mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
135 lines
4.3 KiB
Plaintext
135 lines
4.3 KiB
Plaintext
|
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"attachments": {},
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"# Psychic\n",
|
||
|
"This notebook covers how to load documents from `Psychic`. See [here](../../../../ecosystem/psychic.md) for more details.\n",
|
||
|
"\n",
|
||
|
"## Prerequisites\n",
|
||
|
"1. Follow the Quick Start section in [this document](../../../../ecosystem/psychic.md)\n",
|
||
|
"2. Log into the [Psychic dashboard](https://dashboard.psychic.dev/) and get your secret key\n",
|
||
|
"3. Install the frontend react library into your web app and have a user authenticate a connection. The connection will be created using the connection id that you specify."
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"attachments": {},
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Loading documents\n",
|
||
|
"\n",
|
||
|
"Use the `PsychicLoader` class to load in documents from a connection. Each connection has a connector id (corresponding to the SaaS app that was connected) and a connection id (which you passed in to the frontend library)."
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 7,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"name": "stdout",
|
||
|
"output_type": "stream",
|
||
|
"text": [
|
||
|
"\n",
|
||
|
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.2\u001b[0m\n",
|
||
|
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"# Uncomment this to install psychicapi if you don't already have it installed\n",
|
||
|
"!poetry run pip -q install psychicapi"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"from langchain.document_loaders import PsychicLoader\n",
|
||
|
"from psychicapi import ConnectorId\n",
|
||
|
"\n",
|
||
|
"# Create a document loader for google drive. We can also load from other connectors by setting the connector_id to the appropriate value e.g. ConnectorId.notion.value\n",
|
||
|
"# This loader uses our test credentials\n",
|
||
|
"google_drive_loader = PsychicLoader(\n",
|
||
|
" api_key=\"7ddb61c1-8b6a-4d31-a58e-30d1c9ea480e\",\n",
|
||
|
" connector_id=ConnectorId.gdrive.value,\n",
|
||
|
" connection_id=\"google-test\"\n",
|
||
|
")\n",
|
||
|
"\n",
|
||
|
"documents = google_drive_loader.load()"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"attachments": {},
|
||
|
"cell_type": "markdown",
|
||
|
"metadata": {},
|
||
|
"source": [
|
||
|
"## Converting the docs to embeddings \n",
|
||
|
"\n",
|
||
|
"We can now convert these documents into embeddings and store them in a vector database like Chroma"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||
|
"from langchain.vectorstores import Chroma\n",
|
||
|
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||
|
"from langchain.llms import OpenAI\n",
|
||
|
"from langchain.chains import RetrievalQAWithSourcesChain\n",
|
||
|
"\n"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": [
|
||
|
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||
|
"texts = text_splitter.split_documents(documents)\n",
|
||
|
"\n",
|
||
|
"embeddings = OpenAIEmbeddings()\n",
|
||
|
"docsearch = Chroma.from_documents(texts, embeddings)\n",
|
||
|
"chain = RetrievalQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", retriever=docsearch.as_retriever())\n",
|
||
|
"chain({\"question\": \"what is psychic?\"}, return_only_outputs=True)"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"display_name": "Python 3",
|
||
|
"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": "3.10.8"
|
||
|
},
|
||
|
"orig_nbformat": 4,
|
||
|
"vscode": {
|
||
|
"interpreter": {
|
||
|
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
|
||
|
}
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 2
|
||
|
}
|