{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "cd80bc40-f10d-4ab3-826d-6cd0636d11e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from operator import itemgetter\n",
    "\n",
    "from langchain.chat_models import ChatOpenAI, ChatAnthropic\n",
    "from langchain.prompts import SystemMessagePromptTemplate, ChatPromptTemplate\n",
    "from langchain.schema.output_parser import StrOutputParser\n",
    "from langchain.runnables.openai_functions import OpenAIFunctionsRouter\n",
    "\n",
    "from permchain.connection_inmemory import InMemoryPubSubConnection\n",
    "from permchain.pubsub import PubSub\n",
    "from permchain.topic import Topic"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54c553be-9ed1-452c-a4ab-828f34dbb3ce",
   "metadata": {},
   "source": [
    "## Content Fetcher"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56a6788d-b67c-4331-af8d-7741a66f03af",
   "metadata": {},
   "source": [
    "First, we are going to define our content fetcher. This is responsible for taking a search query an getting relevant web pages."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a9c32e92-6f19-4cf1-8b87-1b756de0e263",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.utilities import GoogleSearchAPIWrapper\n",
    "from langchain.document_loaders import AsyncHtmlLoader\n",
    "from langchain.document_transformers import Html2TextTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "89d4a96a-2f59-491f-81fd-4a5d755c0081",
   "metadata": {},
   "outputs": [],
   "source": [
    "from duckduckgo_search import DDGS\n",
    "\n",
    "ddgs = DDGS()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "dcdc3812-0cdc-4677-bf9d-f9d7d5cac7e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def retrieve_documents(query):\n",
    "    query = query.strip().strip('\"')\n",
    "    search_results = ddgs.text(query)\n",
    "    urls_to_look = []\n",
    "    for res in search_results:\n",
    "        if res.get(\"href\", None):\n",
    "            urls_to_look.append(res[\"href\"])\n",
    "        if len(urls_to_look) >= 4:\n",
    "            break\n",
    "\n",
    "    # Relevant urls\n",
    "    # Load, split, and add new urls to vectorstore\n",
    "    if urls_to_look:\n",
    "        loader = AsyncHtmlLoader(urls_to_look)\n",
    "        html2text = Html2TextTransformer()\n",
    "        docs = loader.load()\n",
    "        docs = list(html2text.transform_documents(docs))\n",
    "    else:\n",
    "        docs = []\n",
    "    return docs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "45bb7661-35db-4a67-a62e-9c791c9de359",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nest_asyncio\n",
    "\n",
    "nest_asyncio.apply()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d087d2b4-d1fa-4f63-81de-d3d4e1dc5b1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# docs = retrieve_documents(\"langchain\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73e0b79f-f6bd-4f68-9433-645ee1eea81e",
   "metadata": {},
   "source": [
    "## Summarizer\n",
    "We will now come up with an actor to summarize the results given a query and some search results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "901e1f8d-c973-4998-a731-5dab0c147b8c",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = ChatPromptTemplate.from_template(\n",
    "    \"Answer the user's question given the search results\\n\\n<question>{question}</question><search_results>{search_results}</search_results>\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "915bec33-d210-4471-b051-859ecba608be",
   "metadata": {},
   "outputs": [],
   "source": [
    "summarizer_chain = (\n",
    "    prompt\n",
    "    | ChatOpenAI(max_retries=0).with_fallbacks(\n",
    "        [ChatOpenAI(model=\"gpt-3.5-turbo-16k\"), ChatAnthropic(model=\"claude-2\")]\n",
    "    )\n",
    "    | StrOutputParser()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6bf403ec-39a4-4061-9401-06850ffe3761",
   "metadata": {},
   "source": [
    "## All together now!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "edc0def4-d184-4438-9099-e6604ba9ff28",
   "metadata": {},
   "outputs": [],
   "source": [
    "summarizer_inbox = Topic(\"summarizer\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "23f89611-7b0f-4f01-b9a7-119124e3341d",
   "metadata": {},
   "outputs": [],
   "source": [
    "search_actor = (\n",
    "    Topic.IN.subscribe()\n",
    "    | {\n",
    "        \"search_results\": retrieve_documents,\n",
    "        \"question\": Topic.IN.current(),\n",
    "    }\n",
    "    | summarizer_inbox.publish()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "2d4a6b51-bd93-47c2-a301-9593a47df7d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "summ_actor = (\n",
    "    summarizer_inbox.subscribe() | {\"answer\": summarizer_chain} | Topic.OUT.publish()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "11d3b066-7f95-4ad9-82d0-ba64bbf3e3fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "web_researcher = PubSub(\n",
    "    processes=(search_actor, summ_actor),\n",
    "    connection=InMemoryPubSubConnection(),\n",
