If you want to explore finetuning LLaMA2, we'll be talking at and helping out with a 1 day in-person event focused explicitly on finetuning OSS models Hopefully this guide will come in handy! RSVP here (s/o @swyx and @NaderLikeLadder for organizing): https://
partiful.com/e/T4ngRPaU2uUT
XM8pN17d
…
@hwchase17
-
Fine-tuning LLaMA2 Workshop: One-Day In-Person Event
By
–
-
LLMate Launches Solution for Structured Data QA
By
–
QA over structured data is hard
— Harrison Chase (@hwchase17) 23 août 2023
Excited to so LLMate working with @manuelsoria_ and @fpingham to bring a solution to market
We've been chatting with them for a while – they've got some good ideas https://t.co/4ZLpFG4StDQA over structured data is hard Excited to so LLMate working with @manuelsoria_ and @fpingham to bring a solution to market We've been chatting with them for a while – they've got some good ideas
-
Conversational Retrieval Agent Real-World Benefits
By
–
This is great example of real-world benefits of using the conversational retrieval agent Allows you to query for multiple different terms and react to previously queried results
-
Airbyte’s 300+ Document Loaders Simplify Python LangChain Integration
By
–
Airbyte has 300+ document loaders – this will make it easier to use them in pure python – no need to set up the Airbyte server Bring the necessary context into your LangChains!
-
Amazon Textract Integration for LangChain PDF Loading
By
–
Amazon Textract Integration Loading PDFs has been one of the biggest areas of questions for folks using LangChain to connect to their data That's why I'm excited to highlight our recently-added integration with Amazon Textract https://
python.langchain.com/docs/integrati
ons/document_loaders/pdf-amazonTextractPDFLoader
… -
What retrieval areas deserve more research focus?
By
–
What areas of retrieval are most interesting to folks and we should push more on?
-
LangChain Retrieval Docs Revamp: New Algorithms
By
–
New Retrieval Docs Took some time over the weekend to revamp our retrieval docs Aside from everything needed for ingestion (load, split, embed, store), @langchain also has a collection of retrieval algorithms (self-query, parent document, etc) https://
python.langchain.com/docs/modules/d
ata_connection/
… -
BG Embeddings Lead Leaderboards with LangChain Integration Guide
By
–
BG Embeddings are at the top of several emebedding leaderboards – awesome guide by @umitmertcakmak showing how to use them in langchain!
-
Data Ingestion Fundamentals with Airbyte and Sweep
By
–
Before you can retrieve data, you first need to ingest it Chatted in depth about this during our most recent webinar with @AirbyteHQ and @sweepai – check it out on YouTube here:
-
LangChain Expression Language for Agent Creation
By
–
really great exploration of using langchain expression language to create an agent