Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

community/templates: ClickHouse Template #17247

Closed
wants to merge 12 commits into from

Conversation

mneedham
Copy link
Contributor

@mneedham mneedham commented Feb 8, 2024

Description: A RAG template for ClickHouse. Also has a change to let users pass in index_type as None.
Twitter handle: @markhneedham

@efriis efriis added the template label Feb 8, 2024
@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Feb 8, 2024
@efriis efriis self-assigned this Feb 8, 2024
Copy link

vercel bot commented Feb 8, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
langchain ❌ Failed (Inspect) Mar 29, 2024 3:19am

@dosubot dosubot bot added Ɑ: vector store Related to vector store module 🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features labels Feb 8, 2024
Copy link
Member

@efriis efriis left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks! some comments

templates/rag-clickhouse/README.md Outdated Show resolved Hide resolved
templates/rag-clickhouse/pyproject.toml Outdated Show resolved Hide resolved
@mneedham
Copy link
Contributor Author

thanks! some comments

Thanks - have addressed the comments!

@mneedham
Copy link
Contributor Author

@efriis does it seem ok now?

@kellytoole
Copy link

@efriis gentle nudge on this - any chance we could have eyes on this for a merge? Thank you!

Copy link
Member

@efriis efriis left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey @mneedham ! Two requests:

  • can we split this into 2 PRs, one with upgrades to community implementation, and one with the template (the community implementation needs to be released before the template is usable)
  • in the community PR, could you add some documentation of what these changes do? docstring on _schema
  • some comments below

@@ -72,7 +72,7 @@ class ClickhouseSettings(BaseSettings):
username: Optional[str] = None
password: Optional[str] = None

index_type: str = "annoy"
index_type: Optional[str] = "annoy"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is this supposed to do? I think this will have unintended consequences in some string substitution stuff lower in the file

You'll also need to install ClickHouse:

```bash
curl https://clickhouse.com/ | sh
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this looks kinda wild but looks like you serve that script via curl!


It utilizes Ollama the LLM, GPT4All for embeddings, and ClickHouse for the vectorstore.

The vectorstore is created in `chain.py` and by default indexes a [blog post about feature stores]([https://lilianweng.github.io/posts/2023-06-23-agent/](https://clickhouse.com/blog/powering-featurestores-with-clickhouse)) for question-answering.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

wrong link text

@mneedham
Copy link
Contributor Author

mneedham commented Mar 1, 2024

@efriis I've pulled out the community stuff in this PR - #18381

@efriis
Copy link
Member

efriis commented Apr 6, 2024

Closing until community updates make it in

@efriis efriis closed this Apr 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features size:L This PR changes 100-499 lines, ignoring generated files. template Ɑ: vector store Related to vector store module
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants