| Name | llm-sql-prompt JSON |
| Version |
0.10.0
JSON |
| download |
| home_page | None |
| Summary | Utility to generate ChatGPT prompts for SQL writing, offering table structure snapshots and sample row data from Postgres and sqlite databases. |
| upload_time | 2025-08-29 23:27:43 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | ~=3.11 |
| license | None |
| keywords |
chatgpt
database
llms
postgres
prompt
sql
sqlite
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# ChatGPT Prompt for SQL Writing
Generate a prompt for writing SQL queries with LLMs like ChatGPT. Drop your database URL and table name into the script and it will generate a prompt for you to copy and paste into your favorite LLM.
## What this does
- Snapshot of Table Structure: Understand the columns, types, and organization of your table at a glance.
- Sample Rows: Includes INSERT statements to describe the data in your table.
- Extracts Table and Field Comments: If you have comments on your tables or columns, they will be included in the prompt.
## Usage
Install the package:
```shell
pip install llm-sql-prompt
```
Here's how to use it:
```shell
Usage: llm-sql-prompt [OPTIONS] DATABASE_URL [TABLE_NAME]
Options:
--help Show this message and exit.
```
Generate a prompt from a postgres database:
```shell
llm-sql-prompt postgresql://postgres:postgres@localhost:5555/database_name table_name | pbcopy
llm-sql-prompt $DATABASE_URL
```
From a local sqlite database:
```shell
llm-sql-prompt "$HOME/Library/Application Support/BeeperTexts/index.db" --all
```
### Tunneling to a remote port
If you find yourself wanting to tunnel into a remote box and work with a production database, here's some helpful commands so you don't need to remember the weird SSH tunneling syntax:
```shell
function find_random_open_port() {
local start_port=${1:-1024}
local max_attempts=100
local attempt=0
local port=$start_port
while (( attempt < max_attempts )); do
if ! nc -z localhost $port 2>/dev/null; then
echo $port
return
fi
port=$((port + 1))
attempt=$((attempt + 1))
done
echo "No open port found after $max_attempts attempts, starting from $start_port." > /dev/stderr
return 1
}
function ssh-tunnel() {
if [ $# -lt 2 ]; then
echo "Usage: ssh-tunnel remote_host remote_port [local_port]"
echo "This function sets up SSH port forwarding."
return 1
fi
local remote_host=$1
local remote_port=$2
local local_port=${3:-$(find-random-open-port $remote_port)}
if [[ -z $local_port ]]; then
echo "Failed to find an open local port."
return 1
fi
echo "Forwarding local port $local_port to remote port $remote_port on $remote_host..."
set -x
ssh $remote_host -L ${local_port}:localhost:${remote_port}
}
```
## TODO
Super basic script, needs a lot of work
- [x] pg support
- [x] one entrypoint
- [x] use DB comments on columns + tables
- [x] multiple tables
- [ ] prompt tweaking
- [ ] understand prompt size limits and sample records until one fits
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-sql-prompt",
"maintainer": null,
"docs_url": null,
"requires_python": "~=3.11",
"maintainer_email": null,
"keywords": "chatgpt, database, llms, postgres, prompt, sql, sqlite",
"author": null,
"author_email": "Michael Bianco <mike@mikebian.co>",
"download_url": "https://files.pythonhosted.org/packages/ba/f7/e8928f5171b4caae2b3b9ac58c5b44da80ebb62db069ed0c6f80f44cf3d2/llm_sql_prompt-0.10.0.tar.gz",
"platform": null,
