-    "    intermediate_result: str\n",
-    "\n",
-    "\n",
-    "class MultiStepWorkflow(Workflow):\n",
-    "    @step\n",
-    "    async def step_one(self, ev: StartEvent) -> ProcessingEvent:\n",
-    "        # Process initial data\n",
-    "        return ProcessingEvent(intermediate_result=\"Step 1 complete\")\n",
-    "\n",
-    "    @step\n",
-    "    async def step_two(self, ev: ProcessingEvent) -> StopEvent:\n",
-    "        # Use the intermediate result\n",
-    "        final_result = f\"Finished processing: {ev.intermediate_result}\"\n",
-    "        return StopEvent(result=final_result)\n",
-    "\n",
-    "\n",
-    "w = MultiStepWorkflow(timeout=10, verbose=False)\n",
-    "result = await w.run()\n",
-    "result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Loops and Branches\n",
-    "\n",
-    "We can also use type hinting to create branches and loops. Note that we can use the `|` operator to specify that the step can return multiple types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Good thing happened\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Finished processing: First step complete.'"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.core.workflow import Event\n",
-    "import random\n",
-    "\n",
-    "\n",
-    "class ProcessingEvent(Event):\n",
-    "    intermediate_result: str\n",
-    "\n",
-    "\n",
-    "class LoopEvent(Event):\n",
-    "    loop_output: str\n",
-    "\n",
-    "\n",
-    "class MultiStepWorkflow(Workflow):\n",
-    "    @step\n",
-    "    async def step_one(self, ev: StartEvent) -> ProcessingEvent | LoopEvent:\n",
-    "        if random.randint(0, 1) == 0:\n",
-    "            print(\"Bad thing happened\")\n",
-    "            return LoopEvent(loop_output=\"Back to step one.\")\n",
-    "        else:\n",
-    "            print(\"Good thing happened\")\n",
-    "            return ProcessingEvent(intermediate_result=\"First step complete.\")\n",
-    "\n",
-    "    @step\n",
-    "    async def step_two(self, ev: ProcessingEvent | LoopEvent) -> StopEvent:\n",
-    "        # Use the intermediate result\n",
-    "        final_result = f\"Finished processing: {ev.intermediate_result}\"\n",
-    "        return StopEvent(result=final_result)\n",
-    "\n",
-    "\n",
-    "w = MultiStepWorkflow(verbose=False)\n",
-    "result = await w.run()\n",
-    "result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Drawing Workflows\n",
-    "\n",
-    "We can also draw workflows using the `draw_all_possible_flows` function.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'NoneType'>\n",
-      "<class '__main__.ProcessingEvent'>\n",
-      "<class '__main__.LoopEvent'>\n",
-      "<class 'llama_index.core.workflow.events.StopEvent'>\n",
-      "workflow_all_flows.html\n"
-     ]
-    }
-   ],
-   "source": [
-    "from llama_index.utils.workflow import draw_all_possible_flows\n",
-    "\n",
-    "draw_all_possible_flows(w)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "![drawing](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/unit2/llama-index/workflow-draw.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### State Management\n",
-    "\n",
-    "Instead of passing the event information between steps, we can use the `Context` type hint to pass information between steps. \n",
-    "This might be useful for long running workflows, where you want to store information between steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Query: What is the capital of France?\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Finished processing: Step 1 complete'"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.core.workflow import Event, Context\n",
-    "from llama_index.core.agent.workflow import ReActAgent\n",
-    "\n",
-    "\n",
-    "class ProcessingEvent(Event):\n",
-    "    intermediate_result: str\n",
-    "\n",
-    "\n",
-    "class MultiStepWorkflow(Workflow):\n",
-    "    @step\n",
-    "    async def step_one(self, ev: StartEvent, ctx: Context) -> ProcessingEvent:\n",
-    "        # Process initial data\n",
-    "        await ctx.set(\"query\", \"What is the capital of France?\")\n",
-    "        return ProcessingEvent(intermediate_result=\"Step 1 complete\")\n",
-    "\n",
-    "    @step\n",
