Charna Parkey, Ph.D. (she/her)

2.7K posts

Charna Parkey, Ph.D. (she/her) banner
Charna Parkey, Ph.D. (she/her)

Charna Parkey, Ph.D. (she/her)

@CharnaParkey

Host, Open Source Data, VP, Innovation@DataStax prev VP, Product@Kaskada — co-creator of the first feature engine with time travel.

Seattle, WA Katılım Şubat 2010
2.6K Takip Edilen1.2K Takipçiler
Jerry Liu
Jerry Liu@jerryjliu0·
Pretty excited about this new RAG technique I cooked up 🧑‍🍳 A top issue with RAG chunking is it splits the document into fragmented pieces, causing top-k retrieval to return partial context. Also most documents have multiple hierarchies of sections: top-level sections, sub-sections, etc. This is also why lots of people are interested in exploring the idea of knowledge graphs - pulling in "links" to related pages to expand retrieved context. This notebook lets you retrieve contiguous chunks without having to spend a lot of time tuning the chunking algorithm, thanks to GraphRAG-esque metadata tagging + retrieval. Tag chunks with sections, and use the section ID to expand the retrieved set. Check it out github.com/run-llama/llam…
Jerry Liu tweet media
LlamaIndex 🦙@llama_index

We’re excited to feature a new RAG technique - dynamic section retrieval 💫 - which ensures that you can retrieve entire contiguous sections instead of naive fragmented chunks from a document. This is a top pain point we’ve heard from our community on multi-document RAG challenges - naive RAG returns fragmented context without awareness of the surrounding document. Our approach allows you to start off with a “simple” chunking technique (e.g. per page), but do a post-processing workflow to attach section/sub-section metadata. You can then do GraphRAG-like retrieval (two-pass retrieval): retrieve chunks, look up the attached section metadata, and then do a second call to return all chunks that match the section ID. github.com/run-llama/llam…

English
13
112
632
117.8K
Charna Parkey, Ph.D. (she/her) retweetledi
LangChain
LangChain@LangChain·
@AstraDB Cassandra-based Vector DB 🌌 Explore the langchain-astradb integration package! Harness the serverless, vector-capable database built on Apache Cassandra for scalable NoSQL solutions enhanced with the power of vector similarity search. python.langchain.com/docs/integrati…
LangChain tweet media
English
0
16
26
1.9K
Charna Parkey, Ph.D. (she/her) retweetledi
LlamaIndex 🦙
LlamaIndex 🦙@llama_index·
We’re excited to feature the AI Chatbot Starter 🤖🧰 - a web server powered by AstraDB (@DataStax) and @llama_index that you can easily spin up to chat over any web documentation 🌐📑 Easily use this as a standalone service or integrate it with your full-stack application. Set it up by simply setting a few credentials and ingesting your documents. A huge shoutout to the @Datastax team for creating this: check it out below 👇 Repo: github.com/datastax/ai-ch…
English
5
46
184
23.9K
Dara
Dara@daraladje·
Looking for a new vector database provider. Any recommendations? We've been loving @pinecone but they just lost all of our data, so looking for something more reliable
English
59
7
84
29.8K
Charna Parkey, Ph.D. (she/her) retweetledi
Chet Kapoor
Chet Kapoor@ChetKapoor·
⚡️Real-Time AI: a thread⚡️ ⏲️Why NOW ? Every business today needs an AI strategy – the market has been validating this for years. Leading enterprises (Google, Netflix, Uber) use AI to drive business outcomes. And most applications will include ML models by 2027. [1/5]
English
1
3
2
999
Charna Parkey, Ph.D. (she/her) retweetledi
Ania Kubów #JavaScriptGames
Ania Kubów #JavaScriptGames@ania_kubow·
#CassandraForward is your opportunity to learn all about Apache Cassandra — new capabilities and exciting use cases. Register for the free two-hour virtual event and join the global Cassandra community on March 14: dtsx.io/3ZCNSHB
English
1
18
100
23.2K
Charna Parkey, Ph.D. (she/her) retweetledi
Chet Kapoor
Chet Kapoor@ChetKapoor·
What does Real-Time AI done right look like ? ➡️Timely insight & action at scale ➡️Flexibility & responsiveness ➡️Reduced time, cost, & complexity GREAT blog by @CharnaParkey 👇 datastax.com/blog/real-time…
English
0
1
2
145
Charna Parkey, Ph.D. (she/her) retweetledi
Apache Cassandra
Apache Cassandra@cassandra·
Unfortunately, Cassandra Summit has been postponed until December 12 but Cassandra Forward is on March 14th. Register today! It's free and online. No travel is required. Use this link to get notified about changes. lnkd.in/gAUQD5sm #ApacheCassandra #community #event
Apache Cassandra tweet media
English
0
9
12
3.4K
Charna Parkey, Ph.D. (she/her) retweetledi
Patrick McFadin
Patrick McFadin@PatrickMcFadin·
Budgets are getting cut everywhere. I know this will help. If you are able, let’s get together in San Jose!
English
0
9
11
1.4K
Charna Parkey, Ph.D. (she/her)
Charna Parkey, Ph.D. (she/her)@CharnaParkey·
Will I see you there? I'll be attending and looking to connect with other AI leaders who are using #Cassandra as a feature store for real-time applications.
Apache Cassandra@cassandra

Join us at Cassandra Summit, the world’s largest gathering of #ApacheCassandra community members including architects, developers, users & industry thought leaders, March 13-14 in San Jose: bit.ly/3eyhMea #cassandrasummit #opensource #oss #linuxfoundation

English
0
0
1
177

Keşfet

@jerryjliu0 @lesbiantech @rusic_milos @deepset_ai @Haystack_AI @AstraDB @DataStax @llama_index