Big moment for Postgres!
@_avichawla78K followers
187,280 views
36 Comments
Comments from the original post on X (Twitter)

@_avichawla
GitHub repo: (don't forget to star it ⭐ )
83 likes

@_avichawla
If you found it insightful, reshare it with your network. Find me → @_avichawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.
4 likes

@akshay_pachaar
One thing worth adding here: the version-aware search is underrated. PG14 and PG17 handle things like JSON operators and identity columns differently. So getting the right docs for your specific version prevents subtle bugs that only show up in production.
13 likes

@Badbrothers__
Can we make this a skill to not fill up my context 😭
11 likes

@jpalomaki
"420% more indexes" - I don't think is a very good metric. More interesting would be to know if it can figure out really good indexes. Like ones where single index serves multiple queries and if it can setup the queries so that they benefit from existing indexes.
8 likes

@ejc3
Try Opus 4.5 without the MCP and see how it does when you specify what version of Postgres to use. Your hypothesis about how these models are trained is incorrect. It’s not just reading stack overflow posts. They get literal experts in the field to evaluate the model’s output to fine tune it.
5 likes

@somi_ai
This pattern extends beyond Postgres. We see the same issue with any rapidly evolving API or framework. Models trained on 2022 docs suggest deprecated patterns for 2024 libraries. MCP servers as domain-specific knowledge injectors is the right architectural fix. Beats fine-tuning because you can version the knowledge separately from the model.
3 likes

@gilbertsahumada
does it work with ORMs? like drizzle or prisma
2 likes

@0xRapid
Timescaledb was here for a long time. One of the best tools in the market atm
2 likes

@Everlier
Good old SQL Chat in Harbor ( worked reasonably well for everything I trrown at it. For more compicated scenarios - coding agents were usually able to debug and fix performance issues granted connection creds (don't worry - never in production)
1 like

@Ithora
As more developers skips stackoverflow and look for answers directly on AI searches this will get worser for all tech not just postgres.
1 like

@HaldankarDeven
@ai_with_gopi this can be replicated for any other framework or tool. For eg. Sqlalchemy, typescript
1 like

@codewithimanshu
Postgres code generation quality shows significant performance variations across models.

@alternatefaraz
Will check must needed

@Itsadreeskhan
Finally AI that respects Postgres history, not just Stack Overflow copy paste.

@duborges
pg17 isnt modern, pg18 is!

@deluxebear
great

@mokshmsharma
This goes beyond simple RAG for raw documentation; it's about injecting expert judgment and evolutionary context directly into the generation process.

@Esteban_Puerta9
Hell yeah this is a very useful one

@connyb
I though the trend last week was that we were deprecating MCP:s in favor of “Skills”















