LangChain @LangChainAI Twitter profile | Pikagi

Pikagi

LangChain

@LangChainAI

137,506

Followers

24

Following

990

Media

7,721

Statuses

⚡ Build context-aware, reasoning applications ⚡

https://t.co/Sh5ftHbX6A

Joined November 2022

Don't wanna be here? Send us removal request.

Pinned Tweet

@LangChainAI

LangChain

3 months

✨ Today, we’re thrilled to announce ✨ - The general availability of LangSmith (no more waitlist!) - Our Series A fundraise led by @sequoia - Our beautiful new homepage and brand We've worked hard over the past few months to add requested features and ensure LangSmith can…

Tweet media one

75

170

1K

Last Seen Profiles

@OBOhockeyUK

@SVELEZ4EDU

@boycatapp

@TDFCdiabetes

@METhompson72

@steveshealth23

@Tradiio

@pebblely_ai

@LoLLoROD

@superbatson

@STAHawksWGOLF

@Redinkyboi

@ChayanLoun

@AssoFinale

@svscarpino

@bitrefill

@nhrecruitment

@TheFl0orIsLaVa

@NotAlone_Game

@TyNewton16

@CyprianKello

@NairaHotCam

@wired_jp

@HannahRTaylor__

@Mustafaoksz28

@MSaltWFTV

@Only_dylanbaker

@DiglidiDude

@cyngn

@yewyunz

@trish_kelshaw

@YoungCease4

@JosuLobos295775

@rebecca3overstr

@OKaschula

@AshanDeSilva04

@LangChainAI

LangChain

6 months

🦜🤖OpenGPTs OpenAI just announced "GPTs" - chatbots augmented with custom tools and custom instructions that anyone can create We're excited to announce OpenGPTs - a open source GitHub repo enabling similar functionality. This will allow: 🛠️Easier tool definition 🧠Usage of…

Tweet media one

64

413

2K

@LangChainAI

LangChain

3 months

RAG From Scratch: Video series focused on understanding the RAG landscape RAG is central for LLM application development, connecting LLMs to external data sources. But, the pace of innovation and new approaches makes it challenging to keep up. We're launching a new video…

Tweet media one

16

230

1K

@LangChainAI

LangChain

14 days

Reliable, fully local RAG agents with Llama3 With the release of Llama3, there's high interest in agents that run reliably & locally (e.g., on your laptop). Here, we show to how build reliable local agents using LangGraph and Llama3-8b from scratch. As a example, we combine…

Tweet media one

16

229

1K

@LangChainAI

LangChain

6 months

🏃Step-back prompting A new prompting technique from Google Deepmind, can be used to improve RAG results 🦜🔗Now in LangChain! 💬"STEP-BACK PROMPTING is motivated by the observation that many tasks contain a lot of details, and are hard for LLMs to retrieve relevant facts to…

Tweet media one

23

240

1K

@LangChainAI

LangChain

1 year

⭐️LangChains as a ChatPGT Plugin⭐️ 🫢ChatGPT 😮ChatGPT with normal plugins 🤯ChatGPT with LangChain plugins Releasing `langchain-aiplugins`: a repository showing how to deploy LangChains as an AIPlugin, letting ChatGPT call other chains and agents

Tweet card media

GitHub - langchain-ai/langchain-aiplugin

Contribute to langchain-ai/langchain-aiplugin development by creating an account on GitHub.

27

170

1K

@LangChainAI

LangChain

10 months

🦜🛠️ Introducing LangSmith 🦜🔗 A unified platform to help developers debug, test, evaluate, and monitor their LLM applications. Integrates seamlessly with LangChain, but doesn't require it.

Tweet media one

22

195

1K

@LangChainAI

LangChain

6 months

🦜🏗️LangChain Templates Today we're excited to announce the release of ✨LangChain Templates✨ - a collection of easily deployable reference architectures for a wide variety of tasks This is a new way to 🖌️create, 🤝share, ⏬download, and 💱customize chains and agents ❓How…

Tweet media one

33

205

948

@LangChainAI

LangChain

4 months

🦜🚀LangChain v0.1.0 After a year of development, we've released LangChain v0.1.0 Read the full blog here: After talking with the users and developers, we released this stable version and focused the library on a few core areas: 👀Observability:…

