Merge pull request #1472 from MikeBirdTech/more-cookbooks

More cookbooks

examples/custom_tool.ipynb

@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Add a Custom Tool to your Instance\n",
+    "\n",
+    "You can create custom tools for your instance of Open Interpreter. This is extremely helpful for adding new functionality in a reliable way.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First, create a profile and configure your instance:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configure Open Interpreter\n",
+    "from interpreter import interpreter\n",
+    "\n",
+    "interpreter.llm.model = \"claude-3-5-sonnet-20240620\"\n",
+    "interpreter.computer.import_computer_api = True\n",
+    "interpreter.llm.supports_functions = True\n",
+    "interpreter.llm.supports_vision = True\n",
+    "interpreter.llm.context_window = 100000\n",
+    "interpreter.llm.max_tokens = 4096"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Then you will define your custom tool by writing valid Python code within a comment. This example is for searching the AWS documentation using Perplexity:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "custom_tool = \"\"\"\n",
+    "\n",
+    "import os\n",
+    "import requests\n",
+    "\n",
+    "def search_aws_docs(query):\n",
+    "\n",
+    "    url = \"https://api.perplexity.ai/chat/completions\"\n",
+    "\n",
+    "    payload = {\n",
+    "        \"model\": \"llama-3.1-sonar-small-128k-online\",\n",
+    "        \"messages\": [\n",
+    "            {\n",
+    "                \"role\": \"system\",\n",
+    "                \"content\": \"Be precise and concise.\"\n",
+    "            },\n",
+    "            {\n",
+    "                \"role\": \"user\",\n",
+    "                \"content\": query\n",
+    "            }\n",
+    "        ],\n",
+    "        \"temperature\": 0.2,\n",
+    "        \"top_p\": 0.9,\n",
+    "        \"return_citations\": True,\n",
+    "        \"search_domain_filter\": [\"docs.aws.amazon.com\"],\n",
+    "        \"return_images\": False,\n",
+    "        \"return_related_questions\": False,\n",
+    "        #\"search_recency_filter\": \"month\",\n",
+    "        \"top_k\": 0,\n",
+    "        \"stream\": False,\n",
+    "        \"presence_penalty\": 0,\n",
+    "        \"frequency_penalty\": 1\n",
+    "    }\n",
+    "    headers = {\n",
+    "        \"Authorization\": f\"Bearer {os.environ.get('PPLX_API_KEY')}\",\n",
+    "        \"Content-Type\": \"application/json\"\n",
+    "    }\n",
+    "\n",
+    "    response = requests.request(\"POST\", url, json=payload, headers=headers)\n",
+    "\n",
+    "    print(response.text)\n",
+    "\n",
+    "    return response.text\n",
+    "\n",
+    "\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Finally, you add the tool to the OI instance's computer:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "interpreter.computer.run(\"python\", custom_tool)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> Note: You can define and set multiple tools in a single instance."
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/jan_computer_control.ipynb

@@ -0,0 +1,73 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Jan Computer Control\n",
+    "\n",
+    "We love Jan as an A.I. inference server. It also has a chat interface to chat with LLMs. But did you know that you can use this same chat interface as a computer control interface? Read on!\n",
+    "\n",
+    "[View on YouTube](https://www.youtube.com/watch?v=1l3B0AzbbjQ)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install and set up Jan\n",
+    "\n",
+    "https://jan.ai/"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install Open Interpreter\n",
+    "\n",
+    "https://docs.openinterpreter.com/getting-started/introduction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Run the Open Interpreter OpenAI-compatible server.\n",
+    "\n",
+    "`interpreter --server`\n",
+    "\n",
+    "Add flags to set the `--model`, `--context_window`, or any other [setting](https://docs.openinterpreter.com/settings/all-settings) you want"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Edit Jan's OpenAI settings to point to the local server.\n",
+    "\n",
+    "Settings => OpenAI => Chat Competion endpoint `http://127.0.0.1:8000/openai/chat/completions`.\n",
+    "\n",
+    "Jan has a requirement to set a dummy OpenAI API key."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Go to Jan's chat window to start a new thread.\n",
+    "\n",
+    "Set `Model` to an OpenAI model. \n",
+    "\n",
+    "Start controlling your computer!"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/organize_photos.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Organize your photos with Open Interpreter"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can use Open Interpreter with a vision model to organize photos based on their contents. This is limited by the ability of the LLM as well as the organization of the directories storing photos.  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> Note: It is always recommended to back up photos and files on a regular basis. Most models are intelligent enough to know the difference between `move` and `delete` but on rare occasions, files can be deleted during some operations. It is important to test on duplicated photos and to keep an eye on code written by an LLM."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a profile. This example uses GPT-4o but you can use any vision model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"\n",
+    "This is an Open Interpreter profile to organize a directory of photos. \n",
+    "\"\"\"\n",
+    "\n",
+    "from interpreter import interpreter\n",
+    "\n",
+    "\n",
+    "# LLM settings\n",
+    "interpreter.llm.model = \"gpt-4o\"\n",
+    "#interpreter.llm.model = \"ollama/codestral\"\n",
+    "interpreter.llm.supports_vision = True\n",
+    "interpreter.llm.execution_instructions = False\n",
+    "interpreter.llm.max_tokens = 1000\n",
+    "interpreter.llm.context_window = 7000\n",
+    "interpreter.llm.load()  # Loads Ollama models\n",
+    "\n",
+    "# Computer settings\n",
+    "interpreter.computer.import_computer_api = True\n",
+    "\n",
+    "# Misc settings\n",
+    "interpreter.auto_run = False\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The following custom instruction is intended for a directory containing one sub-directory of unorganized photos and multiple empty sub-directories with names for the intended organization. Please update the custom instructions to match your use-case. This will take some trial and error, depending on the model used."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Custom Instructions\n",
+    "interpreter.custom_instructions=f\"\"\"\n",
+    "    Recap the plan before answering the user's query!\n",
+    "    Your job is to organize photos. You love organizing photos.\n",
+    "    You will be given a parent directory with sub-directories. \n",
+    "    One sub-directory will be of unorganized photos.\n",
+    "    The other sub-directories will be categories that you move the photos in to.\n",
+    "    Remember the sub-directories's names because they will be the categories for organizing.\n",
+    "    It is extremely important because these are the only options for where you move the photos.\n",
+    "    Loop through every photo in the unorganized photos directory. \n",
+    "    Skip over non-photo files by checking for common photo extensions (.jpg, .jpeg, .png, etc).\n",
+    "    In this loop you will determine the description of each image one at a time. \n",
+    "    Use `computer.vision.query()` to get a description of the image.\n",
+    "    `computer.vision.query()` takes a `path=` argument to know which photo to describe. \n",
+    "    Print out the description so you can get the full context.\n",
+    "    Determine which sub-directory the photo should go in to.\n",
+    "    Every photo needs to go into one of the sub-directories.\n",
+    "    Make sure you actually move the photo. \n",
+    "    Your task is done when every photo in the unorganized photos directory has been moved to another directory. \n",
+    "    **Confirm that the unorganized photos directory has no more photos**.\n",
+    "    \"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Save the profile with a descriptive name. Then run interpreter with:\n",
+    "\n",
+    "`interpreter --profile <profileName.py>`\n",
+    "\n",
+    "Then ask it to organize the directory:\n",
+    "\n",
+    "`Please organize this directory: /path/to/directory`"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}