Add dbpedia dataset to examples #4305
Conversation
|
@shankar-iyer is attempting to deploy a commit to the ClickHouse Team on Vercel. A member of the Team first needs to authorize it. |
|
@shankar-iyer we have an examples repository as well, just an idea to put the Python code there and we can cross link to it from this page. I'll add support for code blocks to display code from external files in the near future. |
| keywords: ['semantic search', 'vector similarity', 'approximate nearest neighbours', 'embeddings'] | ||
| --- | ||
|
|
||
| The [dbpedia dataset](https://huggingface.co/datasets/Qdrant/dbpedia-entities-openai3-text-embedding-3-large-1536-1M) contains 1 million articles from Wikipedia and their vector embeddings generated using the `text-embedding-3-large` model from OpenAI. |
There was a problem hiding this comment.
Shankar, could you add a link to https://platform.openai.com/docs/models/text-embedding-3-large?
| ```sql | ||
| ALTER TABLE dbpedia ADD INDEX vector_index vector TYPE vector_similarity('hnsw', 'cosineDistance', 1536, 'bf16', 64, 512); | ||
|
|
||
| ALTER TABLE dbpedia MATERIALIZE INDEX vector_index; |
There was a problem hiding this comment.
Can we add SETTINGS mutations_sync = 2 to make sure the index is materialized synchrously?
|
@shankar-iyer Very nice example! |
|
@shankar-iyer Once this PR is in, please also link the new page from the ANN docs page, similar to this PR. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
2 Skipped Deployments
|
3 participants
Summary
Basic, starter dataset for vector search in ClickHouse. More to follow, I will update the parent page after all docs have been pushed.
Checklist