Added notebook requirements

lamalab-org · Jun 14, 2024 · 51f52d6 · 51f52d6
1 parent c4e40ab
commit 51f52d6
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 36 deletions.
diff --git a/agents/agent.ipynb b/agents/agent.ipynb
@@ -5,8 +5,6 @@
    "metadata": {},
    "source": [
     "---\n",
-    "author: Martiño Ríos García\n",
-    "date: 2024-05-17\n",
     "title: 5 | Agents\n",
     "keep-ipynb: True\n",
     "include-in-header:\n",
@@ -24,6 +22,15 @@
     "---\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "::: {.callout-caution} \n",
+    "To run this notebook, it is recommended to have access to at least one GPU. With access to a GPU it took less than 5 minutes to run this notebook. The notebook can be run without access to a GPU, but the time will probably increase notably.\n",
+    ":::"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -509,6 +516,24 @@
     "Then we define the prompt, the agent and what it is called by LangChain as the \"chain\".\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import the ReAct prompt from the hub.\n",
+    "prompt = hub.pull(\"hwchase17/react\")\n",
+    "# Construct the ReAct agent\n",
+    "agent = create_react_agent(llm, tools, prompt)\n",
+    "# Define the chain for the agent.\n",
+    "agent_executor = AgentExecutor(\n",
+    "    agent=agent,\n",
+    "    tools=tools,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -538,29 +563,11 @@
     "\n",
     "What are the variables referred in this prompt?\\\n",
     "\n",
-    "- `tools` include all the tools available with the `func`, `name`, `description` and `args_schema` detailed when creating the tool so the model know all the details about the tools.\\\n",
+    "- `tools` is a list with all the tools available. The list includes the `func`, `name`, `description` and `args_schema` arguments detailed when the tools were created.\\\n",
     "- `tool_names` is a list with the names of the tools available.\\\n",
     "- `input`is the query from the user.\\\n",
     "- `agent_scratchpad` contains the previous iterations by the agent.\\\n",
-    ":::\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Import the ReAct prompt from the hub.\n",
-    "prompt = hub.pull(\"hwchase17/react\")\n",
-    "# Construct the ReAct agent\n",
-    "agent = create_react_agent(llm, tools, prompt)\n",
-    "# Define the chain for the agent.\n",
-    "agent_executor = AgentExecutor(\n",
-    "    agent=agent,\n",
-    "    tools=tools,\n",
-    "    verbose=True,\n",
-    ")"
+    ":::"
    ]
   },
   {

diff --git a/finetune/choosing_paradigm.ipynb b/finetune/choosing_paradigm.ipynb
@@ -6,8 +6,6 @@
    "metadata": {},
    "source": [
     "---\n",
-    "author: Martiño Ríos García\n",
-    "date: 2024-05-17\n",
     "title: 4 | Choosing the learning paradigm\n",
     "keep-ipynb: True\n",
     "include-in-header:\n",
@@ -31,7 +29,7 @@
    "metadata": {},
    "source": [
     "::: {.callout-caution}\n",
-    "To run this Notebook, you will need access to at least one GPU. The results that are printed were obtained using a single A100 graphic card with 80 GB of memory. Note that even using such a powerful GPU took the notebook more than 10 hours to complete.\n",
+    "To run this notebook, you will need access to at least one GPU. The results that are printed were obtained using a single A100 graphic card with 80 GB of memory. Note that even using such a powerful GPU took the notebook more than 10 hours to complete.\n",
     ":::"
    ]
   },
@@ -84,19 +82,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "1777e540",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/kevinmaikjablonka/miniconda3/envs/dataextract/lib/python3.8/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import json \n",
     "from dotenv import load_dotenv\n",