adding OctoAI gradio example

demo_apps/OctoAI_API_example/Llama2_Gradio.ipynb

@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "47a9adb3",
+   "metadata": {},
+   "source": [
+    "## This demo app shows how to query Llama 2 using the Gradio UI.\n",
+    "\n",
+    "Since we are using OctoAI in this example, you'll need to obtain an OctoAI token:\n",
+    "\n",
+    "- You will need to first sign into [OctoAI](https://octoai.cloud/) with your Github or Google account\n",
+    "- Then create a free API token [here](https://octo.ai/docs/getting-started/how-to-create-an-octoai-access-token) that you can use for a while (a month or $10 in OctoAI credits, whichever one runs out first)\n",
+    "\n",
+    "**Note** After the free trial ends, you will need to enter billing info to continue to use Llama2 hosted on OctoAI.\n",
+    "\n",
+    "To run this example:\n",
+    "- Run the notebook\n",
+    "- Set up your OCTOAI API token and enter it when prompted\n",
+    "- Enter your question and click Submit\n",
+    "\n",
+    "In the notebook or a browser with URL http://127.0.0.1:7860 you should see a UI with your answer.\n",
+    "\n",
+    "Let's start by installing the necessary packages:\n",
+    "- langchain provides necessary RAG tools for this demo\n",
+    "- octoai-sdk allows us to use OctoAI Llama 2 endpoint\n",
+    "- gradio is used for the UI elements\n",
+    "\n",
+    "And setting up the OctoAI token."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ae4f858-6ef7-49d9-b45b-1ef79d0217a0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install langchain octoai-sdk gradio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3306c11d-ed82-41c5-a381-15fb5c07d307",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from getpass import getpass\n",
+    "import os\n",
+    "\n",
+    "OCTOAI_API_TOKEN = getpass()\n",
+    "os.environ[\"OCTOAI_API_TOKEN\"] = OCTOAI_API_TOKEN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "928041cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema import AIMessage, HumanMessage\n",
+    "import gradio as gr\n",
+    "from langchain.llms.octoai_endpoint import OctoAIEndpoint\n",
+    "\n",
+    "llama2_13b = \"llama-2-13b-chat-fp16\"\n",
+    "\n",
+    "llm = OctoAIEndpoint(\n",
+    "    endpoint_url=\"https://text.octoai.run/v1/chat/completions\",\n",
+    "    model_kwargs={\n",
+    "        \"model\": llama2_13b,\n",
+    "        \"messages\": [\n",
+    "            {\n",
+    "                \"role\": \"system\",\n",
+    "                \"content\": \"You are a helpful, respectful and honest assistant.\"\n",
+    "            }\n",
+    "        ],\n",
+    "        \"max_tokens\": 500,\n",
+    "        \"top_p\": 1,\n",
+    "        \"temperature\": 0.01\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def predict(message, history):\n",
+    "    history_langchain_format = []\n",
+    "    for human, ai in history:\n",
+    "        history_langchain_format.append(HumanMessage(content=human))\n",
+    "        history_langchain_format.append(AIMessage(content=ai))\n",
+    "    history_langchain_format.append(HumanMessage(content=message))\n",
+    "    gpt_response = llm(message) #history_langchain_format)\n",
+    "    return gpt_response#.content\n",
+    "\n",
+    "gr.ChatInterface(predict).launch()"
+   ]
+  }
+ ],
+ "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": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}