langchain Profile picture
Jun 28 6 tweets 2 min read Twitter logo Read on Twitter
⭐️LangChain Integrations⭐️

In this fast moving LLM landscape, we want to give everyone the power and flexibility of as many options as possible

But we also want to make it simple and easy to navigate

That's why we're launching an integrations hub

integrations.langchain.com
It exists to help you navigate the wide range of data sources and connections that’ll help you build awesome applications

A massive thank you to every one of our partners listed on here. If a product is on this page, it works seamlessly with LangChain
📃Document Loaders

These include integrations with other providers like @UnstructuredIO and @AirbyteHQ

As well as:

Chat apps like @discord @telegram @SlackHQ
Productivity apps like: @airtable @NotionHQ @RoamResearch
Social media: @Twitter @YouTube
Devtools: @github @figma
🌲 Vectorstores

Lots of options to choose from!

Includes pure vectorstores like @pinecone @weaviate_io @trychroma @qdrant_engine @milvusio

As well as databases that have added vector support: @supabase @Redisinc @elastic

As well @vectara @lancedb
🌎 Models

Finally, your application would not work without models (LLM, ChatModel, Embedding)

Standard interface for 40+ models including @OpenAI @AnthropicAI @huggingface @nomic_ai @CohereAI VertexAI, Azure, PaLM, and more

As well as wrappers like @promptlayer
The best version of LangChain is the version that lets you connect ANY source of data to ANY LLM, no matter where it lives or how it’s structured

So if something’s not working, tell us! And if there are integrations we’re missing, let us know!

forms.gle/ZAA6QpHSvB6Jxn…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with langchain

langchain Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @LangChainAI

Jun 20
We've talked a lot about OpenAI functions over the past week. But we've been shipping lots of other features in the meantime, too:

🦆 Upgrades to @DuckDuckGo wrapper by GH Undertone0809
🥇 Upgrades to @SingleStoreDB vector store by GH volodymyr-memsql

1/4
🌅 Improvements to @arizeai callback handlers by GH
hakantekgul
✨Improvements to @argilla_io callback handlers by @alvarobartt
🌊Enhanced search for @OpenSearchProj vector stores by @oneryalcin

2/4
♻️Self-query support for @MyScaleDB by GH mpskex
🕸️Integrations with GH oobabooga's text-generation-webui by GH lonestriker
♒️Revamp of @activeloopai's Deep Lake vector store by GH adolkhan
🌤️ Improvements to AnalyticDB vector store by GH wangxuqi
and even more...

3/4
Read 4 tweets
Jun 14
🚨🤖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 👇 Image
First, if you just want to jump right to trying it out:

Python Docs: github.com/hwchase17/lang…

JS Docs: js.langchain.com/docs/modules/a…
Under the hood, we are heavily utilizing the new `functions` parameter available in the chat model

First, we convert the LangChain tool spec to the function tool spec the expect
Read 8 tweets
Jun 12
🦜🔗0.0.198 adds a lot of functionality to every step of the ingestion process!

+2 Document Loader (@airtable, XML)
+2 Text Splitter features
+2 Embedding providers
+3 Vectorstores

Lots of detail, so buckle up👇 Image
🏓Airtable Loader

@airtable is a super popular platform for storing and collecting data (we've used it internally for meetup sign ups)

You can now easily load data from there with our new document loader!

Docs: python.langchain.com/en/latest/modu… Image
✖️ XML Loader

s/o to our friends at @UnstructuredIO for adding an XML loader!

@mrobinson0623 you're the best

Docs: python.langchain.com/en/latest/modu… Image
Read 11 tweets
Jun 11
🦈Querying graph databases with LLMs can be hard🦈

s/o to @tb_tomaz for adding multiple knobs to turn when using our GraphCypherQAChain

🦵Limit the number of results
🪜Return intermediate results
🎯Return Direct results

🧵 ImageImageImage
🦵Limit the number of results

You can limit the number of results from the Cypher QA Chain using the top_k parameter. The default is 10.

This is useful to make sure you don't pass too many results back to the LLM and overwhelm the context window

Docs: python.langchain.com/en/latest/modu…
🪜Return intermediate results

You can return intermediate steps from the Cypher QA Chain using the return_intermediate_steps parameter

This is useful to get programmatic access to the generated graph query

Docs: python.langchain.com/en/latest/modu…
Read 4 tweets
Jun 10
🧙‍♂️Lord of the Retrievers🧙‍♂️

This cheekily named retriever (more simply called the "Merger Retriever" from @musicaoriginal2 allows for easy combination of MULTIPLE retrievers

This can cause a lot of documents to be returned... so what do you do then?

🧵 Image
First: Why would you even want to combine multiple retrievers?

This can be useful if you have potentially relevant information in multiple sources

You could use an existing method like "Routing" to choose between the retrievers... but what if you want to use all of them?
A second way this can be useful is if you want to use multiple different retrieval strategies on the same data

Don't want to choose between semantic similarity, MMR, and BM25? Now you don't have to!
Read 7 tweets
Jun 9
Lets go into the weekend with 🦜🔗0.0.195 with three big items:

🔟 Baseten LLM Integration - serve ML models
❄️Snowflake Document Loader - load documents so you can index them
🐔AWS Kendra Retriever - use this enterprise-grade search functionality to do grounded generation

🧵
🔟 Baseten LLM Integration

Baseten provides all the infrastructure you need to deploy and serve ML models performantly, scalably, and cost-efficiently.

Documentation: python.langchain.com/en/latest/modu… Image
❄️Snowflake Document Loader

Load data from your @SnowflakeDB into document objects. This will allow you to split, embed, and then eventually query it with semantic search

Docs: python.langchain.com/en/latest/modu… Image
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(