Add elasticsearch examples to vector databases folder (#622)

* Add Elasticsearch to vector databases, add notebooks

* Update prompt

* Make intro verbiage more neutral

* Add semantic search notebook outputs

* Add RAG notebook output

* Update query

* Remove unreadable vector output
This commit is contained in:
Liam Thompson 2023-08-29 19:54:08 +02:00 committed by GitHub
parent 169f5e02c8
commit 31b4de22a3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 1741 additions and 1 deletions

View File

@ -9,6 +9,7 @@ Each provider has their own named directory, with a standard notebook to introdu
## Guides & deep dives
- [AnalyticDB](https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/latest/get-started-with-analyticdb-for-postgresql)
- [Chroma](https://docs.trychroma.com/getting-started)
- [Elasticsearch](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html)
- [Hologres](https://www.alibabacloud.com/help/en/hologres/latest/procedure-to-use-hologres)
- [Kusto](https://learn.microsoft.com/en-us/azure/data-explorer/web-query-data)
- [Milvus](https://milvus.io/docs/example_code.md)

View File

@ -0,0 +1,31 @@
# Elasticsearch
Elasticsearch is a popular search/analytics engine and [vector database](https://www.elastic.co/elasticsearch/vector-database).
Elasticsearch offers an efficient way to create, store, and search vector embeddings at scale.
For technical details, refer to the [Elasticsearch documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/knn-search.html).
The [`elasticsearch-labs`](https://github.com/elastic/elasticsearch-labs) repo contains executable Python notebooks, sample apps, and resources for testing out the Elastic platform.
## OpenAI cookbook notebooks 📒
Check out our notebooks in this repo for working with OpenAI, using Elasticsearch as your vector database.
### [Semantic search](https://github.com/openai/openai-cookbook/blob/main/examples/vector_databases/elasticsearch/elasticsearch-semantic-search.ipynb)
In this notebook you'll learn how to:
- Index the OpenAI Wikipedia embeddings dataset into Elasticsearch
- Encode a question with the `openai ada-02` model
- Perform a semantic search
<hr>
### [Retrieval augmented generation](https://github.com/openai/openai-cookbook/blob/main/examples/vector_databases/elasticsearch/elasticsearch-retrieval-augmented-generation.ipynb)
This notebooks builds on the semantic search notebook by:
- Selecting the top hit from a semantic search
- Sending that result to the OpenAI [Chat Completions](https://platform.openai.com/docs/guides/gpt/chat-completions-api) API endpoint for retrieval augmented generation (RAG)

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long