Tweet media one

29

211

931

@LangChainAI

LangChain

1 year

⭐️BabyAGI + Tools⭐️ By default, BabyAGI by @yoheinakajima just "executes" things with an LLM response (eg, makes things up) By changing the execution chain to be an agent with tools, the execution step can now lookup real info, take actions, etc Docs:

Tweet media one

34

162

927

@LangChainAI

LangChain

5 months

🦜Build your own RAG with Mistral-7B and LangChain Using local models can enable chatbots over your data while ensuring your data never leaves your computer Great for enterprise or privacy centric use cases This blog post by Madhav Thaker is one of the best resources we've…

Tweet media one

Tweet media two

7

161

920

@LangChainAI

LangChain

5 months

🦜🤖Open Assistants API OpenGPTs got an update! We've now exposed an API similar to the OpenAI Assistants API... and added in some improvements (like streaming support🎏) 🧠Importantly (now more than ever) this works with multiple models: OpenAI, Azure, Anthropic, Bedrock…

Tweet media one

33

160

871

@LangChainAI

LangChain

1 month

Claude-ception: Teaching Claude3 to prompt engineer itself Claude3 Opus is excellent at prompt engineering. @alexalbert__ recently laid out a nice workflow: write an prompt, run it on test cases, grade responses, let Claude3 Opus use grades to improve prompt, & repeat.…

Tweet media one

23

155

860

@LangChainAI

LangChain

8 months

🎡 Introducing LangChain Hub 🦜🔗 A place to publish, discover, and try out prompts We’re particularly excited about a centralized hub’s promise to enable: -Encoding of expertise -Discoverability of prompts for a variety of models -Inspectability -Cross-team collaboration 🧵

21

181

825

@LangChainAI

LangChain

6 months

🦜🤖OpenGPTs Some big updates to OpenGPTs - an open-source, fully configurable GPTs experience You can now: 📁Upload files to a retrieval tool (with full configurability over the ingestion, vectorstore, and retrieval used) 🌐Share public bots that you've created 🛠️Use more…

Tweet media one

22

152

815

@LangChainAI

LangChain

4 months

⭐️Open-Source RAG Chatbot Builder One of the most popular use cases for GPTs is uploading it some data and creating a chatbot over that data💬 Did you know there's an open-source solution that can do the same thing built entirely in typescript? ⭐️ @dialoqbase by @n4ze3m ⭐️ Uses…

Tweet media one

6

159

705

@LangChainAI

LangChain

2 months

📝 AutoPrompt Auto Prompt is a prompt optimization framework designed to enhance and perfect your prompts for real-world use cases. It iteratively builds a dataset of challenging edge cases and optimizes the prompt accordingly GitHub:

Tweet media one

17

176

801

@LangChainAI

LangChain

6 months

⭐️Multi-modal RAG w/ GPT-4V ⭐️ "A picture is worth 1000 words," but images are typically invisible in RAG apps. Multi-modal LLMs like GPT-4V unlock RAG apps that use images. Using the new @OpenAI GPT-4V API, we'll be releasing templates and cookbooks this week to highlight…

Tweet media one

15

153

779

@LangChainAI

LangChain

5 months

🚨New Paper Alert -🦙⚒️LLMCompiler If you enjoyed @karpathy 's video on an "LLM OS", you're going to want to check out this paper (complete with a full open source repo!) This system compiles an effective plan for executing multiple tasks in parallel, letting LLM agents work…

Tweet media one

18

162

757

@LangChainAI

LangChain

1 year

You can now import BabyAGI, AutoGPT, and the generative agents memory from `langchain.experimental`! We started this module to include more experimental code as we think about how best to include in the core library What should we include next?

Tweet media one

Tweet media two

Tweet media three

28

114

759

@LangChainAI

LangChain

1 year

Introducing the 📧Gmail Agent Toolkit📧 📨Enable agents to search Gmail, retrieve, draft, and even send messages! Docs:

Tweet media one

36

139

726

@LangChainAI

LangChain

1 year

Excited to announce support for running LangChain JS in: 🖨️Browsers ☁️Cloudflare Workers 🌲Next.js/Vercel 🦖Deno 🍜Supabase Edge Functions (in addition to existing Node.js support) Read more here

