Merge pull request #162 from cloudnautique/main

add python example

Author: cloudnautique

docs/README-USECASES.md

@@ -82,6 +82,10 @@ Here is a GPTScript that performs sentiment analysis on the input text: [Social
 
 Here is a GPTScript that reads the content of a CSV file and make query using natural language: [csv-reader.gpt](https://github.com/gptscript-ai/csv-reader/blob/main/examples/csv-reader.gpt)
 
+### JSON Files
+
+Here is a GPTScript that uses the Python module to query JSON data in a jupyter notebook: [json-notebook](../examples/json-notebook)
+
 ### Understanding Code
 
 Here is a GPTScript that summarizes the code stored under the current directory: [`describe-code.gpt`](../examples/describe-code.gpt)

examples/json-notebook/README.md

@@ -0,0 +1,24 @@
+# JSON Query tool and Jupyter Notebook
+
+This is a simple example of how to use the JSON Query tool in Jupyter Notebook, along with the gptscript python module.
+
+## Prerequisites
+
+You will need to set the OPENAI_API_KEY environment variable with your OpenAI key in the shell you start the notebook from.
+
+## Running the notebook
+
+Open the notebook, it will install both gptscript when possible and download a dataset and query it using the json-query tool.
+
+## Example
+
+```bash
+# Create a Python venv
+python3 -m venv venv
+. ./venv/bin/activate
+pip install jupyter ipykernel
+python -m ipykernel install --user --name=venv
+jupyter notebook
+```
+
+Once the notebook is open, make sure you are using the venv kernel and run the cells.

examples/json-notebook/json-query.ipynb

@@ -0,0 +1,59 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98d5cd09-dfe4-4bbe-b1ba-344a535fa763",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pip install gptscript"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "144cb0f4-7936-4701-9246-e948c09f94c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from gptscript.command import stream_exec\n",
+    "from gptscript.tool import Tool\n",
+    "\n",
+    "t = Tool(tools=[\"github.com/gptscript-ai/json-query\",\"sys.download\",\"sys.read\"],\n",
+    "         instructions=\"\"\"\n",
+    "download the contents from this url https://data.transportation.gov/api/views/anj8-k6f5/rows.json?accessType=DOWNLOAD and save to file ai-usecases.json\n",
+    "Wait until the file is downloaded before proceeding.\n",
+    "Using the downloaded file, determine which agencies have AI initiatives and list a summary of each.\n",
+    "\"\"\",\n",
+    "        )\n",
+    "\n",
+    "results, err, wait = stream_exec(t)\n",
+    "for line in err:\n",
+    "    print(line)\n",
+    "print(results.read())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}