Small OSS Models with LangGraph.js

LangChain · Intermediate ·🧠 Large Language Models ·2y ago

Skills: LLM Engineering90%LLM Foundations70%

Key Takeaways

Building reliable LLM-powered apps with LangGraph.js and small OSS models

Original Description

One of the benefits to LangGraph is that it can help you improve the reliability of LLM-powered apps. By using it to design your apps to more closely match the actual logic you'd use to solve a problem, you can reduce the range of decisions an LLM has to make. This is particularly striking when working with smaller, open-source models. Jacob Lee demonstrates an example of this using a small, 7B parameter Mistral fine tune with LangGraph.js to build a customer support workflow. Let us know what you think! Code 💻: https://github.com/langchain-ai/langgraphjs/blob/main/examples/chatbots/customer_support_mistral.ipynb LangGraph.js 🦜🕸️: https://github.com/langchain-ai/langgraphjs

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from LangChain · LangChain · 0 of 60

← Previous Next →

Chat With Your Documents Using LangChain + JavaScript

Chat With Your Documents Using LangChain + JavaScript

LangChain SQL Webinar

LangChain SQL Webinar

LangChain "OpenAI functions" Webinar

LangChain "OpenAI functions" Webinar

LangSmith Launch

LangSmith Launch

LangChain x Pinecone: Supercharging Llama-2 with RAG

LangChain x Pinecone: Supercharging Llama-2 with RAG

LangChain Expression Language

LangChain Expression Language

Building LLM applications with LangChain with Lance

Building LLM applications with LangChain with Lance

Benchmarking Question/Answering Over CSV Data

Benchmarking Question/Answering Over CSV Data

LangChain "RAG Evaluation" Webinar

LangChain "RAG Evaluation" Webinar

Fine-tuning in Your Voice Webinar

Fine-tuning in Your Voice Webinar

Tabular Data Retrieval

Tabular Data Retrieval

Building an LLM Application with Audio by AssemblyAI

Building an LLM Application with Audio by AssemblyAI

Superagent Deepdive Webinar

Superagent Deepdive Webinar

Lessons from Deploying LLMs with LangSmith

Lessons from Deploying LLMs with LangSmith

Shortwave Assistant Deepdive Webinar

Shortwave Assistant Deepdive Webinar

Cognitive Architectures for Language Agents

Cognitive Architectures for Language Agents

Effectively Building with LLMs in the Browser with Jacob

Effectively Building with LLMs in the Browser with Jacob

Data Privacy for LLMs

Data Privacy for LLMs

"Theory of Mind" Webinar with Plastic Labs

"Theory of Mind" Webinar with Plastic Labs

LangChain Templates

LangChain Templates

Using Natural Language to Query Postgres with Jacob

Using Natural Language to Query Postgres with Jacob

Building a Research Assistant from Scratch

Building a Research Assistant from Scratch

Benchmarking RAG over LangChain Docs

Benchmarking RAG over LangChain Docs

Skeleton-of-Thought: Building a New Template from Scratch

Skeleton-of-Thought: Building a New Template from Scratch

Benchmarking Methods for Semi-Structured RAG

Benchmarking Methods for Semi-Structured RAG

LangSmith Highlights: Getting Started

LangSmith Highlights: Getting Started

LangSmith Highlights: Debugging

LangSmith Highlights: Debugging

LangSmith Highlights: Datasets

LangSmith Highlights: Datasets

LangSmith Highlights: Evaluation

LangSmith Highlights: Evaluation

LangSmith Highlights: Human Annotation

LangSmith Highlights: Human Annotation

LangSmith Highlights: Monitoring

LangSmith Highlights: Monitoring

LangSmith Highlights: Hub

LangSmith Highlights: Hub

SQL Research Assistant

SQL Research Assistant

Getting Started with Multi-Modal LLMs

Getting Started with Multi-Modal LLMs

Build a Full Stack RAG App With TypeScript

Build a Full Stack RAG App With TypeScript

Auto-Prompt Builder (with Hosted LangServe)

