langchain/docs/docs/integrations/chat_loaders/langsmith_dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a9ab2a39-7c2d-4119-9dc7-8035fdfba3cb",
   "metadata": {},
   "source": [
    "# LangSmith Chat Datasets\n",
    "\n",
    "This notebook demonstrates an easy way to load a LangSmith chat dataset fine-tune a model on that data.\n",
    "The process is simple and comprises 3 steps.\n",
    "\n",
    "1. Create the chat dataset.\n",
    "2. Use the LangSmithDatasetChatLoader to load examples.\n",
    "3. Fine-tune your model.\n",
    "\n",
    "Then you can use the fine-tuned model in your LangChain app.\n",
    "\n",
    "Before diving in, let's install our prerequisites.\n",
    "\n",
    "## Prerequisites\n",
    "\n",
    "Ensure you've installed langchain >= 0.0.311 and have configured your environment with your LangSmith API key."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef488003-514a-48b4-93f1-7de4417abf5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install --upgrade --quiet  langchain langchain-openai"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9fba5c30-9e72-48aa-9535-80f2b3d18ead",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import uuid\n",
    "\n",
    "uid = uuid.uuid4().hex[:6]\n",
    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
    "os.environ[\"LANGCHAIN_API_KEY\"] = \"YOUR API KEY\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8533ab63-d437-492a-aaec-ccca31167bf2",
   "metadata": {},
   "source": [
    "## 1. Select a dataset\n",
    "\n",
    "This notebook fine-tunes a model directly on selecting which runs to fine-tune on. You will often curate these from traced runs. You can learn more about LangSmith datasets in the docs [docs](https://docs.smith.langchain.com/evaluation/concepts#datasets).\n",
    "\n",
    "For the sake of this tutorial, we will upload an existing dataset here that you can use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "462515e0-872a-446e-abbd-6166d73d7414",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langsmith.client import Client\n",
    "\n",
    "client = Client()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d384e4ac-5e8f-42a2-8bb5-7d3c9a8a540d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "url = \"https://raw.githubusercontent.com/langchain-ai/langchain/master/docs/docs/integrations/chat_loaders/example_data/langsmith_chat_dataset.json\"\n",
    "response = requests.get(url)\n",
    "response.raise_for_status()\n",
    "data = response.json()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b0d8ae47-2d3f-4b01-b15f-da58bd750fb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_name = f\"Extraction Fine-tuning Dataset {uid}\"\n",
    "ds = client.create_dataset(dataset_name=dataset_name, data_type=\"chat\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "87f085b7-71e1-4ff4-a622-e4e1248aa94a",
   "metadata": {},
   "outputs": [],
   "source": [
    "_ = client.create_examples(\n",
    "    inputs=[e[\"inputs\"] for e in data],\n",
    "    outputs=[e[\"outputs\"] for e in data],\n",
    "    dataset_id=ds.id,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f365a359-52f7-47ff-8c36-aadc1070b409",
   "metadata": {},
   "source": [
    "## 2. Prepare Data\n",
    "Now we can create an instance of LangSmithRunChatLoader and load the chat sessions using its lazy_load() method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "817bc077-c18a-473b-94a4-a7d810d583a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.chat_loaders.langsmith import LangSmithDatasetChatLoader\n",
    "\n",
    "loader = LangSmithDatasetChatLoader(dataset_name=dataset_name)\n",
    "\n",
    "chat_sessions = loader.lazy_load()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f21a3bbd-1ed4-481b-9640-206b8bf0d751",
   "metadata": {},
   "source": [
    "#### With the chat sessions loaded, convert them into a format suitable for fine-tuning."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "9e5ac127-b094-4584-9159-5a6d3d7315c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.adapters.openai import convert_messages_for_finetuning\n",
    "\n",
    "training_data = convert_messages_for_finetuning(chat_sessions)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "188c4978-d85e-4984-a008-a50f6cd6bb84",
   "metadata": {},
   "source": [
    "## 3. Fine-tune the Model\n",
    "Now, initiate the fine-tuning process using the OpenAI library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "11d19e28-be49-4801-8065-1a58d13cd192",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Status=[running]... 429.55s. 46.34s\r"
     ]
    }
   ],
   "source": [
    "import json\n",
    "import time\n",
    "from io import BytesIO\n",
    "\n",
    "import openai\n",
    "\n",
    "my_file = BytesIO()\n",
    "for dialog in training_data:\n",
    "    my_file.write((json.dumps({\"messages\": dialog}) + \"\\n\").encode(\"utf-8\"))\n",
    "\n",
    "my_file.seek(0)\n",
    "training_file = openai.files.create(file=my_file, purpose=\"fine-tune\")\n",
    "\n",
    "job = openai.fine_tuning.jobs.create(\n",
    "    training_file=training_file.id,\n",
    "    model=\"gpt-3.5-turbo\",\n",
    ")\n",
    "\n",
    "# Wait for the fine-tuning to complete (this may take some time)\n",
    "status = openai.fine_tuning.jobs.retrieve(job.id).status\n",
    "start_time = time.time()\n",
    "while status != \"succeeded\":\n",
    "    print(f\"Status=[{status}]... {time.time() - start_time:.2f}s\", end=\"\\r\", flush=True)\n",
    "    time.sleep(5)\n",
    "    status = openai.fine_tuning.jobs.retrieve(job.id).status\n",
    "\n",
    "# Now your model is fine-tuned!"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54c4cead-500d-41dd-8333-2defde634396",
   "metadata": {},
   "source": [
    "## 4. Use in LangChain\n",
    "\n",
    "After fine-tuning, use the resulting model ID with the ChatOpenAI model class in your LangChain app."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3f472ca4-fa9b-485d-bd37-8ce3c59c44db",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the fine-tuned model ID\n",
    "job = openai.fine_tuning.jobs.retrieve(job.id)\n",
    "model_id = job.fine_tuned_model\n",
    "\n",
    "# Use the fine-tuned model in LangChain\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "model = ChatOpenAI(\n",
    "    model=model_id,\n",
    "    temperature=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "7d3b5845-6385-42d1-9f7d-5ea798dc2cd9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='[{\"s\": \"There were three ravens\", \"object\": \"tree\", \"relation\": \"sat on\"}, {\"s\": \"three ravens\", \"object\": \"a tree\", \"relation\": \"sat on\"}]')"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.invoke(\"There were three ravens sat on a tree.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b8c2c79-ce27-4f37-b1b2-5977db8c4e84",
   "metadata": {},
   "source": [
    "Now you have successfully fine-tuned a model using data from LangSmith LLM runs!"
   ]
  }
 ],
 "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}