📣📣📣 Great thanks to Weaxs with his working-in-progress pull request to introduce #TiDB as #VectorStore in Dify.AI !

github.com/langgenius/dif…

#MySQL #VectorSearch #GenAI

Details on OpenAI's new assistants RAG

*Hard* creep into vectorstore territory

Thoughts:
* Default chunk overlap of 50%, super interesting
* Metadata filtering, super interesting how this dips into vectorstore territory
* Unsure about what chunking method they use - 800 tokens

GPT long term memory RAG with embeddings and SQLite as Vectorstore 🚀
code files below 👇

📝 LangChain RetrievalQA lets you ask your documents (embeddings) questions.

Modifying the search for the retriever can increase the quality of your response.

Here is an example using Activeloop's Deep Lake as your vectorstore.

Diagram, Code, and More. Lets Go! ⤵️

Confused about using LlamaIndex 🦙 indices or configuring parameters for building robust QA Systems?

See my new video on:

1️⃣ VectorStore Index
2️⃣ Storage Context
3️⃣ Service Context
4️⃣ List Index
5️⃣ KeyWordTable Index

📺 Video: rb.gy/ofmvo
📔 Notebook:

Previously I've talked about the amazing Ingestion Pipeline from LlamaIndex 🦙.

Here's how to use Redis (@Redisinc) as the docstore, vectorstore and cache for the pipeline.

LlamaIndex abstractions make it really easy to just use Redis for the entire pipeline 🔥👇

🦜🤖OpenGPTs

Some big updates to OpenGPTs - an open-source, fully configurable GPTs experience

You can now:

📁Upload files to a retrieval tool (with full configurability over the ingestion, vectorstore, and retrieval used)
🌐Share public bots that you've created
🛠️Use more

Master Transformer in 18 Hours with PyTorch🚀

Check out on my YouTube Channel

🟠 youtube.com/playlist?list=…

#MachineLearning #opensource #LLM #vectorstore #NLP #ArtificialIntelligence #datascience #textprocessing #deeplearning #deeplearning ai

5人目は森 一弥氏「AI全盛時代に備えるナレッジデータ管理〜VectorStoreの選び方〜」のトークです。
RAG（検索拡張生成）環境の基本概念とそのビジネスへの応用可能性を解説。実際に触ってみた感触も踏まえてトーク！
#生成AI協会 #gais #ChatGPT #ジェネレーティブＡＩ勉強会

⚡️ Mindwave Progress:
Got the architecture sketched out, 'Concept' docs written, interfaces for the building blocks defined.

✅ OpenaAI Chat and Complete API support added,
✅ InMemory Array Vectorstore is working (for testing)
✅ text-embedding-ada-002 Embedding API working

smolvecstore:

tired of hearing about all the vectorstore libraries along with buzzwords thrown around, here is a tiny implementation of a 'Vectorstore' built with numpy.

this implementation is only ~100 lines of python code but still works fast enough (on cpu).

lol, lmao even.

Fun to work w/ anton (𝔴𝔞𝔯𝔱𝔦𝔪𝔢) + Chroma on RAG w/ multi-modal embeddings.

Built a vectorstore of OpenCLIP embedded image + texts on impt artworks/photos.

GPT-4V can serve as an art critic, providing details about any retrieved images + texts.

Cookbook:
github.com/langchain-ai/l…

Playing around with langchain and offline LLMs today – made a bot that answers questions based on expo docs 📖

This is mostly based of this tutorial, but with llama.cpp for both LLM and embedding models and Redis as vectorstore.
python.langchain.com/docs/use_cases…

LlamaParse with LangChain 🔥

Uploaded a video on how I used Llamaparse from LlamaIndex 🦙 with LangChain to create a super simple RAG app using Chainlit

- Qdrant as vectorstore
- mixtral from Mistral AI via Groq Inc
- Langsmith for traces

Video:

All the code that is required for a simple, yet effective RAG pipeline.

VectorStore on Supabase + Langchain is incredibly powerful.

Run as a build script on your documentation markdown.

And watch what happens.

I have a simple Conversational Retrieval Chain with a Vectorstore of 6,108 indices.

What are some techniques to speed up Q/A on Documents with LangChain?

If you have a suggestions, would love to hear them below ⤵️
I'll also include any of my findings 🤔

Step by Step guide to use LlamaIndex 🦙 with Pinecone ⚡️

🦙LlamaIndex | CHAT With Documents with PINECONE As VectorStore

#llamaindex #pinecone #nlp #chatwithdocuments

youtu.be/4kwAhzzaW4A

🦜🧱Building an LLM Application for Document Q&A Using Chainlit, Qdrant and Zephyr

This guide is not only super detailed, but also:

💬Uses a local model (Zephyr) and local vectorstore (Qdrant)
🧮Uses more advanced RAG techniques (reranking)

Blog: nayakpplaban.medium.com/building-an-ll…

🧠 Mindwave update:

✅ Re-worked the vectorstore interface, its not much simpler. (we can expand it later if needed YAGNIKISS etc)
✅ Weaviate Driver now works.
✅ Added Gmail OAuth to the Mindwave demo (chat with your emails) etc, will be available as a Document loader in core

Ready to build your own RAG? Here’s the tech stack you need 👇

- LangChain as framework
- UnstructuredIO for data prep
- Fastembed for embedding
- Qdrant as vectorstore
- Llama3 via Groq Inc

Video: youtu.be/m_3q3XnLlTI

#rag #llm #groq #langchain #unstructured