Auto-Prompt Builder (with Hosted LangServe)

LangChain v0.1.0 Launch: Introduction

LangChain v0.1.0 Launch: Introduction

LangChain v0.1.0 Launch: Observability

LangChain v0.1.0 Launch: Observability

LangChain v0.1.0 Launch: Integrations

LangChain v0.1.0 Launch: Integrations

LangChain v0.1.0 Launch: Composability

LangChain v0.1.0 Launch: Composability

LangChain v0.1.0 Launch: Streaming

LangChain v0.1.0 Launch: Streaming

LangChain v0.1.0 Launch: Output Parsing

LangChain v0.1.0 Launch: Output Parsing

LangChain v0.1.0 Launch: Retrieval

LangChain v0.1.0 Launch: Retrieval

LangChain v0.1.0 Launch: Agents

LangChain v0.1.0 Launch: Agents

Build and Deploy a RAG app with Pinecone Serverless

Build and Deploy a RAG app with Pinecone Serverless

Hosted LangServe + LangChain Templates

Hosted LangServe + LangChain Templates

LangGraph: Intro

LangGraph: Intro

LangGraph: Agent Executor

LangGraph: Agent Executor

LangGraph: Chat Agent Executor

LangGraph: Chat Agent Executor

LangGraph: Human-in-the-Loop

LangGraph: Human-in-the-Loop

LangGraph: Dynamically Returning a Tool Output Directly

LangGraph: Dynamically Returning a Tool Output Directly

LangGraph: Respond in a Specific Format

LangGraph: Respond in a Specific Format

LangGraph: Managing Agent Steps

LangGraph: Managing Agent Steps

LangGraph: Force-Calling a Tool

LangGraph: Force-Calling a Tool

LangGraph: Multi-Agent Workflows

LangGraph: Multi-Agent Workflows

Streaming Events: Introducing a new `stream_events` method

Streaming Events: Introducing a new `stream_events` method

Building a web RAG chatbot: using LangChain, Exa (prev. Metaphor), LangSmith, and Hosted Langserve

Building a web RAG chatbot: using LangChain, Exa (prev. Metaphor), LangSmith, and Hosted Langserve

Open Source RAG with Nomic's New Embedding Model (and ChromaDB and Ollama)

Open Source RAG with Nomic's New Embedding Model (and ChromaDB and Ollama)

LangGraph: Persistence

LangGraph: Persistence

More on: LLM Engineering

View skill →

Build an LLM and RAG-based Chat Application using AlloyDB and LangChain

FULLY LOCAL Mistral AI PDF Processing [Hands-on Tutorial]

FULLY LOCAL Mistral AI PDF Processing [Hands-on Tutorial]

Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation

Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation

Ultimate Guide: Deploy Google ADK Agents to Vertex AI & Cloud Run (Step-by-Step Tutorial)

Ultimate Guide: Deploy Google ADK Agents to Vertex AI & Cloud Run (Step-by-Step Tutorial)

Shane | LLM Implementation

How to Make an Asteroids Game Bot (LIVE)

How to Make an Asteroids Game Bot (LIVE)

Using Claude Code + Nano Banana Pro To Create a Dataset of Engineering Drawings

Using Claude Code + Nano Banana Pro To Create a Dataset of Engineering Drawings

Automata Learning Lab

Related Reads

How a simple AI search architecture I made defined industry standard

Learn how a simple AI search architecture became an industry standard and apply similar design principles to your own projects

Colibri: Running a 744B AI Model on Your Laptop

Run massive AI models like GLM-5.2 on low-resource devices using Colibri, a C inference engine that streams model experts from disk

What Actually Happens When You Fine-Tune a Language Model, Explained Simply

Learn how fine-tuning a language model works in simple terms

What Actually Happens When You Fine-Tune a Language Model, Explained Simply

Learn how fine-tuning a language model works in simple terms, without jargon or complex math

Medium · Machine Learning

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems

Dave Ebbelaar (LLM Eng)