Update ntbk w/ config

ntbk/testing.ipynb

@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -79,6 +79,13 @@
     "}"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that we can pass any configuration parameters in [configuration.py](../src/enrichment_agent/configuration.py) via `configurable` key in the input."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -90,11 +97,16 @@
     "# Thread\n",
     "thread = await client.threads.create()\n",
     "\n",
+    "# Model \n",
+    "llm = \"anthropic/claude-3-5-sonnet-20240620\"\n",
+    "llm = \"openai/gpt-4o\"\n",
+    "\n",
     "# Stream \n",
     "async for event in client.runs.stream(thread[\"thread_id\"], \n",
     "                                      assistant_id=\"agent\", \n",
     "                                      input={\"topic\": topic,\n",
-    "                                             \"extraction_schema\": schema}, \n",
+    "                                             \"extraction_schema\": schema,\n",
+    "                                             \"configurable\": {\"model_name\":llm}}, \n",
     "                                             stream_mode=\"values\"):\n",
     "    messages = event.data.get('messages', None)\n",
     "    if messages:\n",
@@ -104,7 +116,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -113,7 +125,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -123,16 +135,16 @@
        "# Top 5 Chip Providers for LLM Training\n",
        "\n",
        "## Companies\n",
-       "NVIDIA, AMD, Google, Intel, Apple\n",
+       "Nvidia, AMD, Google, OpenAI, Microsoft, Meta, Amazon, Baidu, Alibaba, Huawei\n",
        "\n",
        "## Key Technologies\n",
-       "GPUs (e.g., NVIDIA A100 and H100), Custom AI chips (e.g., Google TPUs), CPUs optimized for AI workloads\n",
+       "GPUs (particularly Nvidia A100 and H100), TPUs (Google's custom AI chips), Large Language Models (LLMs)\n",
        "\n",
        "## Market Share\n",
-       "NVIDIA dominates with a significant market share in the data center GPU market. While exact percentages are not provided, NVIDIA's data center revenue (primarily from GPU sales for LLM use cases) grew 279% year-over-year to $14.5 billion in Q3 2023, indicating their strong market position.\n",
+       "Nvidia dominates the market, particularly in data center GPUs. In 2023, the top five LLM developers acquired around 88.22% of the market revenue. The global LLM market is projected to grow from $1,590 million in 2023 to $259,800 million in 2030, with a CAGR of 79.80%.\n",
        "\n",
        "## Future Outlook\n",
-       "The LLM market is expected to grow rapidly, with a projected CAGR of 35.9% from 2024 to 2030, reaching $35.43 billion by 2030. Key trends include a focus on data quality, transparency, and legal considerations such as licensing and privacy. Advanced pre-training techniques and the application of LLMs in various industries, including chip design, are expected to drive innovation. The development of more efficient and specialized AI chips is likely to continue, with an emphasis on reducing power consumption and improving performance for LLM training and inference.\n"
+       "The LLM market is expected to experience explosive growth, with projections reaching $35.43 billion by 2030 at a CAGR of 35.9%. Key developments include advanced pre-training techniques, multimodal models like Google's VideoPoet, and a focus on efficiency and specialized models. The industry is also seeing increased investment in AI infrastructure, prompt engineering, and MLOps (Machine Learning Operations) to support the growing demand for AI technologies.\n"
       ],
       "text/plain": [
        "<IPython.core.display.Markdown object>"