langchain/templates/rag-pinecone-rerank/rag_pinecone_rerank.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "681a5d1e",
   "metadata": {},
   "source": [
    "## Connect to template"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d774be2a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The agent memory consists of two components: short-term memory and long-term memory. The short-term memory is used for in-context learning and allows the model to learn from its experiences. The long-term memory enables the agent to retain and recall an infinite amount of information over extended periods by leveraging an external vector store and fast retrieval.'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langserve.client import RemoteRunnable\n",
    "\n",
    "rag_app_pinecone = RemoteRunnable(\"http://localhost:8001/rag_pinecone_rerank\")\n",
    "rag_app_pinecone.invoke(\"How does agent memory work?\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}