-    "    async def step_two(self, ev: ProcessingEvent, ctx: Context) -> StopEvent:\n",
-    "        # Use the intermediate result\n",
-    "        query = await ctx.get(\"query\")\n",
-    "        print(f\"Query: {query}\")\n",
-    "        final_result = f\"Finished processing: {ev.intermediate_result}\"\n",
-    "        return StopEvent(result=final_result)\n",
-    "\n",
-    "\n",
-    "w = MultiStepWorkflow(timeout=10, verbose=False)\n",
-    "result = await w.run()\n",
-    "result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Multi-Agent Workflows\n",
-    "\n",
-    "We can also create multi-agent workflows. Here we define two agents, one that multiplies two integers and one that adds two integers."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AgentOutput(response=ChatMessage(role=<MessageRole.ASSISTANT: 'assistant'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='I have handed off the request to an agent who can help you with adding 5 and 3. Please wait for their response.')]), tool_calls=[ToolCallResult(tool_name='handoff', tool_kwargs={'to_agent': 'addition_agent', 'reason': 'Add 5 and 3'}, tool_id='call_F97vcIcsvZjfAAOBzzIifW3y', tool_output=ToolOutput(content='Agent addition_agent is now handling the request due to the following reason: Add 5 and 3.\\nPlease continue with the current request.', tool_name='handoff', raw_input={'args': (), 'kwargs': {'to_agent': 'addition_agent', 'reason': 'Add 5 and 3'}}, raw_output='Agent addition_agent is now handling the request due to the following reason: Add 5 and 3.\\nPlease continue with the current request.', is_error=False), return_direct=True), ToolCallResult(tool_name='handoff', tool_kwargs={'to_agent': 'addition_agent', 'reason': 'Add 5 and 3'}, tool_id='call_jf49ktFRs09xYdOsnApAk2zz', tool_output=ToolOutput(content='Agent addition_agent is now handling the request due to the following reason: Add 5 and 3.\\nPlease continue with the current request.', tool_name='handoff', raw_input={'args': (), 'kwargs': {'to_agent': 'addition_agent', 'reason': 'Add 5 and 3'}}, raw_output='Agent addition_agent is now handling the request due to the following reason: Add 5 and 3.\\nPlease continue with the current request.', is_error=False), return_direct=True)], raw={'id': 'chatcmpl-B6Cy54VQkvlG3VOrmdzCzgwcJmVOc', 'choices': [{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': 'stop', 'index': 0, 'logprobs': None}], 'created': 1740819517, 'model': 'gpt-3.5-turbo-0125', 'object': 'chat.completion.chunk', 'service_tier': 'default', 'system_fingerprint': None, 'usage': None}, current_agent_name='addition_agent')"
-      ]
-     },
-     "execution_count": 33,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
-    "\n",
-    "# Define some tools\n",
-    "def add(a: int, b: int) -> int:\n",
-    "    \"\"\"Add two numbers.\"\"\"\n",
-    "    return a + b\n",
-    "\n",
-    "def multiply(a: int, b: int) -> int:\n",
-    "    \"\"\"Multiply two numbers.\"\"\"\n",
-    "    return a * b\n",
-    "\n",
-    "llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
-    "\n",
-    "# we can pass functions directly without FunctionTool -- the fn/docstring are parsed for the name/description\n",
-    "multiply_agent = ReActAgent(\n",
-    "    name=\"multiply_agent\",\n",
-    "    description=\"Is able to multiply two integers\",\n",
-    "    system_prompt=\"A helpful assistant that can use a tool to multiply numbers.\",\n",
-    "    tools=[multiply], \n",
-    "    llm=llm,\n",
-    ")\n",
-    "\n",
-    "addition_agent = ReActAgent(\n",
-    "    name=\"add_agent\",\n",
-    "    description=\"Is able to add two integers\",\n",
-    "    system_prompt=\"A helpful assistant that can use a tool to add numbers.\",\n",
-    "    tools=[add], \n",
-    "    llm=llm,\n",
-    ")\n",
-    "\n",
-    "# Create the workflow\n",
-    "workflow = AgentWorkflow(\n",
-    "    agents=[multiply_agent, addition_agent],\n",
-    "    root_agent=\"multiply_agent\"\n",
-    ")\n",
-    "\n",
-    "# Run the system\n",
-    "response = await workflow.run(user_msg=\"Can you add 5 and 3?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": ".venv",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.11"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}