refreshing gradio app to use llama3, migrate to use OpenAI APIs

Author: tmoreau89

recipes/llama_api_providers/OctoAI_API_examples/Llama2_Gradio.ipynb

@@ -5,14 +5,14 @@
    "id": "47a9adb3",
    "metadata": {},
    "source": [
-    "## This demo app shows how to query Llama 2 using the Gradio UI.\n",
+    "## This demo app shows how to query Llama 3 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",
+    "**Note** After the free trial ends, you will need to enter billing info to continue to use Llama 3 hosted on OctoAI.\n",
     "\n",
     "To run this example:\n",
     "- Run the notebook\n",
@@ -22,8 +22,7 @@
     "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",
+    "- openai for us to use its APIs to talk to the OctoAI endpoint\n",
     "- gradio is used for the UI elements\n",
     "\n",
     "And setting up the OctoAI token."
@@ -36,7 +35,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install langchain octoai-sdk gradio"
+    "!pip install openai gradio"
    ]
   },
   {
@@ -60,37 +59,34 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.schema import AIMessage, HumanMessage\n",
     "import gradio as gr\n",
-    "from langchain.llms.octoai_endpoint import OctoAIEndpoint\n",
+    "import openai\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",
+    "# Init OctoAI client\n",
+    "client = openai.OpenAI(\n",
+    "    base_url=\"https://text.octoai.run/v1\",\n",
+    "    api_key=os.environ[\"OCTOAI_API_TOKEN\"]\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",
-    "    llm_response = llm(message, history_langchain_format)\n",
-    "    return llm_response.content\n",
+    "    history_openai_format = []\n",
+    "    for human, assistant in history:\n",
+    "        history_openai_format.append({\"role\": \"user\", \"content\": human})\n",
+    "        history_openai_format.append({\"role\": \"assistant\", \"content\": assistant})\n",
+    "    history_openai_format.append({\"role\": \"user\", \"content\": message})\n",
+    "\n",
+    "    response = client.chat.completions.create(\n",
+    "        model = 'meta-llama-3-70b-instruct',\n",
+    "        messages = history_openai_format,\n",
+    "        temperature = 0.0,\n",
+    "        stream = True\n",
+    "     )\n",
+    "\n",
+    "    partial_message = \"\"\n",
+    "    for chunk in response:\n",
+    "        if chunk.choices[0].delta.content is not None:\n",
+    "              partial_message = partial_message + chunk.choices[0].delta.content\n",
+    "              yield partial_message\n",
     "\n",
     "gr.ChatInterface(predict).launch()"
    ]