Tweet card media

Announcing LangChainJS Support for Multiple JS Environments

TLDR: We're announcing support for running LangChain.js in browsers, Cloudflare Workers, Vercel/Next.js, Deno, Supabase Edge Functions, alongside existing support for Node.js ESM and CJS. See...

blog.langchain.dev

27

107

727

@LangChainAI

LangChain

2 months

⛵️Advanced RAG series: Indexing Indexing is a huge part or RAG. Lot's of different stuff to optimize: 1. Chunk Optimization 2. Multi-representation indexing 3. Specialized Embeddings 4. Hierarchical Indexing Great article by @divyanshu_van diving into all these topics! Blog:…

Tweet media one

9

158

724

@LangChainAI

LangChain

1 month

RAG From Scratch: Query Structuring Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the 11th video in our series and focuses on query structuring. 🔧 Problem: We interact w/ databases using domain-specific…

Tweet media one

11

130

707

@LangChainAI

LangChain

6 months

LangChain 🤝🏾 Microsoft Today, we’re thrilled to announce our collaboration with @microsoft @azure . Our joint customers will enjoy deeper product integrations that live up to our commitment to AI with the enterprise assurances the Azure ecosystem provides. more on the blog and…

22

103

702

@LangChainAI

LangChain

5 months

🐟Tuna: a no-code tool for quickly generating LLM fine-tuning datasets from scratch 🧑🏽‍🎓built by Student Hacker, @itsandrewgao

Tweet card media

Introducing Tuna - A Tool for Rapidly Generating Synthetic Fine-Tuning Datasets

Editor's Note: This post was written by Andrew Kean Gao through LangChain's Student Hacker in Residence Program. Brief Overview Tuna is a no-code tool for quickly generating LLM fine-tuning datasets...

blog.langchain.dev

6

127

695

@LangChainAI

LangChain

11 months

🚨🤖New Agent Release🤖🚨 We can @OpenAI 's new function parameter to create a new type of agent (`openai-functions`) now available in Python and JS Links to documentation a thread on what went into it below 👇

Tweet media one

27

135

686

@LangChainAI

LangChain

7 months

⭐️ Multi-Vector Retriever for RAG on tables, text, and images ⭐️ Seamless question-answering across diverse data types (images, text, tables) is one of the holy grails of RAG. We’re releasing three new cookbooks that showcase the multi-vector retriever to tackle this challenge.…

Tweet media one

10

149

683

@LangChainAI

LangChain

5 months

🦜LangChain 🤝Gemini♊️ Gemini API access is out! Access it through LangChain with our first standalone integration package: `pip install langchain-google-genai` We're also launching an integration guide showing how to: 🎏Stream results 🖼️Use it's multimodal capabilities…

Tweet media one

Tweet media two

17

164

681

@LangChainAI

LangChain

5 months

💬AnythingLLM: a private ChatGPT to chat with anything An efficient🚤, customizable🧩, and open-source enterprise-ready document chatbot solution. An awesome example of a fullstack (JS) LLM application (s/o @MintplexLabs ) Code:

9

127

585

@LangChainAI

LangChain

1 year

🤖LangChain x AutoGPT🤖 First BabyAGI, then CAMEL, then generative agents, now finally AutoGPT... Implementing the core AutoGPT prompt + agent executor in LangChain primitives (to allow for swapping between models, vectorstores, tools, etc) Notebook:

Tweet media one

Tweet media two

Tweet media three

18

124

665

@LangChainAI

LangChain

2 months

RAG From Scratch: Routing Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the 10th video in our series and focuses on query routing. 🔧 Problem: We often have multiple possible datastores (e.g., different vectorDBs,…

Tweet media one

10

151

665

@LangChainAI

LangChain

6 months

⭐️ Applying OpenAI's RAG strategies ⭐️ At demo day, OpenAI reported a series of useful tricks for improving RAG app performance. In this short guide, we: 1/ Describe each of the strategies mentioned 2/ Link to docs so you can test each for yourself 3/ Show related ideas that…

Tweet media one

6

120

656

@LangChainAI

LangChain

30 days

RAG From Scratch: Feedback + self-reflection Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the final part in our series, focusing on self-reflection + feedback to improve RAG systems. 🔧Problem: RAG systems…

