Skip to content

Commit 2ba8883

Browse files
umarbutlerumarbutler
committed
docs: add example notebook
1 parent d95bc48 commit 2ba8883

File tree

1 file changed

+213
-0
lines changed

1 file changed

+213
-0
lines changed

‎docs/embeddings.ipynb‎

Lines changed: 213 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,213 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": null,
6+
"id": "58d4d40a",
7+
"metadata": {},
8+
"outputs": [
9+
{
10+
"name": "stdout",
11+
"output_type": "stream",
12+
"text": [
13+
"Defaulting to user installation because normal site-packages is not writeable\n",
14+
"Collecting isaacus\n",
15+
" Downloading isaacus-0.9.1-py3-none-any.whl.metadata (15 kB)\n",
16+
"Collecting isaacus-sagemaker\n",
17+
" Downloading isaacus_sagemaker-0.1.2-py3-none-any.whl.metadata (9.8 kB)\n",
18+
"Requirement already satisfied: anyio<5,>=3.5.0 in /usr/lib/python3/dist-packages (from isaacus) (4.2.0)\n",
19+
"Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from isaacus) (1.9.0)\n",
20+
"Collecting httpx<1,>=0.23.0 (from isaacus)\n",
21+
" Downloading httpx-0.28.1-py3-none-any.whl.metadata (7.1 kB)\n",
22+
"Requirement already satisfied: pydantic<3,>=1.9.0 in /usr/lib/python3/dist-packages (from isaacus) (1.10.14)\n",
23+
"Requirement already satisfied: sniffio in /usr/lib/python3/dist-packages (from isaacus) (1.3.0)\n",
24+
"Requirement already satisfied: typing-extensions<5,>=4.10 in /usr/lib/python3/dist-packages (from isaacus) (4.10.0)\n",
25+
"Collecting boto3>=1.40.49 (from isaacus-sagemaker)\n",
26+
" Downloading boto3-1.40.59-py3-none-any.whl.metadata (6.6 kB)\n",
27+
"Collecting msgspec>=0.19.0 (from isaacus-sagemaker)\n",
28+
" Downloading msgspec-0.19.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.9 kB)\n",
29+
"Collecting orjson>=3.11.4 (from isaacus-sagemaker)\n",
30+
" Downloading orjson-3.11.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (41 kB)\n",
31+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.8/41.8 kB\u001b[0m \u001b[31m14.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
32+
"\u001b[?25hCollecting pytest-asyncio>=1.2.0 (from isaacus-sagemaker)\n",
33+
" Downloading pytest_asyncio-1.2.0-py3-none-any.whl.metadata (4.1 kB)\n",
34+
"Collecting pytest>=8.4.2 (from isaacus-sagemaker)\n",
35+
" Downloading pytest-8.4.2-py3-none-any.whl.metadata (7.7 kB)\n",
36+
"Requirement already satisfied: idna>=2.8 in /usr/lib/python3/dist-packages (from anyio<5,>=3.5.0->isaacus) (3.6)\n",
37+
"Collecting botocore<1.41.0,>=1.40.59 (from boto3>=1.40.49->isaacus-sagemaker)\n",
38+
" Downloading botocore-1.40.59-py3-none-any.whl.metadata (5.7 kB)\n",
39+
"Collecting jmespath<2.0.0,>=0.7.1 (from boto3>=1.40.49->isaacus-sagemaker)\n",
40+
" Downloading jmespath-1.0.1-py3-none-any.whl.metadata (7.6 kB)\n",
41+
"Collecting s3transfer<0.15.0,>=0.14.0 (from boto3>=1.40.49->isaacus-sagemaker)\n",
42+
" Downloading s3transfer-0.14.0-py3-none-any.whl.metadata (1.7 kB)\n",
43+
"Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx<1,>=0.23.0->isaacus) (2023.11.17)\n",
44+
"Collecting httpcore==1.* (from httpx<1,>=0.23.0->isaacus)\n",
45+
" Downloading httpcore-1.0.9-py3-none-any.whl.metadata (21 kB)\n",
46+
"Collecting h11>=0.16 (from httpcore==1.*->httpx<1,>=0.23.0->isaacus)\n",
47+
" Downloading h11-0.16.0-py3-none-any.whl.metadata (8.3 kB)\n",
48+
"Collecting iniconfig>=1 (from pytest>=8.4.2->isaacus-sagemaker)\n",
49+
" Downloading iniconfig-2.3.0-py3-none-any.whl.metadata (2.5 kB)\n",
50+
"Requirement already satisfied: packaging>=20 in /usr/lib/python3/dist-packages (from pytest>=8.4.2->isaacus-sagemaker) (24.0)\n",
51+
"Collecting pluggy<2,>=1.5 (from pytest>=8.4.2->isaacus-sagemaker)\n",
52+
" Downloading pluggy-1.6.0-py3-none-any.whl.metadata (4.8 kB)\n",
53+
"Requirement already satisfied: pygments>=2.7.2 in /usr/lib/python3/dist-packages (from pytest>=8.4.2->isaacus-sagemaker) (2.17.2)\n",
54+
"Collecting typing-extensions<5,>=4.10 (from isaacus)\n",
55+
" Downloading typing_extensions-4.15.0-py3-none-any.whl.metadata (3.3 kB)\n",
56+
"Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /usr/lib/python3/dist-packages (from botocore<1.41.0,>=1.40.59->boto3>=1.40.49->isaacus-sagemaker) (2.8.2)\n",
57+
"Requirement already satisfied: urllib3!=2.2.0,<3,>=1.25.4 in /usr/lib/python3/dist-packages (from botocore<1.41.0,>=1.40.59->boto3>=1.40.49->isaacus-sagemaker) (2.0.7)\n",
58+
"Downloading isaacus-0.9.1-py3-none-any.whl (90 kB)\n",
59+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.9/90.9 kB\u001b[0m \u001b[31m56.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
60+
"\u001b[?25hDownloading isaacus_sagemaker-0.1.2-py3-none-any.whl (9.9 kB)\n",
61+
"Downloading boto3-1.40.59-py3-none-any.whl (139 kB)\n",
62+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m139.3/139.3 kB\u001b[0m \u001b[31m85.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
63+
"\u001b[?25hDownloading httpx-0.28.1-py3-none-any.whl (73 kB)\n",
64+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.5/73.5 kB\u001b[0m \u001b[31m46.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
65+
"\u001b[?25hDownloading httpcore-1.0.9-py3-none-any.whl (78 kB)\n",
66+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.8/78.8 kB\u001b[0m \u001b[31m33.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
67+
"\u001b[?25hDownloading msgspec-0.19.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (213 kB)\n",
68+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m213.6/213.6 kB\u001b[0m \u001b[31m45.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
69+
"\u001b[?25hDownloading orjson-3.11.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (136 kB)\n",
70+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m136.3/136.3 kB\u001b[0m \u001b[31m60.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
71+
"\u001b[?25hDownloading pytest-8.4.2-py3-none-any.whl (365 kB)\n",
72+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m365.8/365.8 kB\u001b[0m \u001b[31m160.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
73+
"\u001b[?25hDownloading pytest_asyncio-1.2.0-py3-none-any.whl (15 kB)\n",
74+
"Downloading typing_extensions-4.15.0-py3-none-any.whl (44 kB)\n",
75+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m37.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
76+
"\u001b[?25hDownloading botocore-1.40.59-py3-none-any.whl (14.1 MB)\n",
77+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m168.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:01\u001b[0m\n",
78+
"\u001b[?25hDownloading iniconfig-2.3.0-py3-none-any.whl (7.5 kB)\n",
79+
"Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)\n",
80+
"Downloading pluggy-1.6.0-py3-none-any.whl (20 kB)\n",
81+
"Downloading s3transfer-0.14.0-py3-none-any.whl (85 kB)\n",
82+
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.7/85.7 kB\u001b[0m \u001b[31m69.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
83+
"\u001b[?25hDownloading h11-0.16.0-py3-none-any.whl (37 kB)\n",
84+
"Installing collected packages: typing-extensions, pluggy, orjson, msgspec, jmespath, iniconfig, h11, pytest, httpcore, botocore, s3transfer, pytest-asyncio, httpx, isaacus, boto3, isaacus-sagemaker\n",
85+
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
86+
"fastapi 0.101.0 requires starlette<0.28.0,>=0.27.0, but you have starlette 0.31.1 which is incompatible.\u001b[0m\u001b[31m\n",
87+
"\u001b[0mSuccessfully installed boto3-1.40.59 botocore-1.40.59 h11-0.16.0 httpcore-1.0.9 httpx-0.28.1 iniconfig-2.3.0 isaacus-0.9.1 isaacus-sagemaker-0.1.2 jmespath-1.0.1 msgspec-0.19.0 orjson-3.11.4 pluggy-1.6.0 pytest-8.4.2 pytest-asyncio-1.2.0 s3transfer-0.14.0 typing-extensions-4.15.0\n"
88+
]
89+
}
90+
],
91+
"source": [
92+
"# Install the Isaacus SDK and Isaacus SageMaker Python integration.\n",
93+
"!pip install isaacus isaacus-sagemaker\n",
94+
"\n",
95+
"# Install optional dependencies necessary for this example (`httpx` and `numpy`).\n",
96+
"!pip install httpx numpy"
97+
]
98+
},
99+
{
100+
"cell_type": "code",
101+
"execution_count": null,
102+
"id": "d5cf275c",
103+
"metadata": {},
104+
"outputs": [],
105+
"source": [
106+
"from isaacus import Isaacus, AsyncIsaacus\n",
107+
"from isaacus_sagemaker import IsaacusSageMakerRuntimeHTTPClient, AsyncIsaacusSageMakerRuntimeHTTPClient, \\\n",
108+
" IsaacusSageMakerRuntimeEndpoint\n",
109+
"\n",
110+
"# NOTE This assumes you have already purchased Kanon 2 Embedder and set up an endpoint.\n",
111+
"endpoints = [\n",
112+
" IsaacusSageMakerRuntimeEndpoint(\n",
113+
" name=\"my-sagemaker-endpoint\",\n",
114+
" # region=\"us-west-2\", # Optional, defaults to the client or AWS SDK default region\n",
115+
" # profile=\"my-aws-profile\", # Optional, defaults to the client or AWS SDK default profile\n",
116+
" # models=[\"kanon-2-embedder\"], # Optional, models supported by this endpoint,\n",
117+
" # # defaults to all models\n",
118+
" )\n",
119+
"]\n",
120+
"\n",
121+
"client = Isaacus(\n",
122+
" http_client=IsaacusSageMakerRuntimeHTTPClient(\n",
123+
" endpoints=endpoints,\n",
124+
" # region=\"us-west-2\", # Optional, defaults to AWS SDK default region\n",
125+
" # profile=\"my-aws-profile\", # Optional, defaults to AWS SDK default profile\n",
126+
" # boto_session_kwargs={\"aws_access_key_id\": \"...\",}, # Optional, additional boto3 session kwargs\n",
127+
" # **{}, # Optional, additional httpx.Client kwargs\n",
128+
" )\n",
129+
")\n",
130+
"\n",
131+
"# For asynchronous usage:\n",
132+
"aclient = AsyncIsaacus(\n",
133+
" http_client=AsyncIsaacusSageMakerRuntimeHTTPClient(\n",
134+
" endpoints=endpoints,\n",
135+
" # region=\"us-west-2\", # Optional, defaults to AWS SDK default region\n",
136+
" # profile=\"my-aws-profile\", # Optional, defaults to AWS SDK default profile\n",
137+
" # boto_session_kwargs={\"aws_access_key_id\": \"...\",}, # Optional, additional boto3 session kwargs\n",
138+
" # **{}, # Optional, additional httpx.AsyncClient kwargs\n",
139+
" )\n",
140+
")"
141+
]
142+
},
143+
{
144+
"cell_type": "code",
145+
"execution_count": null,
146+
"id": "87b1a88c",
147+
"metadata": {},
148+
"outputs": [],
149+
"source": [
150+
"import httpx\n",
151+
"import numpy as np\n",
152+
"\n",
153+
"# Download the GitHub terms of service as an example.\n",
154+
"tos = httpx.get(\"https://examples.isaacus.com/github-tos.md\").text\n",
155+
"\n",
156+
"# Embed the terms of service.\n",
157+
"document_response = client.embeddings.create(\n",
158+
" model=\"kanon-2-embedder\",\n",
159+
" texts=tos, # You can pass a single text or a list of texts here.\n",
160+
" task=\"retrieval/document\",\n",
161+
" # dimensions=1792, # You may optionally wish to specify a lower dimension.\n",
162+
")\n",
163+
"\n",
164+
"# Embed our search queries.\n",
165+
"query_responses = client.embeddings.create(\n",
166+
" model=\"kanon-2-embedder\",\n",
167+
" texts=[\n",
168+
" \"What are GitHub's billing policies?\", # This is a relevant query.\n",
169+
" \"What are Microsoft's billing policies?\", # This is an irrelevant query.\n",
170+
" ],\n",
171+
" task=\"retrieval/query\",\n",
172+
" # dimensions=1792, # You may optionally wish to specify a lower dimension.\n",
173+
")\n",
174+
"\n",
175+
"# Unpack the embeddings.\n",
176+
"document_embedding = document_response.embeddings[0].embedding\n",
177+
"\n",
178+
"query_embeddings = query_responses.embeddings\n",
179+
"relevant_query_embedding = query_embeddings[0].embedding\n",
180+
"irrelevant_query_embedding = query_embeddings[1].embedding\n",
181+
"\n",
182+
"# Compute the similarity between the queries and the document.\n",
183+
"relevant_similarity = np.dot(relevant_query_embedding, document_embedding)\n",
184+
"irrelevant_similarity = np.dot(irrelevant_query_embedding, document_embedding)\n",
185+
"\n",
186+
"# Log the results.\n",
187+
"print(f\"Similarity of relevant query to the document: {relevant_similarity * 100:.2f}\")\n",
188+
"print(f\"Similarity of irrelevant query to the document: {irrelevant_similarity * 100:.2f}\")"
189+
]
190+
}
191+
],
192+
"metadata": {
193+
"kernelspec": {
194+
"display_name": ".venv",
195+
"language": "python",
196+
"name": "python3"
197+
},
198+
"language_info": {
199+
"codemirror_mode": {
200+
"name": "ipython",
201+
"version": 3
202+
},
203+
"file_extension": ".py",
204+
"mimetype": "text/x-python",
205+
"name": "python",
206+
"nbconvert_exporter": "python",
207+
"pygments_lexer": "ipython3",
208+
"version": "3.13.7"
209+
}
210+
},
211+
"nbformat": 4,
212+
"nbformat_minor": 5
213+
}

0 commit comments

Comments
 (0)