docs: add use cases tutorials for AI workflows #392
Conversation
|
How to use the Graphite Merge QueueAdd either label to this PR to merge it via the merge queue:
You must have a Graphite account in order to use the merge queue. Sign up using this link. An organization admin has enabled the Graphite Merge Queue in this repository. Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue. This stack of pull requests is managed by Graphite. Learn more about stacking. |
|
View your CI Pipeline Execution ↗ for commit 62aac2a
☁️ Nx Cloud last updated this comment at |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| @@ -0,0 +1 @@ | |||
| /home/jumski/Code/pgflow-dev/claude/source/CLAUDE.md No newline at end of file | |||
There was a problem hiding this comment.
CLAUDE.md is committed as a symlink to /home/jumski/Code/pgflow-dev/claude/source/CLAUDE.md, which only exists on the author’s machine. In any other checkout the target is missing, leaving the doc unreadable and leaking a local path, so any process expecting this file will fail; the link should be made relative or the actual content checked in.
Useful? React with 👍 / 👎.
| -- Create index for faster similarity search | ||
| create index on documents using ivfflat (embedding vector_cosine_ops); |
There was a problem hiding this comment.
The RAG pipeline schema creates an IVFFLAT index without specifying the required WITH (lists = ...) option (create index on documents using ivfflat (embedding vector_cosine_ops);). pgvector rejects this statement with “missing required parameter lists”, so running the migration as written will fail and the tutorial cannot be followed until a list count is provided.
Useful? React with 👍 / 👎.
| ); | ||
|
|
||
| create index on knowledge_base using ivfflat (embedding vector_cosine_ops); |
There was a problem hiding this comment.
The chatbot schema also creates an IVFFLAT index without the mandatory WITH (lists = ...) parameter (create index on knowledge_base using ivfflat ...). PostgreSQL/pgvector will error with “missing required parameter lists”, preventing users from applying the migration or running the tutorial; the index needs an explicit list count.
Useful? React with 👍 / 👎.
jumski
force-pushed
the
claude/add-use-cases-tutorials-011CUrzyLUcAZQ8EY4BCi1eC
branch
from
843cc1b to
9750eff
Compare
Add new tutorial section covering common AI patterns: - Automatic embeddings with database triggers - Structured output using Zod schemas - RAG pipeline with query transformation and reranking - Chatbot with parallel history and knowledge retrieval All tutorials demonstrate proper pgflow DSL patterns with factual, working examples using AI SDK and standard libraries.
jumski
force-pushed
the
claude/add-use-cases-tutorials-011CUrzyLUcAZQ8EY4BCi1eC
branch
from
9750eff to
62aac2a
Compare
🔍 Preview Deployment: Website✅ Deployment successful! 🔗 Preview URL: https://pr-392.pgflow.pages.dev 📝 Details:
_Last updated: _ |
Add new tutorial section covering common AI patterns:
All tutorials demonstrate proper pgflow DSL patterns with
factual, working examples using AI SDK and standard libraries.