Joe McElroy

engineering @elastic. working on @searchkit. Github

[Joe McElroy @phoey1]

Searchkit: React Components for elasticsearch. Make fast usable searches quick! https://t.co/0uO4D0VzxW

[Joe McElroy @phoey1]

The 3d transition animation is gorgeous 😍 https://t.co/GXcosh4OkA

[Joe McElroy @phoey1]

@JesseCohenInv I don’t think this leaves people jobless for those who want to work. It should be viewed as entry level roles disappear because the bar is higher. We will also have a higher ceiling to excel.

[Joe McElroy @phoey1]

@JesseCohenInv We need to stop viewing AI as a replacement for the worker and start seeing it as the treadmill. It’s raising the floor of what a human needs to do, but it’s also providing the gym for them to get that strong before they even start.

[Joe McElroy @phoey1]

Great move. Excited to try this out.

[Aidan Gomez @aidangomez]

Your search can see now.

We're excited to release fully multimodal embeddings for folks to start building with!

[Joe McElroy @phoey1]

@johtani_en @xeraa Hey Jun, could you tell me steps you did where you encountered the issue? Happy for this to be in a DM :)

[Elastic @elastic]

Domain-specific generative AI: comparing pre-training, fine-tuning, and RAG as approaches for storing and retrieving knowledge from LLMs. Learn more: https://t.co/4WhMY2Smgd

#ElasticSearchLabs #GenerativeAI

[Chris Hegarty @chegar999]

Vector Similarity Computations FMA-style https://t.co/AI8MzBbnAZ

[LangChain @LangChain]

🦜🏁Self Query Template (@elastic)

Often times documents come with really useful metadata! But how can you best take advantage of this metadata when doing RAG? 🤔

Self-query is one way to do so. This converts a 🗨️natural language query into one piece that is embedded and compared via cosine similarity, just as in naive RAG. But then a "metadata filter" is also extracted, that can be applied to metadata present in the vectorstore

❓This is useful because often times a query may not only refer to semantic meaning, but could also reference some of the metadata

For example: "what is a movie about aliens from the year 1980" 👽

While "aliens" may be a semantic query, "year == 1980" is not, this is an explicit filter that should be applied

Most vectorstores allow for some metadata filters, so this can be used with most of them

Check out our recent template which does this for ElasticSearch: https://t.co/CZzVP15peT

This is an example "query construction" - check out @RLanceMartin's awesome post on this from earlier in the week: https://t.co/Vw5Zb4H5PW

[Josh Devins @joshdevins]

Interested in multilingual vector search with #Elasticsearch? New blog post drop featuring @Microsoft's multilingual E5 embedding model. Have a read, run the notebook, und suche in deiner Sprache! 😉

https://t.co/o6g45ugjO1

[Joe McElroy @phoey1]

@derekcheungsa @llama_index @elastic Hey! I've updated the documentation to better reflect the ElasticsearchStores abilities. Thanks for providing feedback!

[Joe McElroy @phoey1]

@llama_index @elastic Thanks so much for accepting the contribution! More to come :)

[LlamaIndex 🦙 @llama_index]

LlamaIndex + @elastic 🚀

This has been a highly requested feature (a lot of our users are using Elasticsearch!)

HUGE shoutout to @phoey1 for making this happen.
- Vector/text/hybrid search
- Metadata + metadata filtering
- es_filters
- And more!

https://t.co/vxmGb4QXBd

[LangChain @LangChain]

The latest and greatest in 🦜🔗:

🧠 @neural_internet Bittensor LLM
⚡ DashVector store
🤖 @zep_ai vector store
♻️ @elastic search self-querying retriever

a 🧵:

[LangChain @LangChain]

♻️ @elastic search self-querying retriever

Combine the power of the Elasticsearch vector store with LangChain’s query constructor chain to create a self-querying retriever.

Huge s/o to @phoey1 for continuing to add Elasticsearch features to 🦜🔗!

Docs: https://t.co/N6ZCpnT0ie

[Philipp Krenn @xeraa]

more #elasticsearch integrations coming your way :)
PS: we'll also have LangChain at our upcoming ElasticON AI event in san francisco: https://t.co/mjYsGn0GCY

[LangChain @LangChain]

New in 🦜🔗==0.0.265!

3 new model wrappers and vector store improvements:

🐾 Ernie chat model
🚅 @berriai LiteLLM chat model support
🪄 @neuralmagic DeepSparse LLM
🤹 Major @elastic vector store improvements

a 🧵:

[LangChain @LangChain]

🤹 New @elastic vector store

@phoey1 has done a huge revamp and added a new Elasticsearch-backed vector store, allowing for a number of new index / query strategies.

Try it out:
``from langchain.vectorstores import ElasticsearchStore``

Docs: https://t.co/Bw27k3Kjtl

[Benjamin Trent @benwtrent]

This is why optimization tasks are addictive! Getting some nice improvements for vector search in Apache Lucene 9.7. https://t.co/i0sBBpMI8I

[Shay Banon @kimchy]

Why we designed, in the last couple of years, Elasticsearch and Lucene vector database implementation the way we did, and where we are heading https://t.co/yNTwxLf6FD

[Shay Banon @kimchy]

I ❤️Lucene.

Like so many times before (real time search, doc values, bm25, bkd, compressions, …), we are actively investing in making Apache Lucene also a great Vector Database https://t.co/nWmx492Vpu