inital commit for yellowhammer jupyter assistant (#3)

* inital commit for yellowhammer jupyter assistant * minor changes for initial commit * minor changes for initial commit * pre-commit update
datalab-org · Oct 25, 2024 · d91f04a · d91f04a
1 parent f3789f6
commit d91f04a
Show file tree

Hide file tree

Showing 13 changed files with 1,199 additions and 138 deletions.
diff --git a/examples/001-getting-started.ipynb b/examples/001-getting-started.ipynb
diff --git a/examples/Demo_anthropic.ipynb b/examples/Demo_anthropic.ipynb
@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2671fc38-c9ca-49ef-948a-abb7815ca2b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%reload_ext yellowhammer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "32c5ffc5-ea83-458c-8e5a-75bb15da8a2d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Enter your LLM API key ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "os.environ[\"LLM_PROVIDER\"] = \"ANTHROPIC\"\n",
+    "os.environ[\"LLM_API_KEY\"] = getpass.getpass(\"Enter your LLM API key\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2f61e78f-b8a3-4f0c-b5e4-503af30019f3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Enter your Datalab API key ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "os.environ[\"DATALAB_API_KEY\"] = getpass.getpass(\"Enter your Datalab API key\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f44cabeb-58ef-4ccd-86d7-5cb04a3f8643",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Datalab is a data management platform designed to help scientists manage their experimental data, plan experiments, analyze data, and plot results. It provides a structured way to store, organize, and interact with scientific data, particularly in the context of materials science and chemistry experiments. \n",
+       "\n",
+       "Some key features of Datalab include:\n",
+       "\n",
+       "1. Sample management: You can create, store, and retrieve information about experimental samples, including their chemical composition, synthesis methods, and related metadata.\n",
+       "\n",
+       "2. File attachments: Datalab allows you to attach files (such as raw data or images) to sample entries, making it easy to keep all relevant information together.\n",
+       "\n",
+       "3. Data blocks: These are used to parse attached files according to scientific schemas and generate plots, facilitating data analysis and visualization.\n",
+       "\n",
+       "4. Search functionality: You can search for items (samples, materials, etc.) across the Datalab instance.\n",
+       "\n",
+       "5. Relationship tracking: Datalab can track relationships between different items, helping to maintain the context of experiments and materials.\n",
+       "\n",
+       "6. API access: Datalab provides a Python API that allows programmatic interaction with the platform, enabling integration with other tools and scripts.\n",
+       "\n",
+       "Datalab is particularly useful for maintaining experimental workflows, ensuring data provenance, and facilitating collaboration among scientists. It helps in organizing complex scientific data in a structured manner, making it easier to retrieve, analyze, and share research findings."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%llm\n",
+    "What is datalab?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "d10442e5-7c5c-40cd-becf-9c2e9a79fd45",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "To create a sample with the specified details using the Datalab API, we'll use the `create_item` method of the `DatalabClient`. Here's what the code will do:\n",
+       "\n",
+       "1. Import the necessary module\n",
+       "2. Create a DatalabClient instance\n",
+       "3. Prepare the sample data as a dictionary\n",
+       "4. Use the create_item method to create the sample\n",
+       "5. Print the response to confirm the sample creation"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%llm\n",
+    "Create a sample with ID llm-test4, sample name \"virtual sample (Claude)\", formula FrCl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "6ef8a1c2-50c8-4807-b84b-008c0bfb4efa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/yue/Library/CloudStorage/OneDrive-Personal/code/yellowhammer/.venv/lib/python3.10/site-packages/datalab_api/_base.py:165: UserWarning: Found API URL https://demo-api.datalab-org.io in HTML meta tag. Creating client with this URL instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Sample creation response:\n",
+      "{'collections': [], 'creator_ids': [{'$oid': '66abc00dcb992f4b299aa60a'}], 'creators': [{'contact_email': None, 'display_name': 'Yue Wu'}], 'date': '2024-10-22T20:06:55.888755', 'item_id': 'llm-test4', 'name': 'virtual sample (Claude)', 'nblocks': 0, 'refcode': 'demo:YASTWQ', 'type': 'samples'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from datalab_api import DatalabClient\n",
+    "\n",
+    "# Create a DatalabClient instance\n",
+    "with DatalabClient(\"https://demo.datalab-org.io\") as client:\n",
+    "    # Prepare the sample data\n",
+    "    sample_data = {\n",
+    "        \"item_id\": \"llm-test4\",\n",
+    "        \"name\": \"virtual sample (Claude)\",\n",
+    "        \"chemform\": \"FrCl\",\n",
+    "        \"type\": \"samples\",\n",
+    "    }\n",
+    "\n",
+    "    # Create the sample\n",
+    "    response = client.create_item(item_id=\"llm-test4\", item_type=\"samples\", item_data=sample_data)\n",
+    "\n",
+    "    # Print the response\n",
+    "    print(\"Sample creation response:\")\n",
+    "    print(response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f3241bc-ba1f-4807-babb-3a928baad6ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "yellowhammer",
+   "language": "python",
+   "name": "yellowhammer"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}