Tweet media one

9

136

655

@LangChainAI

LangChain

6 months

✒️Query Rewriting for Retrieval-Augmented Large Language Models This paper by Microsoft uses the concept of query rewriting to get better retrieval results - which are crucial for any RAG app! 🦜🔗Now in LangChain! 💬"Because the original query can not be always optimal to…

Tweet media one

14

128

640

@LangChainAI

LangChain

7 months

⭐️ Semi-structured RAG ⭐️ Many documents contain a mixture of text and tables, which present a challenge for RAG. Back in August, we released the multi-vector retriever, which offers a great way to tackle this problem. It creates and embeds a reference (such as a summary) to…

Tweet media one

13

118

645

@LangChainAI

LangChain

6 months

🦜🖊️ Research Assistant Template One of the most exciting templates we've added so far: a template to do longer form research, heavily based on (and in collaboration with) GPT-Researcher. With this template you can easily plug in an arbitrary retriever, allowing you to do…

Tweet media one

2

107

630

@LangChainAI

LangChain

6 months

🎂It's LangChain's First Birthday! today, we're feeling especially thankful for our community. some reflections and highlights from our first year building together. thank you 🙏🏽 💚 The LangChain Team

Tweet card media

LangChain's First Birthday

It’s LangChain’s first birthday! It’s been a really exciting year! We worked with thousands of developers building LLM applications and tooling. We shipped and learned a lot. We grew our team. And...

blog.langchain.dev

32

90

632

@LangChainAI

LangChain

6 months

📃🧨RAG-Fusion A new retrieval technique that builds upon the idea of MultiQueryRetrieval. Originally by @Raudaschl 🦜🔗Now available in LangChain! Algorithm as follows: 💬Based on a user question, multiple sub queries are generated 🌲For each of those sub queries, do some…

Tweet media one

16

129

610

@LangChainAI

LangChain

7 months

So many companies are building Q&A over their company docs/knowledge sources. Chat LangChain makes it really easy to try it for yourself. Especially as a fun weekend hacking project 👩🏽‍💻

Tweet card media

GitHub - langchain-ai/chat-langchain

Contribute to langchain-ai/chat-langchain development by creating an account on GitHub.

9

120

615

@LangChainAI

LangChain

1 year

To say today's release (🦜🔗v0.0.124) is MASSIVE would be an understatement This merges in a massive backlog of PRs including: 📄 8 *brand new* document loaders 🪝 2 new retrieval methods 🪘 1 new embedding class 🛟 2 LLM improvements 🧵

22

64

606

@LangChainAI

LangChain

4 months

🦜🕸️LangGraph ⚡ Building language agents as graphs ⚡ The "one more thing" from our LangChain v0.1.0 announcement is introducing LangGraph to the world 🤖We've been alpha testing this over the past six months as a better way to create LLM agents…

Tweet media one

23

109

602

@LangChainAI

LangChain

1 year

⭐️LangChain x Supabase⭐️ We put together a template repo for how to build a full stack application with LangChain and Supabase Repo: For more details (and more ways to use Supabase within LangChain) see 👇

Tweet card media

LangChain x Supabase

Supabase is holding an AI Hackathon this week. Here at LangChain we are big fans of both Supabase and hackathons, so we thought this would be a perfect time to highlight the multiple ways you can use...

blog.langchain.dev

24

73

599

@LangChainAI

LangChain

1 year

💬Natural Language API Toolkit💬 Last week we showed how to wrap a single API endpoint in a chain The next natural step is to use those chains as tools themselves, resulting in an agent that can communicate with many APIs... all in natural language

Tweet media one

Tweet media two

21

73

596

@LangChainAI

LangChain

2 months

🌲Advanced RAG Series: Retrieval This is the fourth post in a series focused on retrieval by @divyanshu_van It dives into different retrieval algorithms that can be part of your RAG system Check it out:

Tweet media one

7

124

593

@LangChainAI

LangChain

4 months

🦜👑LangChain State of AI 2023 What are people building? Which LLMs are they using? Which vectorstores are they using? How are they testing? 📊We turn to anonymized usage stats from LangSmith to answer these questions with real data. Blog: Recap 🧵

Tweet media one

Tweet media two

Tweet media three

Tweet media four

7

143

596

@LangChainAI

LangChain

1 year

🌵LangChain x GPTCache🌵 Caching can be useful in certain situations to save money on repeated LLM calls GPTCache is a project that caches requests/responses not only the exact prompt, but based on semantic similarity. h/t Frank Liu for adding Docs:

