Thanks to visit codestin.com
Credit goes to github.com

Skip to content

[E-4] 13-LangChain-Expression-Language / 02-InspectRunnables.ipynb #252

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jan 9, 2025
Merged

[E-4] 13-LangChain-Expression-Language / 02-InspectRunnables.ipynb #252

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
957bcf1
[E-4] 13-LangChain-Expression-Language / 02-InspectRunnables.ipynb
ranian963 Jan 8, 2025
ea6855c
Update 02-InspectRunnables.ipynb
ranian963 Jan 9, 2025
2f76bb7
Update 02-InspectRunnables.ipynb
ranian963 Jan 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
280 changes: 280 additions & 0 deletions 13-LangChain-Expression-Language/02-InspectRunnables.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,280 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "intro-inspect-runnables",
"metadata": {},
"source": [
"# Inspect Runnables\n",
"\n",
"- Author: [ranian963](https://github.com/ranian963)\n",
"- Peer Review: []()\n",
"- This is a part of [LangChain Open Tutorial](https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial)\n",
"\n",
"[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/) [![Open in GitHub](https://img.shields.io/badge/Open%20in%20GitHub-181717?style=flat-square&logo=github&logoColor=white)](https://github.com/)\n",
"\n",
"## Overview\n",
"In this tutorial, we introduce how to **inspect** and visualize various components (including the graph structure) of a `Runnable` chain. Understanding the underlying graph structure can help diagnose and optimize complex chain flows.\n",
"\n",
"### Table of Contents\n",
"- [Overview](#overview)\n",
"- [Environment Setup](#environment-setup)\n",
"- [Introduction to Inspecting Runnables](#introduction-to-inspecting-runnables)\n",
" - [Graph Inspection](#graph-inspection)\n",
" - [Graph Output](#graph-output)\n",
" - [Prompt Retrieval](#prompt-retrieval)\n",
"\n",
" ### References\n",
"- [LangChain: Runnables](https://python.langchain.com/api_reference/core/runnables.html)\n",
"- [LangChain Open Tutorial](https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial)\n",
"----\n"
]
},
{
"cell_type": "markdown",
"id": "env-setup",
"metadata": {},
"source": [
"## Environment Setup\n",
"\n",
"Set up the environment. You may refer to [Environment Setup](https://wikidocs.net/257836) for more details.\n",
"\n",
"**[Note]**\n",
"- `langchain-opentutorial` is a package that provides a set of easy-to-use environment setup, useful functions and utilities for tutorials. \n",
"- You can checkout the [`langchain-opentutorial`](https://github.com/LangChain-OpenTutorial/langchain-opentutorial-pypi) for more details."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "install-libraries",
"metadata": {},
"outputs": [],
"source": [
"%%capture --no-stderr\n",
"%pip install langchain-opentutorial"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "install-req",
"metadata": {},
"outputs": [],
"source": [
"from langchain_opentutorial import package\n",
"\n",
"package.install(\n",
" [\n",
" \"langsmith\",\n",
" \"langchain\",\n",
" \"langchain_core\",\n",
" \"langchain_community\",\n",
" \"langchain_openai\",\n",
" \"faiss-cpu\",\n",
" \"grandalf\",\n",
" ],\n",
" verbose=False,\n",
" upgrade=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "set-env",
"metadata": {},
"outputs": [],
"source": [
"# Set environment variables\n",
"from langchain_opentutorial import set_env\n",
"\n",
"set_env(\n",
" {\n",
" \"OPENAI_API_KEY\": \"\",\n",
" \"LANGCHAIN_API_KEY\": \"\",\n",
" \"LANGCHAIN_TRACING_V2\": \"true\",\n",
" \"LANGCHAIN_ENDPOINT\": \"https://api.smith.langchain.com\",\n",
" \"LANGCHAIN_PROJECT\": \"02-InspectRunnables\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "dotenv-option",
"metadata": {},
"source": [
"You can alternatively set `OPENAI_API_KEY` in `.env` file and load it. \n",
"\n",
"[Note] This is not necessary if you've already set `OPENAI_API_KEY` in previous steps."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "load-dotenv",
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv(override=True)"
]
},
{
"cell_type": "markdown",
"id": "introduction-to-inspecting-runnables",
"metadata": {},
"source": [
"## Introduction to Inspecting Runnables\n",
"\n",
"LangChain `Runnable` objects can be composed into pipelines, commonly referred to as **chains** or **flows**. After setting up a `runnable`, you might want to **inspect its structure** to see what's happening under the hood.\n",
"\n",
"By inspecting these, you can:\n",
"- Understand the sequence of transformations and data flows.\n",
"- Visualize the graph for debugging.\n",
"- Retrieve or modify prompts or sub-chains as needed.\n"
]
},
{
"cell_type": "markdown",
"id": "graph-inspection",
"metadata": {},
"source": [
"### Graph Inspection\n",
"\n",
"We'll create a runnable chain that includes a retriever from FAISS, a prompt template, and a ChatOpenAI model. Then we’ll **inspect the chain’s graph** to understand how data flows between these components.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "chain-setup",
"metadata": {},
"outputs": [],
"source": [
"from langchain_core.prompts import ChatPromptTemplate\n",
"from langchain_community.vectorstores import FAISS\n",
"from langchain_core.output_parsers import StrOutputParser\n",
"from langchain_core.runnables import RunnablePassthrough\n",
"from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
"\n",
"# Create a FAISS vector store from simple text data\n",
"vectorstore = FAISS.from_texts(\n",
" [\"Teddy is an AI engineer who loves programming!\"], embedding=OpenAIEmbeddings()\n",
")\n",
"\n",
"# Create a retriever based on the vector store\n",
"retriever = vectorstore.as_retriever()\n",
"\n",
"template = \"\"\"Answer the question based only on the following context:\\n{context}\\n\\nQuestion: {question}\"\"\"\n",
"# Create a prompt template\n",
"prompt = ChatPromptTemplate.from_template(template)\n",
"\n",
"# Initialize ChatOpenAI model\n",
"model = ChatOpenAI(model=\"gpt-4o-mini\")\n",
"\n",
"# Construct the chain: (dictionary format) => prompt => model => output parser\n",
"chain = (\n",
" {\n",
" \"context\": retriever,\n",
" \"question\": RunnablePassthrough(),\n",
" } # Search context and question\n",
" | prompt\n",
" | model\n",
" | StrOutputParser()\n",
")"
]
},
{
"cell_type": "markdown",
"id": "graph-output",
"metadata": {},
"source": [
"### Graph Output\n",
"We can **inspect** the chain’s internal graph of nodes (steps) and edges (data flows)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "node-inspection",
"metadata": {},
"outputs": [],
"source": [
"# Get nodes from the chain's graph\n",
"chain.get_graph().nodes"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "edge-inspection",
"metadata": {},
"outputs": [],
"source": [
"# Get edges from the chain's graph\n",
"chain.get_graph().edges"
]
},
{
"cell_type": "markdown",
"id": "graph-print-ascii",
"metadata": {},
"source": [
"We can also print the graph in an ASCII-based diagram to visualize the chain flow."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "print-ascii",
"metadata": {},
"outputs": [],
"source": [
"chain.get_graph().print_ascii()"
]
},
{
"cell_type": "markdown",
"id": "prompt-retrieval",
"metadata": {},
"source": [
"### Prompt Retrieval\n",
"Finally, we can retrieve the **actual prompts** used in this chain. This is helpful to see exactly what LLM instructions are being sent.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "get-prompts",
"metadata": {},
"outputs": [],
"source": [
"chain.get_prompts()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "python3",
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading