Merge pull request #21 from ContextualAI/download-files

Download file from Github

Author: Sean Smith

01-getting-started/end-to-end-example.ipynb

@@ -123,9 +123,9 @@
    "outputs": [],
    "source": [
     "if not os.path.exists('data/Apple.pdf'):\n",
-    "    print(f\"Fetching data/fin_train.jsonl\")\n",
-    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/01-getting-started/data/fin_train.jsonl\")\n",
-    "    with open('data/fin_train.jsonl', 'wb') as f:\n",
+    "    print(f\"Fetching data/Apple.pdf\")\n",
+    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/01-getting-started/data/Apple.pdf\")\n",
+    "    with open('data/Apple.pdf', 'wb') as f:\n",
     "        f.write(response.content)"
    ]
   },
@@ -135,7 +135,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open('Apple.pdf', 'rb') as f:\n",
+    "with open('data/Apple.pdf', 'rb') as f:\n",
     "    ingestion_result = client.datastores.documents.ingest(datastore_id, file=f)\n",
     "    document_id = ingestion_result.id\n",
     "    print(f\"Successfully uploaded to datastore {datastore_id}\")"

02-hands-on-lab/lab1_create_agent.ipynb

@@ -74,6 +74,7 @@
    "outputs": [],
    "source": [
     "import os\n",
+    "import requests\n",
     "from contextual import ContextualAI\n",
     "from IPython.display import display, Markdown"
    ]
@@ -167,6 +168,19 @@
     "I am using a example PDF. You can also use your own documents here. If you have very long documents (hundreds of pages), processing can take longer."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.exists('data/Apple.pdf'):\n",
+    "    print(f\"Fetching data/Apple.pdf\")\n",
+    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/02-hands-on-lab/data/Apple.pdf\")\n",
+    "    with open('data/Apple.pdf', 'wb') as f:\n",
+    "        f.write(response.content)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,

02-hands-on-lab/lab2_evalulate_agent.ipynb

@@ -36,6 +36,7 @@
     "import os\n",
     "import json\n",
     "import ast\n",
+    "import requests\n",
     "import pandas as pd\n",
     "from contextual import ContextualAI"
    ]
@@ -158,6 +159,19 @@
     "Let's start with an evaluation dataset:"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.exists('data/eval_short.csv'):\n",
+    "    print(f\"Fetching data/eval_short.csv\")\n",
+    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/01-hands-on-lab/data/eval_short.csv\")\n",
+    "    with open('data/eval_short.csv', 'wb') as f:\n",
+    "        f.write(response.content)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 23,
@@ -715,6 +729,19 @@
     "- prompt field should be a question or statement that the model should respond to."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.exists('data/fin_train.jsonl'):\n",
+    "    print(f\"Fetching data/fin_train.jsonl\")\n",
+    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/01-hands-on-lab/data/fin_train.jsonl\")\n",
+    "    with open('data/fin_train.jsonl', 'wb') as f:\n",
+    "        f.write(response.content)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -730,13 +757,6 @@
     "!head data/fin_train.jsonl"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {

02-hands-on-lab/lab3_improve_agent.ipynb

@@ -18,6 +18,7 @@
    "outputs": [],
    "source": [
     "import os\n",
+    "import requests\n",
     "from contextual import ContextualAI\n",
     "from IPython.display import display, Markdown"
    ]
@@ -192,6 +193,19 @@
     "Now that you have updated the agent, go try running another evaluation job. You will see the performance has improved."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.exists('data/eval_short.csv'):\n",
+    "    print(f\"Fetching data/eval_short.csv\")\n",
+    "    response = requests.get(\"https://raw.githubusercontent.com/ContextualAI/examples/refs/heads/main/02-hands-on-lab/data/eval_short.csv\")\n",
+    "    with open('data/eval_short.csv', 'wb') as f:\n",
+    "        f.write(response.content)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 28,