12

82

592

@LangChainAI

LangChain

3 months

RAG From Scratch: Query Translation (RAG-Fusion) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the second in our videos on Query Translation, focused on RAG-Fusion by @Raudaschl . 🔧 Problem: A single user…

Tweet media one

10

121

597

@LangChainAI

LangChain

4 months

⚙️ Agents are the “killer” LLM app, but building and evaluating agents is hard. A huge part of agents is tool use, but there aren't enough open-source tool use benchmarks out there. Today, we are excited to release four new test environments for benchmarking LLMs’ ability to…

Tweet media one

9

107

510

@LangChainAI

LangChain

1 year

Rather large 🦜🔗0.0.131 release! 🆓GPT4all model ( @nomic_ai ) 🦙Llama-cpp model ⏹️Support for @qdrant_engine local db 🌲Zilliz cloud ( @milvusio ) Vectorstore support 📧New OutlookMessage Document Loader 🕸️New Selenium Document Loader 🪟 Support for SQL views in SQLChain 🧵

12

84

590

@LangChainAI

LangChain

2 months

Building long context RAG from scratch with RAPTOR + Claude3 (Video) The rise of long context LLMs + embeddings will change RAG design. Instead of splitting docs + indexing doc chunks, it's feasible to index full docs. But, there is a challenge to flexibly answer lower-level…

Tweet media one

9

117

582

@LangChainAI

LangChain

1 year

🤖Multi-Action Agent Asking an agent to take only one action at a time is so March of 2023 With a small little update to the AgentExecutor, it's now possible to have an agent output MULTIPLE agent actions to take Documentation:

Tweet media one

14

84

567

@LangChainAI

LangChain

16 days

RAG From Scratch on FreeCodeCamp We recently released a playlist of videos that explain RAG fundamentals and highlights over a dozen advanced RAG papers / methods. This tutorial is now free on @freeCodeCamp ! Thanks @beaucarnes and team. Video:

Tweet media one

8

127

571

@LangChainAI

LangChain

7 months

If you're looking for an introduction to LangChain, we really like Ivan Reznikov's "LangChain 101 Course" A fun weekend read if you've been meaning to get started!

Tweet card media

LangChain 101 Course (updated)

LangChain 101 course sessions. All code is on GitHub. LLMs, Chatbots

3

100

563

@LangChainAI

LangChain

5 months

🦜🫅AI Driven Consultant 🚀Great example of orchestrating LLMs to accomplish complex tasks - s/o Gil Fernandes Check out the architecture diagram below 🤯 Lot's of different sub-components GitHub: Blog:

Tweet media one

7

120

560

@LangChainAI

LangChain

5 months

🦜🧮Building An LLM-Powered Analyst This great article deep dives on how to empower LLMs with external tools using OpenAI functions At a **19 minute** minute, it's pretty comprehensive It examines two use cases: extraction to get structured output and routing to use external…

Tweet media one

7

115

559

@LangChainAI

LangChain

6 months

🧑‍🏫 OpenAI Assistants API 🧑‍🏫 Spin up OpenAI assistants and run them as any other LangChain agent! This involves connecting them to LangChain's 100+ tools, OpenAI's code interpreter + retrieval, or easily defining your own! Try it out yourself:

Tweet media one

Tweet media two

18

99

549

@LangChainAI

LangChain

3 months

Self RAG Self-reflection is one of the most interesting ideas in RAG, giving an LLM the ability to self-correct problems in retrieval and / or generation. But, implementing this reliably can be tricky. We've found that graphs are a great way to reliably express logical flows,…

Tweet media one

5

90

555

@LangChainAI

LangChain

7 months

🕸️Introducing WebLangChain🌐 An open source web research assistant a look at how it works under-the-hood and what we learned (especially about RAG) in the process. Blog: Repo:

9

111

545

@LangChainAI

LangChain

4 months

🖼️Multimodal RAG using Langchain Expression Language And GPT4-Vision Great guide from Plaban Nayak on multimodal RAG. We suspect this will become more and more popular - so now's a great time to become an expert! Blog:

Tweet media one

2

119

546

@LangChainAI

LangChain

6 months

🧑‍🏫RAG Overview If you've been looking for a good overview of LangChain + RAG, then you're in luck! @sophiamyang recently released a FANTASTIC presentation on exactly that. Covers both the basics as well as more advanced topics Presentation:

