Prompt: Reorganize and improve instructions about working with CrateDB #62
Conversation
WalkthroughThe changes reorganize and refine the CrateDB prompt instructions for improved clarity, technical precision, and structure. Content from the "Things to remember" section was integrated into a new "Details about CrateDB" section, guidelines were expanded, and SQL query rules were clarified. The changelog was updated to reflect these documentation improvements. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Possibly related PRs
Suggested reviewers
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![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
🧹 Nitpick comments (6)
CHANGES.md (1)
4-4: Changelog entry could be more specificConsider explicitly referencing the file path that was re-organized (
src/cratedb_about/prompt/instructions.md) to make the entry self-explanatory when skimming the log months later.- Prompt: Reorganized and improved instructions about working with CrateDB + Prompt (instructions.md): Reorganized and improved the CrateDB prompt instructions for clarity & structuresrc/cratedb_about/prompt/instructions.md (5)
3-4: Italicised sentence looks like a leftover subtitleThe
_Things to remember …_sentence reads like a pre-restructure artefact and doesn’t add information beyond the heading. Removing it keeps the introduction crisp.-_Things to remember when working with CrateDB._
19-28: Minor factual / wording tweaks for technical precision
- Line 19: “in the same way as Elasticsearch is doing it” → Grammarly awkward; drop the comparison clause.
- Line 21: “CrateDB brings together fundamental components to manage big data after the Hadoop and Spark batch-processing era” – subjective and time-bound; suggest focusing on current positioning.
- Line 26: Cloud bullet: “data ingest / ETL utilities” → Plural of “utility” not needed.
- CrateDB is a distributed database written in Java, where individual nodes form a database cluster, using a shared-nothing architecture, in the same way as Elasticsearch is doing it. + CrateDB is a distributed database written in Java; nodes form a shared-nothing cluster. - CrateDB brings together fundamental components to manage big data after the Hadoop and Spark batch-processing era, more like Teradata, BigQuery and Snowflake are doing it. + CrateDB targets interactive analytics on large data sets, similar in spirit to systems such as Teradata, BigQuery, and Snowflake. - CrateDB Cloud offers a managed option for running CrateDB and provides additional features like automated backups, data ingest / ETL utilities, or scheduling recurrent jobs. + CrateDB Cloud is the fully managed service and adds features such as automated backups, ingest/ETL utilities, and scheduled jobs.
32-39: “Remember” bullets partly duplicate & could mergeLines 31–33 both contrast CrateDB with another product. Merging avoids repetition:
- Remember: CrateDB is NOT Elasticsearch - they are different systems - Remember: CrateDB is PostgreSQL wire compatible but NOT PostgreSQL - important differences exist + Remember: CrateDB is NOT Elasticsearch, and while it speaks the PostgreSQL wire protocol it is not PostgreSQL; important differences exist in both cases.
38-38: Replace vague adjective “deep”Static analysis flag is legitimate. “In-depth” conveys the intent more precisely.
- Examine the CrateDB source code when needed for deep technical insights + Examine the CrateDB source code when needed for in-depth technical insights
43-46: Add practical example toDATE_TRUNCguidelineIncluding an idiomatic snippet aids quick copy-paste:
- To filter for a particular date range, apply `DATE_TRUNC` on the timestamp column and use it in the query statement's `WHERE` clause. Do NOT use `DATE_SUB`, it does not exist in CrateDB. Example: ```sql SELECT * FROM my_table WHERE DATE_TRUNC('day', ts) BETWEEN '2025-07-01' AND '2025-07-31';</blockquote></details> </blockquote></details> <details> <summary>📜 Review details</summary> **Configuration used: CodeRabbit UI** **Review profile: CHILL** **Plan: Pro** <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 481111be7452b0d77fb8d3d0153bc3f27e4b43ed and e33d87588ba974b315a4485b49826a98587db985. </details> <details> <summary>📒 Files selected for processing (2)</summary> * `CHANGES.md` (1 hunks) * `src/cratedb_about/prompt/instructions.md` (1 hunks) </details> <details> <summary>🧰 Additional context used</summary> <details> <summary>🧠 Learnings (3)</summary> <details> <summary>📓 Common learnings</summary>Learnt from: amotl
PR: #32
File: src/cratedb_about/outline/cratedb-outline.yaml:321-329
Timestamp: 2025-05-15T21:25:54.870Z
Learning: In the CrateDB outline YAML, content organization prioritizes thematic grouping (keeping related topics together) over content type grouping (separating tutorials from reference docs), as demonstrated by placing the multi-tenancy tutorial alongside user management and privileges documentation in the API section.</details> <details> <summary>CHANGES.md (1)</summary> Learnt from: amotl PR: crate/about#32 File: src/cratedb_about/outline/cratedb-outline.yaml:321-329 Timestamp: 2025-05-15T21:25:54.870Z Learning: In the CrateDB outline YAML, content organization prioritizes thematic grouping (keeping related topics together) over content type grouping (separating tutorials from reference docs), as demonstrated by placing the multi-tenancy tutorial alongside user management and privileges documentation in the API section. </details> <details> <summary>src/cratedb_about/prompt/instructions.md (1)</summary> Learnt from: amotl PR: crate/about#32 File: src/cratedb_about/outline/cratedb-outline.yaml:321-329 Timestamp: 2025-05-15T21:25:54.870Z Learning: In the CrateDB outline YAML, content organization prioritizes thematic grouping (keeping related topics together) over content type grouping (separating tutorials from reference docs), as demonstrated by placing the multi-tenancy tutorial alongside user management and privileges documentation in the API section. </details> </details><details> <summary>🪛 LanguageTool</summary> <details> <summary>src/cratedb_about/prompt/instructions.md</summary> [style] ~38-~38: Consider a different adjective to strengthen your wording. Context: ...the CrateDB source code when needed for deep technical insights ## Rules for writin... (DEEP_PROFOUND) </details> </details> </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
amotl
force-pushed
the
instructions-copy-editing
branch
from
e33d875 to
f13f13f
Compare
amotl
force-pushed
the
instructions-copy-editing
branch
from
401b9a3 to
1bb8451
Compare
| ## Impersonation | ||
|
|
||
| - You are a friendly assistant who processes information from CrateDB and its documentation. | ||
| - Your task is to translate questions into SQL queries, run them on CrateDB, and return results. | ||
| - Try to generate SQL queries based on the known data model and don't ask questions back. | ||
| - You are a CrateDB database engineer, focused on technical level and optimization abilities. | ||
| - Your primary task is to translate questions into accurate CrateDB SQL queries and present the expected result format. | ||
| - Generate queries based on the known data model; if critical information is missing, ask concise follow-up questions rather than guessing. | ||
| - Another responsibility is to discover optimal information from the CrateDB knowledgebase. |
There was a problem hiding this comment.
We are observing a few regressions on MCP use: It looks like the knowledge finding process goes less to the docs, and uses more of internal memory now, which is obviously low on first-class information.
Could this amendment be responsible for that?
About
Iterate a bit on copy-editing after the first version added the other day.