How to Build the Ultimate AI Automation with Multi-Agent Collaboration
Editor's Note: The following post is authored by Assaf Elovic, Head of R&D at Wix. In this blog, he walks through how to build an autonomous research assistant using LangGraph with a team of specialized agents. It has only been a year since the initial release of GPT Researcher, but methods for building, testing, and deploying AI agents have already evolved significantly. That’s just the nature an
How Dataherald Makes Natural Language to SQL Easy
Editor's Note: we're excited to feature this guest post from the Dataherald team. Text-to-SQL is a HUGE use case, and Dataherald is the open-source leader in the space. This is a great look behind the curtains to see what makes it tick. When ChatGPT came out in late 2022, everyone went over to see if AI could do their day to day work. Marketers wanted their blog posts written, college students the
LangGraph: Multi-Agent Workflows
Links Python ExamplesJS ExamplesYouTubeLast week we highlighted LangGraph - a new package (available in both Python and JS) to better enable creation of LLM workflows containing cycles, which are a critical component of most agent runtimes. As a part of the launch, we highlighted two simple runtimes: one that is the equivalent of the AgentExecutor in langchain, and a second that was a version of t
LangGraph
TL;DR: LangGraph is module built on top of LangChain to better enable creation of cyclical graphs, often needed for agent runtimes. Python RepoPython YouTube PlaylistJS RepoIntroductionOne of the things we highlighted in our LangChain v0.1 announcement was the introduction of a new library: LangGraph. LangGraph is built on top of LangChain and completely interoperable with the LangChain ecosystem.
Evaluating RAG pipelines with Ragas + LangSmith
Editor's Note: This post was written in collaboration with the Ragas team. One of the things we think and talk about a lot at LangChain is how the industry will evolve to identify new monitoring and evaluation metrics that evolve beyond traditional ML ops metrics. Ragas is an exciting new framework that helps developers evaluate QA pipelines in new ways. This post shows how LangSmith and Ragas can
Multi-modal RAG on slide decks
Key LinksLangChain public benchmark evaluation notebooksLangChain template for multi-modal RAG on presentationsMotivationRetrieval augmented generation (RAG) is one of the most important concepts in LLM app development. Documents of many types can be passed into the context window of an LLM, enabling interactive chat or Q+A assistants. While many of the RAG apps to date have focused on text, a gre
Query Construction
Key Links Text-to-metadata: Updated self-query docs and templateText-to-SQL+semantic: Cookbook and templateThere's great interest in seamlessly connecting natural language with diverse types of data (structured, unstructured, and semi-structured). But, this emerging "LUI" (language user interface) has specific challenges/considerations for each data type: Structured Data: Predominantly housed with
Multi-Vector Retriever for RAG on tables, text, and images
Applying RAG to Diverse Data TypesYet, RAG on documents that contain semi-structured data (structured tables with unstructured text) and multiple modalities (images) has remained a challenge. With the emergence of several multimodal models, it is now worth considering unified strategies to enable RAG across modalities and semi-structured data. Multi-Vector RetrieverBack in August, we released the
Query Transformations
Although this is not a new phenomenon (query expansion has been used in search for years) what is new is the ability to use LLMs to do it. Below are a few variations of papers and retrieval methods that take advantage of this. They are all using an LLM to generate a new (or multiple new) queries, and the main difference is the prompt they use to do that generation. Rewrite-Retrieve-ReadThis paper
Using a Knowledge Graph to implement a DevOps RAG application
Using a Knowledge Graph to implement a DevOps RAG application Editor's Note: This post was written in collaboration with the Neo4J team. RAG applications are all the rage at the moment. Everyone is building their company documentation chatbot or similar. Mostly, they all have in common that their source of knowledge is unstructured text, which gets chunked and embedded in one way or another. Howev
Summarizing and Querying Data from Excel Spreadsheets Using eparse and a Large Language Model
Summarizing and Querying Data from Excel Spreadsheets Using eparse and a Large Language Model Editor's Note: This post was written by Chris Pappalardo, a Senior Director at Alvarez & Marsal, a leading global professional services firm. The standard processes for building with LLM work well for documents that contain mostly text, but do not work as well for documents that contain tabular data (like
Label Studio x LangChain: From Foundation Models to Fine-Tuned Applications Using Label Studio
Label Studio x LangChain: From Foundation Models to Fine-Tuned Applications Using Label Studio Editor's Note: This post was written by Jimmy Whitaker, Data Scientist in Residence at HumanSignal. Label Studio is an open-source data labeling platform that provides LangChain with flexibility when it comes to labeling data for fine-tuning large language models (LLMs). It also enables the preparation o
Rebuff: Detecting Prompt Injection Attacks
[Editor's Note]: we're excited to highlight a guest blog by Willem Pienaar. As more and more LangChains make their way into production, we're getting an increased amount of questions about the security and privacy of these systems. We did a webinar on this topic a few weeks ago, and the main action item that emerged was the best thing at the moment is more awareness of this topic is needed. That i
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Building (and Breaking) WebLangChain
Sharing LangSmith Benchmarks
LangChain x Context: Building Better Chat Products With User Analytics