Tweet media one

Tweet media two

Tweet media three

4

104

537

@LangChainAI

LangChain

3 months

🧮Build Knowledge Graph From TextData using LangChain Converting text to knowledge graphs can be helpful for both visualizing the data and allowing for structured querying later on This blog goes through how to use LLMs to extract knowledge triplets

Tweet media one

11

107

544

@LangChainAI

LangChain

1 year

New version 🦜🔗 v0.0.132 with a focus on interacting with APIs (using OpenAPI specs) ⚕️OpenAPIEndpointChain - a chain that wraps a specific endpoint to provide a "Natural Language API" 📒OpenAPI Planner/Executor Agent - good for interacting with large specs 🧵

Tweet media one

Tweet media two

Tweet media three

10

81

532

@LangChainAI

LangChain

4 months

🧱Can LLMs Replace Data Analysts? Getting Answers Using SQL This is an involved *31 minute read* on how to create a custom data science agent by Mariya Mansurova A great read for custom tools and custom agents (almost all production agents are custom)

Tweet media one

7

111

533

@LangChainAI

LangChain

1 month

RAG From Scratch: Multi-Representation Indexing Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the 12th video in our series and focuses on some useful tricks for indexing full documents. 🔧 Problem: Many RAG…

Tweet media one

6

110

534

@LangChainAI

LangChain

7 months

🏓Introduction LangServe The best way to deploy your LangChains 📤Input/Output schema 📃/docs endpoint 🔠invoke/batch/stream endpoints 🎏/stream_log endpoint for streaming intermediate steps 🛠️LangSmith Integration Used to power ChatLangChain and WebLangChain Blog post and 🧵

Tweet media one

Tweet media two

Tweet media three

15

107

533

@LangChainAI

LangChain

4 months

🚀Build a Conversational RAG with Mistral-7B and LangChain This post by Madhav Thaker covers three important topics: 🦋How to get started with RAG 💬How to build a chatbot 🦙How to use open source models Highly recommend reading!

Tweet media one

9

122

528

@LangChainAI

LangChain

6 months

⛪️Adding Structure-Aware Retrieval to GenAI Stack A great post by Joshua Yu takes a look at improving retrieval performance by using the GenAI stack: @Docker + @neo4j + @LangChainAI + @Ollama_ai This stack is (1) fully local, (2) uses advanced retrieval methods that encode…

Tweet media one

11

108

514

@LangChainAI

LangChain

2 months

⚡ Using knowledge graphs to boost RAG accuracy ⚡ Check out this guide to constructing and retrieving information from knowledge graphs in RAG applications with @neo4j and LangChain. ➡ Graph RAG is gaining momentum as a powerful addition to…

Tweet card media

Enhancing RAG-based application accuracy by constructing and leveraging knowledge graphs

A practical guide to constructing and retrieving information from knowledge graphs in RAG applications with Neo4j and LangChain Editor's Note: the following is a guest blog post from Tomaz Bratanic,...

blog.langchain.dev

9

127

516

@LangChainAI

LangChain

1 month

👨‍🎓Advanced RAG Series: Generation and Evaluation In the fifth part of this series, we look at techniques for: 🔊 Generation (CRAG, Self-RAG, RRR) 🧮Evaluation (RAGAs, Langsmith, DeepEval) Another awesome blog by @divyanshu_van

Tweet media one

4

105

508

@LangChainAI

LangChain

6 months

⭐️RAG with multi-modal embeddings ⭐️ The launch of the GPT-4V API has sparked a surge in interest for multi-modal RAG applications. Multi-modal embeddings will become central to these apps, mapping text and images into a common space for retrieval. This week, @trychroma rolled…

Tweet media one

Tweet media two

5

105

510

@LangChainAI

LangChain

1 month

✂️Open Source Extraction Service Have you ever wanted to extract specific structured information from text, HTML, or PDFs? Today we are launching a hosted version of our most recent OSS use-case accelerant: a service for extracting structured data from unstructured sources,…

Tweet media one

6

103

510

@LangChainAI

LangChain

3 months

✒️10 Lessons from Developing an AI Chatbot Using Retrieval-Augmented Generation A great blog from @fiddlerlabs goes through ten lessons learned when building a chatbot using RAG Covers a LOT of content - check it out!

