minio-langchain-tool/Clean-Poc-Upload-Minio-Agent.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "990e7cef",
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install -q -U minio \"langchain[all]\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "28f213ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "import uuid\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
    "os.environ[\"LANGCHAIN_API_KEY\"] = \"\"\n",
    "os.environ[\"TAVILY_API_KEY\"] = \"\"\n",
    "\n",
    "def _set_if_undefined(var: str):\n",
    "    if not os.environ.get(var):\n",
    "        os.environ[var] = getpass(f\"Please provide your {var}\")\n",
    "\n",
    "\n",
    "_set_if_undefined(\"OPENAI_API_KEY\")\n",
    "_set_if_undefined(\"LANGCHAIN_API_KEY\")\n",
    "_set_if_undefined(\"TAVILY_API_KEY\")\n",
    "\n",
    "# Optional, add tracing in LangSmith.\n",
    "# This will help you visualize and debug the control flow\n",
    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
    "os.environ[\"LANGCHAIN_PROJECT\"] = \"Langchain MinIO Tool\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b2f165fe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Bucket 'test' already exists.\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `upload_file_to_minio` with `{'bucket_name': 'test', 'object_name': 'funny_object.txt', 'data_bytes': 'ZXhhbXBsZSBjb250ZW50Cg=='}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mFile funny_object.txt uploaded successfully to bucket test.\u001b[0m\u001b[32;1m\u001b[1;3mThe object with the funny name 'funny_object.txt' has been successfully uploaded to the 'test' bucket with some example content.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "#from langchain.llms import OpenAI\n",
    "from langchain_openai import ChatOpenAI\n",
    "# Initialize the LLM with your OpenAI API key\n",
    "llm = ChatOpenAI(api_key=\"\")\n",
    "\n",
    "# Necessary imports\n",
    "import io\n",
    "from langchain.agents import tool\n",
    "\n",
    "from minio import Minio\n",
    "from minio.error import S3Error\n",
    "\n",
    "# Initialize MinIO client\n",
    "minio_client = Minio('play.min.io:443',\n",
    "                     access_key='minioadmin',\n",
    "                     secret_key='minioadmin',\n",
    "                     secure=True)\n",
    "\n",
    "# This variable will check if bucket exisits  \n",
    "bucket_name = \"test\"\n",
    "\n",
    "try:\n",
    "    # Check if bucket exists\n",
    "    if not minio_client.bucket_exists(bucket_name):\n",
    "        # Create the bucket because it does not exist\n",
    "        minio_client.make_bucket(bucket_name)\n",
    "        print(f\"Bucket '{bucket_name}' created successfully.\")\n",
    "    else:\n",
    "        print(f\"Bucket '{bucket_name}' already exists.\")\n",
    "except S3Error as err:\n",
    "    print(f\"Error encountered: {err}\")\n",
    "\n",
    "\n",
    "# This is the upload function\n",
    "@tool\n",
    "def upload_file_to_minio(bucket_name: str, object_name: str, data_bytes: bytes):\n",
    "    \"\"\"\n",
    "    Uploads a file to MinIO.\n",
    "    Parameters:\n",
    "        bucket_name (str): The name of the bucket.\n",
    "        object_name (str): The name of the object to create in the bucket.\n",
    "        data_bytes (bytes): The raw bytes of the file to upload.\n",
    "    \"\"\"\n",
    "    data_stream = io.BytesIO(data_bytes)\n",
    "    minio_client.put_object(bucket_name, object_name, data_stream, length=len(data_bytes))\n",
    "    return f\"File {object_name} uploaded successfully to bucket {bucket_name}.\"\n",
    "\n",
    "#### 2. Create RunnableLambda for Upload (if needed for integration)\n",
    "# Depending on the LangChain API's requirements, we might need to wrap the upload function in a RunnableLambda for seamless execution.\n",