"description": "# ChatGPT Prompt for SQL Writing\n\nGenerate a prompt for writing SQL queries with LLMs like ChatGPT. Drop your database URL and table name into the script and it will generate a prompt for you to copy and paste into your favorite LLM.\n\n## What this does\n\n- Snapshot of Table Structure: Understand the columns, types, and organization of your table at a glance.\n- Sample Rows: Includes INSERT statements to describe the data in your table.\n- Extracts Table and Field Comments: If you have comments on your tables or columns, they will be included in the prompt.\n\n## Usage\n\nInstall the package:\n\n```shell\npip install llm-sql-prompt\n```\n\nHere's how to use it:\n\n```shell\nUsage: llm-sql-prompt [OPTIONS] DATABASE_URL [TABLE_NAME]\n\nOptions:\n --help Show this message and exit.\n```\n\nGenerate a prompt from a postgres database:\n\n```shell\nllm-sql-prompt postgresql://postgres:postgres@localhost:5555/database_name table_name | pbcopy\nllm-sql-prompt $DATABASE_URL\n```\n\nFrom a local sqlite database:\n\n```shell\nllm-sql-prompt \"$HOME/Library/Application Support/BeeperTexts/index.db\" --all\n```\n\n### Tunneling to a remote port\n\nIf you find yourself wanting to tunnel into a remote box and work with a production database, here's some helpful commands so you don't need to remember the weird SSH tunneling syntax:\n\n```shell\nfunction find_random_open_port() {\n local start_port=${1:-1024}\n local max_attempts=100\n local attempt=0\n local port=$start_port\n\n while (( attempt < max_attempts )); do\n if ! nc -z localhost $port 2>/dev/null; then\n echo $port\n return\n fi\n port=$((port + 1))\n attempt=$((attempt + 1))\n done\n\n echo \"No open port found after $max_attempts attempts, starting from $start_port.\" > /dev/stderr\n return 1\n}\n\n\nfunction ssh-tunnel() {\n if [ $# -lt 2 ]; then\n echo \"Usage: ssh-tunnel remote_host remote_port [local_port]\"\n echo \"This function sets up SSH port forwarding.\"\n return 1\n fi\n\n local remote_host=$1\n local remote_port=$2\n local local_port=${3:-$(find-random-open-port $remote_port)}\n\n if [[ -z $local_port ]]; then\n echo \"Failed to find an open local port.\"\n return 1\n fi\n\n echo \"Forwarding local port $local_port to remote port $remote_port on $remote_host...\"\n set -x\n ssh $remote_host -L ${local_port}:localhost:${remote_port}\n}\n```\n\n## TODO\n\nSuper basic script, needs a lot of work\n\n- [x] pg support\n- [x] one entrypoint\n- [x] use DB comments on columns + tables\n- [x] multiple tables\n- [ ] prompt tweaking\n- [ ] understand prompt size limits and sample records until one fits",
"bugtrack_url": null,
"license": null,
"summary": "Utility to generate ChatGPT prompts for SQL writing, offering table structure snapshots and sample row data from Postgres and sqlite databases.",
"version": "0.10.0",
"project_urls": {
"Homepage": "https://pypi.org/project/llm-sql-prompt/"
},
"split_keywords": [
"chatgpt",
" database",
" llms",
" postgres",
" prompt",
" sql",
" sqlite"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "34e7b694733a5144e8d9e3461f2457a045ffe23eb93180d5d1fa30168bff0254",
"md5": "0cf8ae8616ebab482795da652aa55868",
"sha256": "a93ee207f5aa3fe32574a53e9cfbbcca21d1cbba5596c45de1e30e3209597855"
},
"downloads": -1,
"filename": "llm_sql_prompt-0.10.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0cf8ae8616ebab482795da652aa55868",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "~=3.11",
"size": 10820,
"upload_time": "2025-08-29T23:27:42",
"upload_time_iso_8601": "2025-08-29T23:27:42.887102Z",
"url": "https://files.pythonhosted.org/packages/34/e7/b694733a5144e8d9e3461f2457a045ffe23eb93180d5d1fa30168bff0254/llm_sql_prompt-0.10.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "baf7e8928f5171b4caae2b3b9ac58c5b44da80ebb62db069ed0c6f80f44cf3d2",
"md5": "2df4149f3a51263b1a387d1fceb33c8c",
"sha256": "4360da3bea59eaee751dc3b09bf6933def7ce4e270c62fd95307f50637caea8c"
},
"downloads": -1,
"filename": "llm_sql_prompt-0.10.0.tar.gz",
"has_sig": false,
"md5_digest": "2df4149f3a51263b1a387d1fceb33c8c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "~=3.11",
"size": 19226,
"upload_time": "2025-08-29T23:27:43",
"upload_time_iso_8601": "2025-08-29T23:27:43.924249Z",
"url": "https://files.pythonhosted.org/packages/ba/f7/e8928f5171b4caae2b3b9ac58c5b44da80ebb62db069ed0c6f80f44cf3d2/llm_sql_prompt-0.10.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-29 23:27:43",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llm-sql-prompt"
}