    ").with_config(run_name=\"WebResearcher\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "bc022d51-69f0-4da9-8025-70afdc3cc6a8",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Fetching pages: 100%|###################################################| 4/4 [00:01<00:00,  2.19it/s]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'answer': 'LangSmith is a platform built by LangChain to help developers build production-grade language model (LLM) applications. It enables developers to trace and evaluate their LLM applications and intelligent agents, ensuring reliability and maintainability in the production environment. LangSmith integrates seamlessly with LangChain and provides features such as tracing runs, testing, and evaluating prompts or answers generated by LLM applications. It aims to facilitate the development lifecycle, maintenance, and improvement of AI models. For more information, you can refer to the LangSmith documentation.'}]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "web_researcher.invoke(\"What is langsmith?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "000f4f24-15ba-476f-8a33-d023081b18d2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Fetching pages:   0%|                                                           | 0/4 [00:00<?, ?it/s]\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:00<00:00,  6.75it/s]\u001b[A\n",
      "\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:01<00:00,  2.99it/s]\u001b[A\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[[{'answer': 'LangSmith is a platform that helps developers build production-grade language model applications and provides tools for testing, evaluating, and monitoring these applications. It is built by the developers of LangChain and integrates seamlessly with that library. LangSmith aims to address the challenges of moving LLM applications from prototypes to production, ensuring reliability and maintainability. It offers features such as tracing, testing, and evaluating prompts and answers generated by language models. For more information, you can refer to the LangSmith documentation.'}],\n",
       " [{'answer': 'According to the search results, a llama is a domesticated livestock species that is a descendant of the guanaco and belongs to the camel family. Llamas are primarily used as pack animals and a source of food, wool, hides, tallow, and dried dung. They are found in South American countries such as Bolivia, Peru, Colombia, Ecuador, Chile, and Argentina. Llamas are known for their long necks, long legs, small heads, and large pointed ears. They are gregarious animals that graze on grass and other plants. Llamas can interbreed with other lamoid species and produce fertile offspring. On the other hand, alpacas are smaller than llamas, have different face shapes and hair textures, and are primarily used for fleece production.'}]]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "web_researcher.batch([\"what is langsmith\", \"what is llama\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5952e9b8-2a56-4d2d-997a-dceb7652186f",
   "metadata": {},
   "source": [
    "## Trying to use it as a sub component"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "43ca019d-a500-4c77-8e62-a46e54ffae7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "858a82ae-a73f-4da2-9210-298af789ea30",
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"\"\"Write between 2 and 5 sub questions that serve as google search queries to search online that form an objective opinion from the following: {question}\"\"\"\n",
    "functions = [\n",
    "    {\n",
    "        \"name\": \"sub_questions\",\n",
    "        \"description\": \"List of sub questions\",\n",
    "        \"parameters\": {\n",
    "            \"type\": \"object\",\n",
    "            \"properties\": {\n",
    "                \"questions\": {\n",
    "                    \"type\": \"array\",\n",
    "                    \"description\": \"List of sub questions to ask.\",\n",
    "                    \"items\": {\"type\": \"string\"},\n",
    "                },\n",
    "            },\n",
    "        },\n",
    "    },\n",
    "]\n",
    "prompt = ChatPromptTemplate.from_template(template)\n",
    "question_chain = (\n",
    "    prompt\n",
    "    | ChatOpenAI(temperature=0).bind(\n",
    "        functions=functions, function_call={\"name\": \"sub_questions\"}\n",
    "    )\n",
    "    | JsonKeyOutputFunctionsParser(key_name=\"questions\")\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c0298fdc-0e7c-4e79-9cb7-cdd4d50fe88f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['What is the purpose of Langsmith?',\n",
       " 'Who developed Langsmith?',\n",
       " 'What are the features of Langsmith?',\n",
       " 'How does Langsmith work?',\n",
       " 'Are there any alternatives to Langsmith?']"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "question_chain.invoke({\"question\": \"what is langsmith?\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "a0101bd0-cd95-4b13-ab26-d5d34d703bf9",
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"\"\"You are tasked with writing a research report to answer the following question:\n",
    "\n",
    "<question>\n",
    "{question}\n",
    "</question>\n",
    "\n",
    "In order to do that, you first came up with several sub questions and researched those. please find those below:\n",
    "\n",
    "<research>\n",
    "{research}\n",
    "</research>\n",
    "\n",
    "Now, write your final report answering the original question!\"\"\"\n",
    "prompt = ChatPromptTemplate.from_template(template)\n",
    "report_chain = prompt | ChatOpenAI() | StrOutputParser()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "d7715e0c-23c0-4985-97a7-bf5b151cf734",
   "metadata": {},
   "outputs": [],
   "source": [
    "research_inbox = Topic(\"research\")\n",
    "writer_inbox = Topic(\"writer_inbox\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f274027a-c9f0-4efa-b798-1921b9b376d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "subquestion_actor = (\n",
    "    # Listed in inputs\n",
    "    Topic.IN.subscribe()\n",
    "    | question_chain\n",
    "    # The draft always goes to the editors inbox\n",
    "    | research_inbox.publish()\n",
