https://github.com/weaviate/recipes

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!
https://github.com/weaviate/recipes

function-calling generative-ai llm-frameworks python retrieval-augmented-generation vector-database vector-search

Last synced: about 21 hours ago
JSON representation

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

• Host: GitHub
• URL: https://github.com/weaviate/recipes
• Owner: weaviate
• Created: 2023-05-16T15:19:31.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-12-13T22:14:49.000Z (8 days ago)
• Last Synced: 2024-12-13T23:20:42.115Z (8 days ago)
• Topics: function-calling, generative-ai, llm-frameworks, python, retrieval-augmented-generation, vector-database, vector-search
• Language: Jupyter Notebook
• Homepage:
• Size: 284 MB
• Stars: 619
• Watchers: 32
• Forks: 116
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Welcome to Weaviate Recipes 💚

![Weaviate logo](.github/Weaviate.png)

This repository covers end-to-end examples of the various features and integrations with [Weaviate](https://www.weaviate.io).

| Category                                | Description                                                                                 |

| ----------------------------------------|---------------------------------------------------------------------------------------------|

| [Integrations](/integrations)           | Notebooks showing you how to use Weaviate plus another technology                           |

| [Weaviate Features](/weaviate-features) | Notebooks covering **vector**, **hybrid** and **generative search**, **reranking**, **multi-tenancy** and more |

## Integrations 🌐

Check out Weaviate's [Integrations Documentation](https://weaviate.io/developers/integrations)!

| Company Category | Companies |

|------------------|-----------|

| Cloud Hyperscalers | Google, AWS, NVIDIA |

| Compute Infrastructure | Modal, Replicate |

| Data Platforms| Databricks, Confluent Cloud, Spark, Unstructured, Firecrawl, Context Data, Aryn, Astronomer, Airbyte, IBM (Docling) |

| LLM Frameworks | DSPy, LangChain, LlamaIndex, Semantic Kernel, Ollama, Composio, Haystack |

| Operations | Arize, Langtrace, LangWatch, Nomic, Ragas, Weights & Biases |

## Weaviate Features 🔧

| Feature | Description |

|---------|-------------|

| Similarity Search | Use Weaviate's `nearText` operator to run semantic search queries (broken out by model provider) |

| Hybrid Search | Use Weaviate's `hybrid` operator to run hybrid search queries (broken out by model provider) |

| Generative Search | Build a simple RAG workflow using Weaviate's `.generate` (broken out by model provider) |

| Filters | Narrow down your search results by adding filters to your queries |

| Reranking | Add reranking to your pipeline to improve search results (broken out by model provider) |

| Media Search | Use Weaviate's `nearImage` and `nearVideo` operator to search using images and videos |

| Classification | Learn how to use KNN and zero-shot classification |

| Multi-Tenancy | Store tenants on separate shards for complete data isolation |

| Product Quantization | Compress vector embeddings and reduce the memory footprint using Weaviate's PQ feature |

| Evaluation | Evaluate your search system |

| CRUD APIs | Learn how to use Weaviate's Create, Read, Update, and Delete APIs |

| Generative Feedback Loops | Write back to your database by storing the language model outputs |

## Feedback ❓

Please note this is an ongoing project, and updates will be made frequently. If you have a feature you would like to see, please create a GitHub issue or feel free to contribute one yourself!