rstudio / rstudio/pointblank

Creating an agent on a duckdb table fails interactively

Open
#658 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
R
Stars
1k
Forks
59
Avg merge
25m
Merged PRs (30d)
4

Description

Following on from https://github.com/rstudio/pointblank/pull/642/files/6b0bd4a66c50c8d306d50a78a7394cc6ad740196#r2301596683.

Creating an agent on a duckdb table works when rendering the vignette, fails in interactive use - and works when sending it through reprex() so here is just the code snippet.

library(pointblank)
library(duckdb)

sales <- dplyr::tibble(
  amount = c(100, 200, 300),
  customer_name = c("Alice", "Bianca", "Charlie"),
  sale_date = as.POSIXct(c("2023-01-01", "2023-01-02", "2023-01-03"))
)

con <- dbConnect(duckdb())

dbWriteTable(con, "sales_data", sales)
sales_db <- dplyr::tbl(con, "sales_data")

agent <- create_agent(sales_db) 

dbDisconnect(con)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the reproducible R snippet in the issue and compare creating the agent interactively with the same operation during vignette rendering and through reprex(). Done means create_agent(sales_db) succeeds interactively for a DuckDB-backed table without changing the example's intended setup.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
databases
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.