update golden-query notebook and fix typo in golden docs (#8253)

updating the documentation to be consistent for Golden query tool and
have a better introduction to the tool
pull/4403/head^2
Emory Petermann 1 year ago committed by GitHub
parent c14571ab37
commit 7734a2b5ab
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -1,6 +1,6 @@
# Golden
>[Golden](https://golden.com) provides a set of natural language APIs for querying and enrichment using the Golden Knowledge Graph e.g. queries such as: `Products from OpenAI`, `Generative ai companies with series a funding`, and `rappers who invest` can be used to retrieve relevant structured data about relevant entities.
>[Golden](https://golden.com) provides a set of natural language APIs for querying and enrichment using the Golden Knowledge Graph e.g. queries such as: `Products from OpenAI`, `Generative ai companies with series a funding`, and `rappers who invest` can be used to retrieve structured data about relevant entities.
>
>The `golden-query` langchain tool is a wrapper on top of the [Golden Query API](https://docs.golden.com/reference/query-api) which enables programmatic access to these results.
>See the [Golden Query API docs](https://docs.golden.com/reference/query-api) for more information.

@ -1,142 +1,160 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "245a954a",
"metadata": {},
"source": [
"# Golden Query\n",
"\n",
"This notebook goes over how to use the golden-query tool.\n",
"\n",
"- Go to the [Golden API docs](https://docs.golden.com/) to get an overview about the Golden API.\n",
"- Create a Golden account if you don't have one on the [Golden Website](golden.com).\n",
"- Get your API key from the [Golden API Settings](https://golden.com/settings/api) page.\n",
"- Save your API key into GOLDEN_API_KEY env variable"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "34bb5968",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"GOLDEN_API_KEY\"] = \"\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "ac4910f8",
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities.golden_query import GoldenQueryAPIWrapper"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "84b8f773",
"metadata": {},
"outputs": [],
"source": [
"golden_query = GoldenQueryAPIWrapper()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "068991a6",
"metadata": {},
"outputs": [
"cells": [
{
"cell_type": "markdown",
"id": "245a954a",
"metadata": {
"id": "245a954a"
},
"source": [
"# Golden Query\n",
"\n",
">[Golden](https://golden.com) provides a set of natural language APIs for querying and enrichment using the Golden Knowledge Graph e.g. queries such as: `Products from OpenAI`, `Generative ai companies with series a funding`, and `rappers who invest` can be used to retrieve structured data about relevant entities.\n",
">\n",
">The `golden-query` langchain tool is a wrapper on top of the [Golden Query API](https://docs.golden.com/reference/query-api) which enables programmatic access to these results.\n",
">See the [Golden Query API docs](https://docs.golden.com/reference/query-api) for more information.\n",
"\n",
"\n",
"This notebook goes over how to use the `golden-query` tool.\n",
"\n",
"- Go to the [Golden API docs](https://docs.golden.com/) to get an overview about the Golden API.\n",
"- Get your API key from the [Golden API Settings](https://golden.com/settings/api) page.\n",
"- Save your API key into GOLDEN_API_KEY env variable"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "34bb5968",
"metadata": {
"id": "34bb5968"
},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"GOLDEN_API_KEY\"] = \"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac4910f8",
"metadata": {
"id": "ac4910f8"
},
"outputs": [],
"source": [
"from langchain.utilities.golden_query import GoldenQueryAPIWrapper"
]
},
{
"data": {
"text/plain": [
"{'results': [{'id': 4673886,\n",
" 'latestVersionId': 60276991,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Samsung', 'citations': []}]}]},\n",
" {'id': 7008,\n",
" 'latestVersionId': 61087416,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Intel', 'citations': []}]}]},\n",
" {'id': 24193,\n",
" 'latestVersionId': 60274482,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Texas Instruments', 'citations': []}]}]},\n",
" {'id': 1142,\n",
" 'latestVersionId': 61406205,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Advanced Micro Devices', 'citations': []}]}]},\n",
" {'id': 193948,\n",
" 'latestVersionId': 58326582,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Freescale Semiconductor', 'citations': []}]}]},\n",
" {'id': 91316,\n",
" 'latestVersionId': 60387380,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Agilent Technologies', 'citations': []}]}]},\n",
" {'id': 90014,\n",
" 'latestVersionId': 60388078,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Novartis', 'citations': []}]}]},\n",
" {'id': 237458,\n",
" 'latestVersionId': 61406160,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Analog Devices', 'citations': []}]}]},\n",
" {'id': 3941943,\n",
" 'latestVersionId': 60382250,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'AbbVie Inc.', 'citations': []}]}]},\n",
" {'id': 4178762,\n",
" 'latestVersionId': 60542667,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'IBM', 'citations': []}]}]}],\n",
" 'next': 'https://golden.com/api/v2/public/queries/59044/results/?cursor=eyJwb3NpdGlvbiI6IFsxNzYxNiwgIklCTS04M1lQM1oiXX0%3D&pageSize=10',\n",
" 'previous': None}"
"cell_type": "code",
"execution_count": null,
"id": "84b8f773",
"metadata": {
"id": "84b8f773"
},
"outputs": [],
"source": [
"golden_query = GoldenQueryAPIWrapper()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "068991a6",
"metadata": {
"id": "068991a6",
"outputId": "c5cdc6ec-03cf-4084-cc6f-6ae792d91d39"
},
"outputs": [
{
"data": {
"text/plain": [
"{'results': [{'id': 4673886,\n",
" 'latestVersionId': 60276991,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Samsung', 'citations': []}]}]},\n",
" {'id': 7008,\n",
" 'latestVersionId': 61087416,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Intel', 'citations': []}]}]},\n",
" {'id': 24193,\n",
" 'latestVersionId': 60274482,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Texas Instruments', 'citations': []}]}]},\n",
" {'id': 1142,\n",
" 'latestVersionId': 61406205,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Advanced Micro Devices', 'citations': []}]}]},\n",
" {'id': 193948,\n",
" 'latestVersionId': 58326582,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Freescale Semiconductor', 'citations': []}]}]},\n",
" {'id': 91316,\n",
" 'latestVersionId': 60387380,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Agilent Technologies', 'citations': []}]}]},\n",
" {'id': 90014,\n",
" 'latestVersionId': 60388078,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Novartis', 'citations': []}]}]},\n",
" {'id': 237458,\n",
" 'latestVersionId': 61406160,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'Analog Devices', 'citations': []}]}]},\n",
" {'id': 3941943,\n",
" 'latestVersionId': 60382250,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'AbbVie Inc.', 'citations': []}]}]},\n",
" {'id': 4178762,\n",
" 'latestVersionId': 60542667,\n",
" 'properties': [{'predicateId': 'name',\n",
" 'instances': [{'value': 'IBM', 'citations': []}]}]}],\n",
" 'next': 'https://golden.com/api/v2/public/queries/59044/results/?cursor=eyJwb3NpdGlvbiI6IFsxNzYxNiwgIklCTS04M1lQM1oiXX0%3D&pageSize=10',\n",
" 'previous': None}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import json\n",
"\n",
"json.loads(golden_query.run(\"companies in nanotech\"))"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import json\n",
"\n",
"json.loads(golden_query.run(\"companies in nanotech\"))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
},
"vscode": {
"interpreter": {
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
}
},
"colab": {
"provenance": []
}
},
"vscode": {
"interpreter": {
"hash": "53f3bc57609c7a84333bb558594977aa5b4026b1d6070b93987956689e367341"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}
"nbformat": 4,
"nbformat_minor": 5
}
Loading…
Cancel
Save