Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

Fix docs for Rockset (#8807)

Browse Source 
* remove error output for notebook
* add comment about vector length for ingest transformation
* change OPENAI_KEY -> OPENAI_API_KEY

cc @baskaryan
pull/8135/head^2
Kshitij Wadhwa 1 year ago committed by GitHub
parent 983678dedc
commit 5f1aab5487
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 56 deletions
Show Stats Download Patch File Download Diff File

68
docs/extras/integrations/vectorstores/rockset.ipynb
Unescape Escape View File

@ -21,7 +21,10 @@
"\n",
"1. Leverage the `Rockset` console to create a [collection](https://rockset.com/docs/collections/) with the Write API as your source. In this walkthrough, we create a collection named `langchain_demo`. \n",
" \n",
" Configure the following [ingest transformation](https://rockset.com/docs/ingest-transformation/) to mark your embeddings field and take advantage of performance and storage optimizations:"
" Configure the following [ingest transformation](https://rockset.com/docs/ingest-transformation/) to mark your embeddings field and take advantage of performance and storage optimizations:\n",
"\n",
"\n",
" (We used OpenAI `text-embedding-ada-002` for this examples, where #length_of_vector_embedding = 1536)"
]
},
{
@ -75,23 +78,10 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "29505c1e",
"metadata": {},
"outputs": [
{
"ename": "InitializationException",
"evalue": "The rockset client was initialized incorrectly: An api key must be provided as a parameter to the RocksetClient or the Configuration object.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mInitializationException\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[5], line 6\u001b[0m\n\u001b[1;32m 4\u001b[0m ROCKSET_API_KEY \u001b[39m=\u001b[39m os\u001b[39m.\u001b[39menviron\u001b[39m.\u001b[39mget(\u001b[39m\"\u001b[39m\u001b[39mROCKSET_API_KEY\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39m# Verify ROCKSET_API_KEY environment variable\u001b[39;00m\n\u001b[1;32m 5\u001b[0m ROCKSET_API_SERVER \u001b[39m=\u001b[39m rockset\u001b[39m.\u001b[39mRegions\u001b[39m.\u001b[39musw2a1 \u001b[39m# Verify Rockset region\u001b[39;00m\n\u001b[0;32m----> 6\u001b[0m rockset_client \u001b[39m=\u001b[39m rockset\u001b[39m.\u001b[39;49mRocksetClient(ROCKSET_API_SERVER, ROCKSET_API_KEY)\n\u001b[1;32m 8\u001b[0m COLLECTION_NAME\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mlangchain_demo\u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m 9\u001b[0m TEXT_KEY\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mdescription\u001b[39m\u001b[39m'\u001b[39m\n",
"File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/rockset/rockset_client.py:242\u001b[0m, in \u001b[0;36mRocksetClient.__init__\u001b[0;34m(self, host, api_key, max_workers, config)\u001b[0m\n\u001b[1;32m 239\u001b[0m config\u001b[39m.\u001b[39mhost \u001b[39m=\u001b[39m host\n\u001b[1;32m 241\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m config\u001b[39m.\u001b[39mapi_key:\n\u001b[0;32m--> 242\u001b[0m \u001b[39mraise\u001b[39;00m InitializationException(\n\u001b[1;32m 243\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mAn api key must be provided as a parameter to the RocksetClient or the Configuration object.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 244\u001b[0m )\n\u001b[1;32m 246\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mapi_client \u001b[39m=\u001b[39m ApiClient(config, max_workers\u001b[39m=\u001b[39mmax_workers)\n\u001b[1;32m 248\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mAliases \u001b[39m=\u001b[39m AliasesApiWrapper(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mapi_client)\n",
"\u001b[0;31mInitializationException\u001b[0m: The rockset client was initialized incorrectly: An api key must be provided as a parameter to the RocksetClient or the Configuration object."
]
}
],
"outputs": [],
"source": [
"import os\n",
"import rockset\n",
@ -118,18 +108,7 @@
"execution_count": null,
"id": "9740d8c4",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mRunning cells with '/opt/local/bin/python3.11' requires the ipykernel package.\n",
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
"\u001b[1;31mCommand: '/opt/local/bin/python3.11 -m pip install ipykernel -U --user --force-reinstall'"
]
}
],
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
@ -155,20 +134,9 @@
"execution_count": null,
"id": "85b6a6c5",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mRunning cells with '/opt/local/bin/python3.11' requires the ipykernel package.\n",
"\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
"\u001b[1;31mCommand: '/opt/local/bin/python3.11 -m pip install ipykernel -U --user --force-reinstall'"
]
}
],
"outputs": [],
"source": [
"embeddings = OpenAIEmbeddings() # Verify OPENAI_KEY environment variable\n",
"embeddings = OpenAIEmbeddings() # Verify OPENAI_API_KEY environment variable\n",
"\n",
"docsearch = Rockset(\n",
" client=rockset_client,\n",
@ -194,22 +162,10 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "0bbf3df0",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'docsearch' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[1], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m query \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mWhat did the president say about Ketanji Brown Jackson?\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m----> 2\u001b[0m output \u001b[39m=\u001b[39m docsearch\u001b[39m.\u001b[39msimilarity_search_with_relevance_scores(query, \u001b[39m4\u001b[39m, Rockset\u001b[39m.\u001b[39mDistanceFunction\u001b[39m.\u001b[39mCOSINE_SIM)\n\u001b[1;32m 4\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39moutput length:\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39mlen\u001b[39m(output))\n\u001b[1;32m 5\u001b[0m \u001b[39mfor\u001b[39;00m d, dist \u001b[39min\u001b[39;00m output:\n",
"\u001b[0;31mNameError\u001b[0m: name 'docsearch' is not defined"
]
}
],
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"output = docsearch.similarity_search_with_relevance_scores(\n",
@ -313,7 +269,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.6"
"version": "3.10.12"
}
},
"nbformat": 4,

Write Preview
Loading…
Cancel
Save