    "\n",
    "\n",
    "from langchain_core.runnables import RunnableLambda\n",
    "\n",
    "upload_file_runnable = RunnableLambda(upload_file_to_minio)\n",
    "\n",
    "\n",
    "#### 3. Define Secondary Tool for Example\n",
    "\n",
    "\n",
    "@tool\n",
    "def get_word_length(word: str) -> int:\n",
    "    \"\"\"Returns the length of a word.\"\"\"\n",
    "    return len(word)\n",
    "\n",
    "\n",
    "#### 4. Create Prompt Template\n",
    "# This step involves creating a ChatPromptTemplate that incorporates the MinIO upload tool and any additional tools.\n",
    "\n",
    "\n",
    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
    "\n",
    "prompt = ChatPromptTemplate.from_messages([\n",
    "    (\"system\", \"You are a powerful assistant equipped with file management capabilities.\"),\n",
    "    (\"user\", \"{input}\"),\n",
    "    MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
    "])\n",
    "\n",
    "\n",
    "#### 5. Bind Tools to LLM\n",
    "\n",
    "\n",
    "tools = [upload_file_to_minio, get_word_length]\n",
    "llm_with_tools = llm.bind_tools(tools)\n",
    "\n",
    "\n",
    "#### 6. Create Agent and Executor\n",
    "\n",
    "\n",
    "from langchain.agents import AgentExecutor\n",
    "from langchain.agents.format_scratchpad.openai_tools import format_to_openai_tool_messages\n",
    "from langchain.agents.output_parsers.openai_tools import OpenAIToolsAgentOutputParser\n",
    "\n",
    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
    "\n",
    "\n",
    "#### 7. Add Memory Management\n",
    "# Integrating memory management allows the agent to maintain context across user interactions, enhancing its ability to handle follow-up queries effectively.\n",
    "\n",
    "\n",
    "from langchain_core.messages import AIMessage, HumanMessage\n",
    "\n",
    "# Update the prompt to include memory management\n",
    "\n",
    "prompt = ChatPromptTemplate.from_messages([\n",
    "    (\"system\", \"You are a powerful assistant with memory capabilities.\"),\n",
    "    MessagesPlaceholder(variable_name=\"chat_history\"),\n",
    "    (\"user\", \"{input}\"),\n",
    "    MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
    "])\n",
    "\n",
    "# Initialize chat history\n",
    "\n",
    "chat_history = []\n",
    "\n",
    "# Update agent definition to include chat_history\n",
    "\n",
    "agent = (\n",
    "    {\n",
    "        \"input\": lambda x: x[\"input\"],\n",
    "        \"agent_scratchpad\": lambda x: format_to_openai_tool_messages(x[\"intermediate_steps\"]),\n",
    "        \"chat_history\": lambda x: x[\"chat_history\"],\n",
    "    }\n",
    "    | prompt\n",
    "    | llm_with_tools\n",
    "    | OpenAIToolsAgentOutputParser()\n",
    ")\n",
    "\n",
    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
    "\n",
    "\n",
    "# This structured approach provides a detailed, step-by-step guide to refactoring the MinIO tutorial for integration with LangChain and OpenAI tools, aligning with your preferences for detailed, logical, and technically rich responses.\n",
    "\n",
    "# Prompt and file structure for file upload\n",
    "input1 = \"Upload an object_name with some funny name to the 'test' bucket with some example content\"\n",
    "file_info = {\n",
    "    \"bucket_name\": \"\",\n",
    "    \"object_name\": \"\",\n",
    "    \"data_bytes\": b\"\"\n",
    "}\n",
    "\n",
    "# Simulate the agent executor invoking the MinIO upload tool\n",
    "result = agent_executor.invoke({\"input\": input1, \"chat_history\": chat_history, \"file_info\": file_info})\n",
    "chat_history.extend([\n",
    "    HumanMessage(content=input1),\n",
    "    AIMessage(content=result[\"output\"]),\n",
    "])"
   ]
  }
 ],
 "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}