AI Native 的开源技术栈：

- 前端UI: Streamlit
- Mulit Agent 框架: crewAI
- Agent 可观测框架：AgentOps 🖇️
- 应用开发： LangChain
- 开源模型部署：ollama
- 最快的AI Infra： Groq Inc
- LLMOps： Dify.AI
- LLM 微调： Unsloth AI
- 向量数据库： Weaviate • vector database

欢迎补充👏🏻

Our open-source RAG app, Verba, can now run Ollama models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little

New video just dropped in my module on how to create a full-stack web application using DSPy, FastAPI, Weaviate, and React. In the video, I explain how to set up a basic API using FastAPI and a simple DSPy service. More chapters are coming in the next few days. Link to the full

Finally added a React frontend to the RAG application. Still using DSPy, FastAPI, and Weaviate in the backend. It is amazing to develop a full-stack web application powered by DSPy.🔥🔥🔥🔥🔥

Link to module in second tweet !

Just a casual night in SF at the GitHub offices full of AI builders.

Shoutout AJ Chan daniel phiri in sf 🇺🇸 and Weaviate • vector database for the event and continuing to support the community.

Vector DB pricing is incredibly complex

I have been trying to answer a simple question:

What is monthly cost to store 10M vectors?

I looked at 3 providers:
• pinecone
• turbopuffer
• weaviate

Here is what I found:
• have to pay for storage (cheap)
• have to pay per write

Remember our “Chat with your code” app?

We’ve now added state-of-the-art RAG techniques such as reranking, code chunking, and few-shot prompting - using ollama, Weaviate, and LlamaIndex 🦙.

Simply copy our new Lightning AI ⚡️ Studio template to get started with your advanced

We are moving fast here. The backend is now up and running. Users can upload documents (TXT, PDFs even OCR). The documents are then chunked and stored in our Weaviate vector store. We use a DSPy RAG module to provide answers and the context used to provide these answers.

Here is

Although your data is distributed throughout numerous databases, you can still use ALL of it for your RAG application 🍱

In this notebook, we build an end-to-end RAG pipeline that uses #Google 's Big Query and Weaviate • vector database, using DSPy!

Context Fusion with Agents will first

It’s happening, over 500+ signups? A packed venue at Edge, amazing partnerships with Arize AI cohere and of course Weaviate • vector database. Excited to learn more about DSPy from Omar Khattab!

New short course: Building Multimodal Search and RAG', by Weaviate • vector database's Sebastian {W}italec ✊🏽✊🏾✊🏿.

Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This

Hack night at GitHub. It was super fun! TY Weaviate • vector database OctoAI Twelve Labs (twelvelabs.io)

Had a great time tonight at GitHub HQ with Weaviate • vector database 's one and only AJ Chan ! Be sure to check them out for all your vector database needs (DB is written in Golang btw)

类 Trieve 的模块化设计、支持人人可构建全栈 RAG 应用的 Weaviate Verba 开源，目前 2.5K Star ⭐️

1. 支持与 LangChain 等框架集成、支持开源 Embedding/LLM
2. 支持多租户设计、数据管理、可私有化/本地部署💥
3. 支持配套的 RAG UI 管理界面 👩‍🌾

github.com/weaviate/Verba

A smart friend recently asked me: Are vector databases a product or a feature?

@Pinecone, Qdrant, Chroma, Weaviate • vector database, and Milvus have raised hundreds of millions and are collectively worth billions. They represent the fastest-growing segment in data

We need deterministic LLM outputs.

An information network.

Graphs!

How to build them with LLMs? 🤔
How to search them?🎓

We help with the new cognee 0.1.4 release!

An optimizer to train a knowledge graph generation with #DSPy and Weaviate • vector database to get better contexts 💥
👇

Another chapter just dropped: adding @weaviate into the mix! The RAG module is powered by DSPy, of course. Things are really starting to take shape in the backend. Amazing to see! 🔥🔥🔥

As always, here is the preview (full link to the video in second tweet)

DSPy talk by Omar Khattab :

Learn to program optimized prompts

cohere Stanford NLP Group Arize AI Weaviate • vector database

Multi vector support is here in the Weaviate 1.24 release 🥳

With the new named vector feature, you'll be able to store more than a single vector in an object with separate names. You can then query within a specific target vector space, further enhancing your search results.

What RAG applications are you going to build with Weaviate • vector database?