LangChain Profile picture
Jul 25 β€’ 5 tweets β€’ 3 min read Twitter logo Read on Twitter
The latest features πŸ¦œπŸ”—:

πŸ‘©β€πŸ‘§β€πŸ‘¦ Ensemble retrieval
πŸ“Š @etherscan document loader
➰ @activeloopai DeepLake self query retriever
πŸ₯‘ @arangodb graph QA chain

Let's dive in 🏊:
πŸ“Š @etherscan document loader

Load in many different types of Ethereum Mainnet transaction histories using EtherScan.

Big s/o to @glazecl for the addition!

Docs: https://t.co/hev9D0u8bzpython.langchain.com/docs/integrati…
Image
➰ @activeloopai DeepLake self query retriever

Wrap the DeepLake vector store in a retrieval system that can translate natural language queries to DeepLake-compatible structured queries, including metadata filters.

s/o to GH user adolkhan!

Docs: https://t.co/aWcoUGTPyrpython.langchain.com/docs/modules/d…

Image
Image
πŸ₯‘ @arangodb graph QA chain

ArangoDB is a graph native database with built-in JSON doc storage, search and more.

Talk to your ArangoDB graph in natural language using this new chain!

Docs: https://t.co/THB8zB9D2Npython.langchain.com/docs/modules/c…

Image
Image
πŸ‘©β€πŸ‘§β€πŸ‘¦ Ensemble retrieval

What's the best retrieval system? Vector similarity search, MMR, KNN, keyword search, ...?

With @dayuanjian21687 new retriever, you can get the best of multiple approaches by fusing the rankings of several retrievers.

Docs: https://t.co/f3kNtKFPoRpython.langchain.com/docs/modules/d…
Image

β€’ β€’ β€’

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

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

Jul 26
Latest and greatest in πŸ¦œπŸ”—:

🌊 @MLflow AI Gateway chat models
πŸ“ @LocalAI_API Embedding models
πŸ” Agent iterators

Allow us to explain (a 🧡):
🌊 @MLflow AI Gateway chat models

AI Gateway makes it easy for organizations to manage and access all of the models they're using.

πŸ—£οΈNow supporting chat models!

Docs: https://t.co/LuEt4YFKlBpython.langchain.com/docs/integrati…
Image
πŸ“ @LocalAI_API Embedding models

LocalAI lets your run LLMs, embedding models and others locally. And its drop-in replacement interface for OpenAI makes it super easy to get off the ground.

Use LocalAI embeddings in πŸ¦œπŸ”— thanks to @mudler_it!

Docs: https://t.co/xDyNBrIovrpython.langchain.com/docs/integrati…
Image
Read 4 tweets
Jul 24
πŸ“š Documentation Improvements πŸ“š

We've been working hard to make our docs better. This is an ongoing effort, so if you have specific feedback or requests, please let us know.

Here's what we've done in the past week:

a 🧡

1/n
Unified JS and Python structure

We've unified the structured of the JS and Python docs, so that they broadly share the same terms and organization, making it clear where there's parity.

JS:
Python: https://t.co/8gnFfZhuVP

2/n https://t.co/8Z5VKMZg30js.langchain.com/docs/get_start…
python.langchain.com/docs/get_start…

Image
Image
Bubbled up Integrations and Use Cases sections

We've moved our Use Cases and Integrations sections to the top level and flattened them, to cleanly separate conceptual and more applied docs and make it easier to get to the page you're looking for.

3/n

https://t.co/UBnVUK6owppython.langchain.com/docs/integrati…
Image
Read 6 tweets
Jul 21
Latest in πŸ¦œπŸ”—:

βš’οΈ @github agent
πŸ‹οΈ @predibase LLMs
πŸͺ Amazon Neptune db

Let's take a look! a 🧡:
βš’οΈ @github agent

Create an agent that can not just write code, but also read from and write to a GitHub repo! (Of course, use with caution!)

s/o to @trevordobbertin for the very cool integration!

Docs: python.langchain.com/docs/modules/a…
πŸ‹οΈ @predibase LLMs

Predibase enables anyone to train their own models. With the new πŸ¦œπŸ”— integration, it's now also easy for anyone to take their custom model and start building applications on top of it πŸ’ͺ

Big s/o to @AbhayyM for the addition!

Docs: python.langchain.com/docs/modules/m…
Read 4 tweets
Jul 20
The latest in LangChain 🎁

πŸ₯‡ Query @Golden knowledge base
✈️ Search flights with @AmadeusITGroup
🌎 Interact with geospatial data vs @geopandas
πŸ—ƒοΈ Caching, tracing, tagging, retries, and more with @PortkeyAI

a 🧡:
πŸ₯‡ Query @Golden knowledge base

Golden is aiming to build the largest open knowledge graph of entities and topics. Now your agents and chains can access that knowledge.

Thanks to GH user constantinmusca!!

Docs: https://t.co/9S4CT4Jfeipython.langchain.com/docs/modules/a…
Image
✈️ Search flights with @AmadeusITGroup

Create chains and agents that can find you realtime flight information using the new Amadeus toolkit!

Time for some AI-generated vacations πŸ˜ŽπŸ–οΈ

s/o to GH user sdelgadoc for the feature!

Docs: https://t.co/FpqN8fivimpython.langchain.com/docs/modules/a…
Image
Read 5 tweets
Jul 18
πŸ¦œπŸ› οΈΒ Introducing LangSmith πŸ¦œπŸ”—

A unified platform to help developers debug, test, evaluate, and monitor their LLM applications.

Integrates seamlessly with LangChain, but doesn't require it. Image
βœ’οΈBlog

what we built, where we’re going, and how our Alpha partners put LangSmith to use

πŸ™πŸ½ to companies like @klarna @SnowflakeDB, @streamlit @BCG @DeepLearningAI_ @fintual @mendableai @multion_ai & @quivr_brain for helping us shape LangSmith

blog.langchain.dev/announcing-lan…
πŸ—ΊοΈComprehensive User Guide

This walks through how to best use the platform, including connectivity with other companies like:

@openai & @anthropicAI for replaying runs

@thefireworksai for finetuning

@getcontextai for analytics

docs.smith.langchain.com/docs/overview
Read 4 tweets
Jul 15
The latest integrations in πŸ¦œπŸ”—:

4⃣ GPT4All embeddings
πŸ—ƒοΈAsync support (and more) for @qdrant_engine vecstore
🧠 Tongyi Qianwen LLM

Let's take a look 🧡
πŸ—ƒοΈAsync support (and more) for @qdrant_engine vecstore

@LukawskiKacper's latest contribution adds full async support along with MMR search and deletion capabilities to the already very capable Qdrant vector store interface.

Docs: python.langchain.com/docs/modules/d…
🧠 Tongyi Qianwen LLM

Access Alibaba's Tongyi Qianwen LLM thanks to GH user wangxuqi's contribution!!

Docs: python.langchain.com/docs/modules/m…
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!

:(