Add HackerNews dataset for vector search #4378
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@shankar-iyer is attempting to deploy a commit to the ClickHouse Team on Vercel. A member of the Team first needs to authorize it. |
Member
Author
|
Thank you @Blargian for all the help in the last few days to get the content ready! |
Member
Author
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
rschu1ze
approved these changes
Sep 3, 2025
| ## Introduction {#introduction} | ||
|
|
||
| The [Hacker News dataset](https://news.ycombinator.com/) contains 28.74 million | ||
| postings and their vector embeddings. The embeddings were generated using [SentenceTransformers](https://sbert.net/) model [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). The dimension of each embedding vector is `384`. |
Member
There was a problem hiding this comment.
Regarding the dimension: Here, we say the dimension is 384, l. 73 says the dimension is 768.
Blargian
approved these changes
Sep 3, 2025
Member
Blargian
left a comment
Blargian
left a comment
There was a problem hiding this comment.
LGTM. Left a few small formatting suggestions.
|
|
||
| ## Dataset details {#dataset-details} | ||
|
|
||
| The complete dataset with vector embeddings is made available by ClickHouse as a single `Parquet` file in a `S3` bucket : https://clickhouse-datasets.s3.amazonaws.com/hackernews-miniLM/hackernews_part_1_of_1.parquet |
Member
There was a problem hiding this comment.
Suggested change
| The complete dataset with vector embeddings is made available by ClickHouse as a single `Parquet` file in a `S3` bucket : https://clickhouse-datasets.s3.amazonaws.com/hackernews-miniLM/hackernews_part_1_of_1.parquet | |
| The complete dataset with vector embeddings is made available by ClickHouse as a single `Parquet` file in a [`S3` bucket](https://clickhouse-datasets.s3.amazonaws.com/hackernews-miniLM/hackernews_part_1_of_1.parquet) |
| INSERT INTO hackernews SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/hackernews-miniLM/hackernews_part_1_of_1.parquet'); | ||
| ``` | ||
|
|
||
| The loading of 28.74 million rows into the table will take a few minutes. |
Member
There was a problem hiding this comment.
Suggested change
| The loading of 28.74 million rows into the table will take a few minutes. | |
| Inserting 28.74 million rows into the table will take a few minutes. |
|
|
||
| ### Build a vector similarity index {#build-vector-similarity-index} | ||
|
|
||
| Run the following SQL to define and build a vector similarity index on the `vector` column of the `hackernews` table : |
Member
There was a problem hiding this comment.
Suggested change
| Run the following SQL to define and build a vector similarity index on the `vector` column of the `hackernews` table : | |
| Run the following SQL to define and build a vector similarity index on the `vector` column of the `hackernews` table: |
| [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) model. | ||
|
|
||
| An example Python script is provided below to demonstrate how to programmatically generate | ||
| embedding vectors using `sentence_transformers1 Python package. The search embedding vector |
Member
There was a problem hiding this comment.
Suggested change
| embedding vectors using `sentence_transformers1 Python package. The search embedding vector | |
| embedding vectors using the `sentence_transformers1 Python package. The search embedding vector |
| efficiently, gaining popularity for its impressive performance and cost-effectiveness. | ||
| ``` | ||
|
|
||
| Code for above application : |
Member
There was a problem hiding this comment.
Suggested change
| Code for above application : | |
| Code for the above application: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
One more (last!) example for vector search.
Checklist