BR-378 - Added note about installing Vectorizer with PEP packages #3
Conversation
📝 WalkthroughWalkthroughThis pull request updates documentation for pgEdge Vectorizer in two files. The index doc is reformatted for line-wrapping and adds two feature bullets: built-in queue and worker monitoring views, and extensive GUC parameters for configuration. The installation doc adds an introductory description of vectorizer behavior and installation options, expands prerequisites to include libcurl4-openssl-dev and pgvector, splits and clarifies clone/build steps (make, sudo make install), adds instructions to create an API key file, and refines postgresql.conf guidance. 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/installation.md`:
- Around line 3-7: Fix the grammatical error in the introductory paragraph by
replacing the phrase "or build from Vectorizer with source code from the" with
"or build Vectorizer from source code from the" so the sentence reads naturally
and clearly; update the text in the same paragraph where pgEdge Vectorizer
installation methods are described.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
docs/index.mddocs/installation.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (5)
docs/index.md (1)
1-75: LGTM!The text reformatting to 79 characters improves readability, and the two new feature bullets (queue/worker monitoring views and GUC parameters) are valuable additions that align with the installation documentation updates.
docs/installation.md (4)
9-13: LGTM!The expanded prerequisites clearly list the required dependencies (libcurl4-openssl-dev and pgvector) for building Vectorizer.
17-30: LGTM!The build instructions are now clearer with separated steps for cloning the repository and building via make commands.
32-37: LGTM!The new section provides clear guidance for creating and securing the API key file, which is essential for the Vectorizer setup.
39-48: LGTM!The postgresql.conf configuration section is now clearer with improved formatting and a more descriptive comment for the databases directive.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
Changed "or build from Vectorizer with source code" to "or build Vectorizer from source code" for clarity. Resolves review comment from @coderabbitai Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
Thanks @susan-pgedge for improving the installation documentation! 🎉 |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@docs/installation.md`:
- Line 47: The comment on the pgedge_vectorizer.databases assignment exceeds the
79-character wrap target; shorten or rephrase the inline comment after
pgedge_vectorizer.databases = 'mydb' so the entire line is ≤79 characters (e.g.,
use a shorter phrase like "# comma-separated DBs" or move the longer explanation
to the next line as a separate wrapped paragraph), ensuring the symbol
pgedge_vectorizer.databases remains unchanged.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/installation.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (3)
docs/installation.md (3)
3-7: Grammatical fix successfully applied!The awkward phrasing has been corrected. Line 6 now reads naturally: "or build Vectorizer from source code from the" instead of the previous "or build from Vectorizer with source code from the".
17-18: LGTM!The clone instruction is properly formatted and wrapped for readability.
39-40: LGTM!The postgresql.conf modification instruction is properly formatted and wrapped for readability.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
| pgedge_vectorizer.api_key_file = '~/.pgedge-vectorizer-llm-api-key' | ||
| pgedge_vectorizer.model = 'text-embedding-3-small' | ||
| pgedge_vectorizer.databases = 'mydb' # Comma-separated list of databases to monitor | ||
| pgedge_vectorizer.databases = 'mydb' # Comma-separated list of monitored databases |
There was a problem hiding this comment.
Line exceeds 79-character wrapping target.
The PR objectives mention wrapping lines to 79 characters, but line 47 is approximately 82 characters long. Consider shortening the comment.
✂️ Proposed fix to meet 79-character limit
-pgedge_vectorizer.databases = 'mydb' # Comma-separated list of monitored databases
+pgedge_vectorizer.databases = 'mydb' # Monitored databases (comma-separated)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| pgedge_vectorizer.databases = 'mydb' # Comma-separated list of monitored databases | |
| pgedge_vectorizer.databases = 'mydb' # Monitored databases (comma-separated) |
🤖 Prompt for AI Agents
In `@docs/installation.md` at line 47, The comment on the
pgedge_vectorizer.databases assignment exceeds the 79-character wrap target;
shorten or rephrase the inline comment after pgedge_vectorizer.databases =
'mydb' so the entire line is ≤79 characters (e.g., use a shorter phrase like "#
comma-separated DBs" or move the longer explanation to the next line as a
separate wrapped paragraph), ensuring the symbol pgedge_vectorizer.databases
remains unchanged.
Also, wrapped installation.md and index.md at 79 characters.