Tweet media one

6

127

509

@LangChainAI

LangChain

5 months

🔎Proposition-Based Retrieval This new paper by @tomchen0 introduces a new retrieval method by changing 🎯what is indexed🎯 in the first place This can easily use our 🌲multi-vector retriever🌲, and we've added a template to get started with it easily! 💡How does it work? 👇…

Tweet media one

6

104

504

@LangChainAI

LangChain

3 months

⚡️Document Search and Retrieval using RAG Great guide by @LightningAI and @aniketmaurya on building a retrieval pipeline Uses open source embedding and reranking models!

Tweet media one

8

99

505

@LangChainAI

LangChain

6 months

📊Graph-based Parent Document Retriever 👩‍👧Parent Document Retriever is a more advanced retrieval technique 🚀We've worked with @neo4j to add a template for this that uses their graph database under the hood! Template: Here's how it works: ---- 👩…

Tweet media one

13

102

497

@LangChainAI

LangChain

3 months

RAG From Scratch: Query Translation (Multi-Query) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. Over the next few days we'll release videos focused on Query Translation, starting with Multi-Query. 🔧 Problem: User queries…

Tweet media one

9

106

500

@LangChainAI

LangChain

3 months

🤖BCG X Releases AgentKit, a Full-Stack Starter Kit for Building Constrained Agents AgentKit is a LangChain-based starter kit to build constrained agents, developed by our partners at BCG X We've often found that in order to productionalize agentic applications, you need to…

Tweet media one

13

119

495

@LangChainAI

LangChain

1 year

It's finally here... ⚡️Javascript/TypeScript support for LangChain⚡️ BIG thank you to everyone in the community who contributed to this, especially @_seanyneutron and @nfcampos ❤️ GitHub: Blog: LOTS to discuss, lets 🧵

Tweet media one

22

78

491

@LangChainAI

LangChain

2 months

💸SalesGPT: Elevating Sales Conversations with LangChain SalesGPT is an awesome open-source repo that creates an AI-driven sales assistant This blog by @andysingal deep dives into how this agent is created and how to use it Blog:

Tweet media one

8

96

485

@LangChainAI

LangChain

2 months

⚔️RAG Arena There's so many RAG strategies out there - how do you decide which one is best? Run them in battle mode: the same question with 2 different strategies. Compare and vote for winner Awesome project by @mendableai ! Inspired by @lmsysorg

Tweet media one

13

103

489

@LangChainAI

LangChain

4 months

Ⓜ️ MistralAI API We’re excited to announce the new langchain_mistralai package today which lets you use Mistral’s new hosted API in LangChain! Mistral’s Open Source models have impressed us along with many others, and we’re excited about making it even easier to get started…

Tweet media one

8

81

423

@LangChainAI

LangChain

5 months

⭐️ GPT-crawler template ⭐️ Easily building chat assistants for websites (documentation, etc) is an extremely popular use-case. GPT-crawler from @builderio is rapidly growing in popularity for building custom GPTs for sites: This template shows how to…

Tweet media one

2

81

482

@LangChainAI

LangChain

1 year

Friday release with: 🧠NEW memory type (backed by a vectorstore, so allows for semantic search over memories) 🔃FOUR new document loaders (slack, bilibili, playwright, git) 🦄Quality of life improvements for token tracking, output parsing typing, OpenAPI planner agent 🧵

10

58

480

@LangChainAI

LangChain

5 months

⭐️Building RAG Pipelines that Use Multiple LLMs: Query Transformation ⭐️ Many advanced RAG pipelines make multiple calls to LLMs at various stages. Most existing templates currently use the same LLM for all stages, but there's no reason that has to be the case. Over the coming…

Tweet media one

7

99

482

@LangChainAI

LangChain

5 months

⭐️ Deconstructing RAG ⭐️ Given the importance of RAG and the fast pace of development, we've grouped popular RAG concepts into a few categories and created guides for each one. The this new blog post, we summarize these categories / guides and highlight some questions to ask…

Tweet media one

2

98

479

@LangChainAI

LangChain

8 months

🤓re-reading this awesome guide on “what’s going on under the hood in a RAG pipeline” by @czue over coffee this morning ☕ a really thorough deep-dive for anyone that wants to really understand how domain-specific chatbots actually work

Tweet card media

How do domain-specific chatbots work? An Overview of Retrieval Augmented Generation (RAG) | Scriv

Demystifying and deconstructing Q&A bots that work over your data.