    ")\n",
    "research_actor = (\n",
    "    research_inbox.subscribe()\n",
    "    | {\n",
    "        \"research\": web_researcher.map(),\n",
    "        # \"research\": lambda x: [web_researcher.invoke({\"question\": i}) for i in x],\n",
    "        \"question\": Topic.IN.current() | itemgetter(\"question\"),\n",
    "    }\n",
    "    | writer_inbox.publish()\n",
    ")\n",
    "write_actor = writer_inbox.subscribe() | report_chain | Topic.OUT.publish()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "789b636d-23ce-44fb-a8e3-fdfbfabe77ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "longer_researcher = PubSub(\n",
    "    processes=(subquestion_actor, research_actor, write_actor),\n",
    "    connection=InMemoryPubSubConnection(),\n",
    ").with_config(run_name=\"LongResearcher\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "8f713a31-5f60-4d90-9b95-3f42d8fbbddb",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Fetching pages:   0%|                                                           | 0/4 [00:00<?, ?it/s]\n",
      "Fetching pages:   0%|                                                           | 0/4 [00:00<?, ?it/s]\u001b[A\n",
      "\n",
      "Fetching pages:   0%|                                                           | 0/4 [00:00<?, ?it/s]\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "Fetching pages:   0%|                                                           | 0/4 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:00<00:00,  5.71it/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:00<00:00,  4.80it/s]\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:01<00:00,  2.77it/s]\n",
      "\n",
      "\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:01<00:00,  2.70it/s]\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "\n",
      "Fetching pages: 100%|###################################################| 4/4 [00:03<00:00,  1.22it/s]\u001b[A\u001b[A\u001b[A\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['Research Report: Understanding LangSmith\\n\\nIntroduction:\\nThe purpose of this research report is to explore and provide insights into the topic of LangSmith. LangSmith is a unified platform that aims to address the challenges developers face when building and deploying language model applications in production environments. By examining various sources, we have gathered information to answer the question, \"What is LangSmith?\"\\n\\nFindings:\\n\\n1. LangSmith\\'s Purpose and Features:\\nLangSmith is designed to assist developers in transitioning from prototype to production with their language model applications. It offers a range of features to trace, test, evaluate, and monitor LLM (Large Language Model) calls for production. The platform is part of the LangChain ecosystem and provides reliable and maintainable solutions for language model applications [1].\\n\\n2. Development and Integration:\\nLangSmith was developed by the same team that created LangChain, the popular language model software tool. With a focus on reliability and maintainability, LangSmith seamlessly integrates with LangChain, enabling developers to efficiently build production-grade LLM applications [2].\\n\\n3. Functionalities and Benefits:\\nLangSmith serves as a unified platform for debugging, testing, and monitoring language model applications. It aids developers in prototyping LLM applications and Agents, facilitating customization and iteration on prompts, chains, and other components. Additionally, LangSmith allows for quick debugging of new chains and agents, visualizes component relationships, evaluates prompts and LLMs, and captures usage traces for generating insights. It also provides benchmarking features to evaluate LLM applications [3].\\n\\n4. Availability and Documentation:\\nLangSmith is currently in beta and periodically allows access to new sign-ups. The platform offers documentation and walkthroughs to guide users through its features, making it easier for developers to utilize LangSmith effectively [3].\\n\\n5. Alternatives to LangSmith:\\nBased on our research, we identified several potential alternatives to LangSmith that offer similar functionalities. These alternatives include LangChain, GradientJ, Vellum, Llama 2, Openlayer, Backengine, Query Vary, and BenchLLM. Each alternative provides different tools and features to support the development, testing, and monitoring of language model applications [4].\\n\\nConclusion:\\nLangSmith is a unified platform developed by the creators of LangChain to address the challenges of building and deploying language model applications in production. It offers tracing, testing, evaluating, and monitoring features for LLM applications. By providing documentation and a walkthrough, LangSmith helps developers transition from prototyping to production. However, it is essential to consider alternative platforms based on specific requirements and needs.\\n\\nReferences:\\n1. [1] LangSmith: A unified platform for language model applications. Retrieved from [source 1].\\n2. [2] LangSmith: Tackling challenges in LLM application development. Retrieved from [source 2].\\n3. [3] Exploring the functionalities of LangSmith. Retrieved from [source 3].\\n4. [4] Alternatives to LangSmith. Retrieved from [source 4].\\n\\nPlease note that the sources mentioned above have not been provided and should be replaced with the actual sources used for research.']"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "longer_researcher.invoke({\"question\": \"what is langsmith?\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fde8b227-64ec-4e96-b337-fc888e7ad787",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}