There was always a balance between small enough chunks to allow the embeddings to capture the semantic meaning of a chunk, while at the same time wanting them to be long enough to have the full context This helps strike this balance Docs: https://
python.langchain.com/docs/modules/d
ata_connection/retrievers/parent_document_retriever
…
@hwchase17
-
Balancing Chunk Size for Semantic Embeddings in RAG Systems
By
–
-
Parent Document Retriever: Semantic Chunk Embeddings Strategy
By
–
Parent Document Retriever A new retrieval algorithm that: Creates small chunks (to allow embeddings to have semantic meaning) Fetches the PARENT documents those chunks came from (to capture full context) Parent documents can be either raw documents or larger chunks
-
Exploring Retrieval Algorithms for LangChain Documentation
By
–
We'd been noodling on this concept for a bit, but spurred into action by @ChrisBoraTweets yesterday: https://
x.com/ChrisBoraTweet
s/status/1689018380584439808?s=20
… What other retrieval algorithms would be good to add? Docs: https://
python.langchain.com/docs/modules/d
ata_connection/retrievers/parent_document_retriever
… -
LangChainJS Text Splitters Available for Development
By
–
i think we have most of these splitters in langchainjs – @Hacubu can maybe help you out
-
Exploring AI Playground Capabilities and Features
By
–
A fun playground experience, good way to explore capabilities https://t.co/Gi5H2O3cvE
— Harrison Chase (@hwchase17) 9 août 2023A fun playground experience, good way to explore capabilities
-
ParentDocumentRetriever Implementation in LangChain Framework
By
–
I ended up going a slightly different direction (in terms of implementation): https://
github.com/langchain-ai/l
angchain/pull/8941
… ParentDocumentRetriever – retrieves the parent document for a given chunk. not exactly the same but close? -
QA Bot Streaming with FastAPI and LangChain
By
–
This is a great example code snippet for creating a QA bot that streams via FastAPI The LangChain Expression Language makes this much simpler than before (more accurately, the standard streaming interface that all LCEL object have makes this simpler)
-
Text Splitters: Nuanced AI Component Deserving More Discussion
By
–
hopefully this also inspires folks to add new text splitters! imo one of the most nuanced and interesting pieces, yet less discussed
-
Text Splitting Playground Open Source for LLM Applications
By
–
Text Splitting Playground Chunking text into appropriate splits is seemingly trivial yet very nuanced Open sourcing a playground to help explore different text splitting strategies GitHub: https://
github.com/langchain-ai/t
ext-split-explorer
… Hosted Playground: https://
share.streamlit.io/app/langchain-
text-splitter/
…