langchain Profile picture
Jul 13 5 tweets 3 min read Twitter logo Read on Twitter
📃 Document Transformers 📃

Doc transformers make it easy to split, combine, tag, contextualize, etc. raw documents. We've got *four* new ones:

👐 Auto-tagging with OpenAI functions
🤖 Translation, extraction, and Q/A extraction using `doctran` library by @psychicapi

1/5
👐Auto-tagging with OpenAI functions👐

2/5

🤖Translation with doctran🤖

Using the `doctran` library by @psychicapi, we can super easily translate any document from one language to another.

Docs:

3/5 https://t.co/Ewo8KFGSiapython.langchain.com/docs/modules/d…




🤖Property extraction with doctran🤖

Similar to the metadata tagger, the doctran property extractor lets you specify the properties to extract for a document's text and add to it's metadata.

Docs:

4/5 https://t.co/QC3EAFRwmLpython.langchain.com/docs/modules/d…


🤖Q/A extraction with doctran🤖

Converting dialogue to a Q/A format can help with document retrieval in Chat-with-data type applications. The QA transformer does this conversion for you.

Docs:

5/5 https://t.co/Da8eEiTGbHpython.langchain.com/docs/modules/d…




• • •

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

Jul 15
The latest integrations in 🦜🔗:

4⃣ GPT4All embeddings
🗃️Async support (and more) for @qdrant_engine vecstore
🧠 Tongyi Qianwen LLM

Let's take a look 🧵
🗃️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
Jul 8
❓How to use @OpenAI Functions within LangChain

We've gotten a lot of questions of whether it's possible to use OpenAI functions within LangChain, so we added some documentation to that effect.

Docs: python.langchain.com/docs/modules/c…
First up: how to use OpenAI functions to return a structured response

One of the simplest yet most powerful use cases for OpenAI functions is just using it to structure responses

This is the main use we focus on documenting
This involves:

- Passing the schema you want as a function
- Forcing the LLM to respond using that function
- Parsing the function call and treating that as the response

With `create_structured_output_chain` we do all that setup for you, and you get an LLMChain that just works
Read 4 tweets
Jul 6
🍄 LangChain Integrations Improvements

New categories: callback managers, tools, toolkits, memory stores

New pages: top, trending, new

Improved pages: logos, links to reference documentation, intercepting routes

🧵
🤙 Callbacks

Callbacks are intercepters between each step in the chain, allowing for a variety of logging observability

Top integrations include @arizeai @WhyLabs @argilla_io @promptlayer @streamlit @aimstackio @Cometml @itsArthurAI

Page: https://t.co/I7iZWaKGoAintegrations.langchain.com/callbacks
🔧 Tools & Toolkits

These pages highlight the collection of tools & toolkits (groups of tools for a specific purpose) we have

Includes @zapier as well as Gmail, Python REPL, wikipedia, etc

Tools page:

Toolkits page: https://t.co/EtC35JV0ze https://t.co/tI4yVYVcEdintegrations.langchain.com/tools
integrations.langchain.com/toolkits


Read 9 tweets
Jun 28
⭐️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
Read 6 tweets
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

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!

:(