5

109

479

@LangChainAI

LangChain

5 months

🦜LangChain & Redis over Financial PDFs Excited to work with the @Redisinc team to create a RAG template for developers to chat with public financial PDF documents such as Nike’s 10k filings. The application uses: 🦄FastAPI and Uvicorn to serve client requests via HTTP 🔃…

Tweet media one

5

110

475

@LangChainAI

LangChain

4 months

👨‍💻codeqai 100% local code search and chat powered by vector embeddings and LLMs Uses a lot of awesome tech to accomplish this! 🌲Tree sitter (for splitting code files) 🧱Sentence Transformers and Instructor embeddings 🌎FAISS 🦙Llama Cpp and @ollama

12

105

464

@LangChainAI

LangChain

3 months

Building Corrective RAG from scratch w/ open source and fully local LLMs (Video) Building LLM apps with more complex logical flows can be challenging with smaller, local LLMs. Graphs offer one way to tackle this, laying out the logic flow as a graph and using local LLMs for…

Tweet media one

4

60

464

@LangChainAI

LangChain

6 months

📃Advanced RAG: Query Transformations We've added a few advanced RAG methods over the past few days that all fall under a similar abstraction: "Query Transformations" ✒️Rewrite-retrieve-read 🧨RAG-Fusion 🏃Step-back prompting We've written a blog on this "Query Transformation"…

Tweet media one

5

85

462

@LangChainAI

LangChain

29 days

🅰️ Anthropic Tool Calling 🛠️ @AnthropicAI just added tool use to their Claude 3 APIs, which is extremely useful for structured outputs. Here's a short video explaining how to use it from the latest langchain-anthropic package! @rlancemartin also explains how to design…

Tweet media one

9

85

468

@LangChainAI

LangChain

2 months

🪆Matryoshka Retriever A recent blog post by @supabase described a new technique for higher performance retrieval, without compromising accuracy. So we've just released a new retriever in LangChain.js 🦜🔗 which implements this exactly! Use any vector store, and two embedding…

Tweet media one

6

102

461

@LangChainAI

LangChain

4 months

🌲RAG With PDFs Want to easily set up a RAG pipeline over PDFs? This great tutorial by our friends at @clarifai goes over how to do exactly that Blog:

Tweet media one

7

83

462

@LangChainAI

LangChain

3 months

🔦Lumos: A RAG LLM co-pilot for browsing the web, powered by local LLMs Use Cases 🧵Summarize long threads 📰Summarize news articles ❓Ask questions about pages Awesome stuff by @andrewnguonly Repo:

Tweet media one

5

81

461

@LangChainAI

LangChain

4 months

🪩RAG Tutorial from Oracle Generative AI Chatbot using LLaMA-2, @qdrant_engine , RAG, LangChain & @streamlit Really detailed blog post walking through ingestion, setting up a chain, and making it look great in the UI Blog:

Tweet media one

5

112

456

@LangChainAI

LangChain

5 months

🦜🛠️We put together a LangSmith demo to show how the platform can help you build production-ready gen AI applications faster and more reliably! Check out these 7 videos, each <10 min, and you'll be a pro in under an hour!

Tweet media one

4

82

452

@LangChainAI

LangChain

6 months

💬Chatting With Your Data Ultimate Guide Do you want a **20 minute** read on all things related to chatting with your data? @Prince_krampah has got you covered (with code as well)! Blog: GitHub:

Tweet media one

6

81

454

@LangChainAI

LangChain

2 months

✂️Semantic Chunking Semantic chunking using embedding distances between sentences to figure out how to split a document. A key decision is what threshold to split at. We now support three methods: 📎Percentile 🟠Interquartile Range 👿Standard Deviation Big shout out to…

Tweet media one

Tweet media two

Tweet media three

5

90

456

@LangChainAI

LangChain

2 months

📹BaoGPT BaoGPT is an AI project that allows you to ask questions about youtube videos Fully OSS, built on LangChain, Anthropic, and Qdrant, with a Discord and Gradio frontend Check out the repo here:

Tweet media one

1

94

456