Share this page!

Enter Twitter Thread URL to Unroll

Needs to be the full URL like: https://twitter.com/threadreaderapp/status/1644127596119195649

How to get URL link on Twitter App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
langchain Profile picture
@LangChainAI
Jun 8 • 8 tweets • 4 min read Twitter logo Read on Twitter
Big Thursday release with a lot of new feature!

👩‍🎤SingleStore Vector Database
🪨Shale Protocol LLM Integration
🌳Deep Infra Embeddings
🦌Fauna Document Loader
💤Sleep tool
☁️Nebula graph
🧬Unstructured CSV Document Loader

Basically one of everything!
👇
👩‍🎤SingleStore Vector Database

@SingleStoreDB is a high-performance distributed database that supports deployment both in the cloud and on-premises

Really excited to add this as another vector database offering! Thanks to `volodymyr-memsql`

Docs: python.langchain.com/en/latest/modu…
🪨Shale Protocol LLM Integration

@ShaleProtocol provides production-ready inference APIs for open LLMs. It’s a Plug & Play API as it’s hosted on a highly scalable GPU cloud infrastructure.

It has a very generous free tier of 1k daily requests!

Docs: python.langchain.com/en/latest/inte…
🌳Deep Infra Embeddings

DeepInfra is a serverless inference as a service that provides access to a variety of LLMs and embeddings models. This notebook goes over how to use LangChain with DeepInfra for text embeddings.

h/t @yessenzhar

Docs: python.langchain.com/en/latest/modu… Image
🦌Fauna Document Loader

Fauna is a distributed serverless database. Thanks to @HaqueShadid for adding a document loader to load data from it!

Docs: python.langchain.com/en/latest/modu…
💤Sleep tool

An agent can now put itself to sleep!

If you need to start a long-running job, it can be useful for an agent needs to wait for these results just doing nothing.

PR: github.com/hwchase17/lang…
☁️Nebula graph

Query data in a @NebulaGraph database! Thanks to @wey_gu for adding this integration

More details here:
🧬Unstructured CSV Document Loader

Thanks to our friends at @UnstructuredIO for adding a CSV loader! Lots of impactful data in CSVs - this helps make it easier to interact with it

Docs: python.langchain.com/en/latest/modu…

• • •

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

langchain Profile picture
Jun 6
Big community 🦜🔧0.0.191 release!

🌲TWO new vectorstores: ClickHouse and Tigris
🧑‍💼Excel Document Loader
📹Multilingual support for YouTube Document Loader
🦜Aviary LLM integration
🩺PubMed integrations (tool and retriever)
🦾Guide for deploying LLMs to production

🧵
🛖ClickHouse vectorstore

@ClickHouseDB is an open-source database for real-time apps and analytics, and recently added ANN search indexes allowing it to be used as a high performance and scalable vector database

Thanks to @haozch for adding this

python.langchain.com/en/latest/modu… Image
🐅Tigris Vectorstore

@TigrisData is an open source Serverless NoSQL Database and Search Platform designed to simplify building high-performance vector search applications

Thanks to @adilansari for adding!

Documentation: Image
Read 9 tweets
langchain Profile picture
Jun 2
🦜🔗 0.0.189 is out! With new features:

🏡@elastic kNN search capabilities
✍️LLM feedback with @argilla_io
🧑‍🦱Mechanism for human-in-the-loop validation of tools

a 🧵:
🏡@elastic kNN search capabilities

The Elasticsearch vector store just got an upgrade! Use the tried and true kNN approach to search over your vectors.

Try it out: python.langchain.com/en/latest/modu… ImageImage
✍️LLM feedback with @argilla_io

@argilla_io is a great tool for LLM data labeling, curation, and monitoring. Use the new Argilla callbacks to easily log and provide feedback for you LangChain LLMs!

Integration docs: python.langchain.com/en/latest/inte…
Argilla docs: docs.argilla.io ImageImageImage
Read 4 tweets
langchain Profile picture
May 27
The language model field is becoming more and more wide open, and that’s great for the community.

It’s also why we’ve added *6* new LLM wrappers this week:

🔱VertexAI
🧱Databricks
🦟MosaicML
🧠 CTransformers
🐞Beam
📬OpenLM

Here's links to all of them, in case you missed it 🧵
🔱VertexAI

🧱Databricks

Read 7 tweets
langchain Profile picture
May 26
New day, new (feature) delivery 📦

📝 Momento Cache for LLM caching and chain memory
📱Twilio tool for sending texts
🧠 CTransformers wrapper for GGML models

Let's dive in! 🧵
📝 Momento Cache

LLM queries are expensive and slow, making it hard to scale LLM applications.

@momentohq's serverless cache significantly reduces the burden for repetitive workloads.

More on the integration: python.langchain.com/en/latest/inte…

h/t to Michael Landis for contribution! Image
📱Twilio

Give your agents texting abilities! Great for things like personal assistants and personal CRMs.

What are the use cases you're excited about?

s/o to GH user Tedma4 for the addition!

Docs: python.langchain.com/en/latest/modu… Image
Read 4 tweets
langchain Profile picture
May 25
📃New data loaders and models 🧠

Any 🦜🔗 app is only as good as the models and data it has access to. Which is why we're excited to have *3* new model integrations and *3* new data loaders:

🧠 VertexAI, Modelscope, Minimax models
📃 Bibtex, Joplin, Iugu document loaders

a 🧵:
🧠Model integrations 🧠

Use VertexAI's powerful LLMs, chat models and embedding models.

Use Modelscope (s/o @thomas_yanxin) and Minimax embedding models.

Read more about LangChain model integrations python.langchain.com/en/latest/modu…

📚 Bibtex Document Loader 📚

Want to search, summarize, or ask questions over the docs in your bibliography?

Now you can load all references in a .bib file in ~1 line of code, which can then easily be plugged into existing chains. h/t @WFShaping!

Docs: python.langchain.com/en/latest/modu… Image
Read 5 tweets
langchain Profile picture
May 24
👯‍♂️New integrations in 🦜🔗 0.0.179! 👯‍♂️

LangChain is designed to easily work with all underlying infrastructure. In that vein, we're excited to announce three new integrations:

🔢 Embeddings from @elastic
📂 Vector store from @typesense
🔤 LLM wrapper from @beam_cloud

a 🧵:
🔢 Embeddings from @elastic

Deploy your embedding models on Elastic and access them through LangChain 💪

Read more from Elastic on the integration: elastic.co/blog/privacy-f… Image
📂 Vector store from @typesense

This one has been requested for a long time now 🧓

Typesense is an open source, in-memory search engine. Thanks to @jasonbosco you can now use it for storing and searching over your vectors!

Try it out! 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!

Send Email!

:(