Skip to content

Commit 3880787

Browse files
oxy-tgoxy-tg
authored
docs: Add Oxylabs integration (#30591)
Description: This PR adds documentation for the langchain-oxylabs integration package. The documentation includes instructions for configuring Oxylabs credentials and provides example code demonstrating how to use the package. Issue: N/A Dependencies: No new dependencies are required. Tests and Docs: Added an example notebook demonstrating the usage of the Langchain-Oxylabs package, located in docs/docs/integrations. Added a provider page in docs/docs/providers. Added a new package to libs/packages.yml. Lint and Test: Successfully ran make format, make lint, and make test.
1 parent 816492e commit 3880787

File tree

3 files changed

+320
-1
lines changed

3 files changed

+320
-1
lines changed

‎docs/docs/integrations/providers/oxylabs.mdx

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
# Oxylabs
2+
3+
[Oxylabs](https://oxylabs.io/) is a market-leading web intelligence collection platform, driven by the highest business,
4+
ethics, and compliance standards, enabling companies worldwide to unlock data-driven insights.
5+
6+
[langchain-oxylabs](https://pypi.org/project/langchain-oxylabs/) implements
7+
tools enabling LLMs to interact with Oxylabs Web Scraper API.
8+
9+
10+
## Installation and Setup
11+
12+
```bash
13+
pip install langchain-oxylabs
14+
```
15+
16+
## Tools
17+
18+
See details on available tools [here](/docs/integrations/tools/oxylabs/).

‎docs/docs/integrations/tools/oxylabs.ipynb

Lines changed: 298 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,298 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"id": "65142ccb18a6add5",
6+
"metadata": {},
7+
"source": "# Oxylabs"
8+
},
9+
{
10+
"cell_type": "markdown",
11+
"id": "19976df355f9c461",
12+
"metadata": {},
13+
"source": [
14+
">[Oxylabs](https://oxylabs.io/) is a market-leading web intelligence collection platform, driven by the highest business, ethics, and compliance standards, enabling companies worldwide to unlock data-driven insights.\n",
15+
"\n",
16+
"## Overview\n",
17+
"\n",
18+
"This package contains the LangChain integration with Oxylabs, providing tools to scrape Google search results with Oxylabs Web Scraper API using LangChain's framework.\n",
19+
"\n",
20+
"The following classes are provided by this package:\n",
21+
"- `OxylabsSearchRun` - A tool that returns scraped Google search results in a formatted text\n",
22+
"- `OxylabsSearchResults` - A tool that returns scraped Google search results in a JSON format\n",
23+
"- `OxylabsSearchAPIWrapper` - An API wrapper for initializing Oxylabs API"
24+
]
25+
},
26+
{
27+
"cell_type": "markdown",
28+
"id": "76e6d8030199710d",
29+
"metadata": {},
30+
"source": [
31+
"| Pricing |\n",
32+
"|:-------------------------------:|\n",
33+
"| ✅ Free 5,000 results for 1 week |"
34+
]
35+
},
36+
{
37+
"cell_type": "markdown",
38+
"id": "eb59c5f3051be9d4",
39+
"metadata": {},
40+
"source": "## Setup"
41+
},
42+
{
43+
"cell_type": "markdown",
44+
"id": "45951d881c460419",
45+
"metadata": {},
46+
"source": "Install the required dependencies."
47+
},
48+
{
49+
"cell_type": "code",
50+
"id": "576e08c41f16ceda",
51+
"metadata": {},
52+
"source": [
53+
"%pip install -qU langchain-oxylabs"
54+
],
55+
"outputs": [],
56+
"execution_count": null
57+
},
58+
{
59+
"cell_type": "markdown",
60+
"id": "ce19bb3a52a3ab60",
61+
"metadata": {},
62+
"source": "### Credentials"
63+
},
64+
{
65+
"cell_type": "markdown",
66+
"id": "b8330dfd5861482e",
67+
"metadata": {},
68+
"source": "Set up the proper API keys and environment variables. Create your API user credentials: Sign up for a free trial or purchase the product in the [Oxylabs dashboard](https://dashboard.oxylabs.io/en/registration) to create your API user credentials (OXYLABS_USERNAME and OXYLABS_PASSWORD)."
69+
},
70+
{
71+
"cell_type": "code",
72+
"id": "474b6eaf6e35efda",
73+
"metadata": {},
74+
"source": [
75+
"import getpass\n",
76+
"import os\n",
77+
"\n",
78+
"os.environ[\"OXYLABS_USERNAME\"] = getpass.getpass(\"Enter your Oxylabs username: \")\n",
79+
"os.environ[\"OXYLABS_PASSWORD\"] = getpass.getpass(\"Enter your Oxylabs password: \")"
80+
],
81+
"outputs": [],
82+
"execution_count": null
83+
},
84+
{
85+
"cell_type": "markdown",
86+
"id": "ae310f86b113bd78",
87+
"metadata": {},
88+
"source": "## Instantiation"
89+
},
90+
{
91+
"cell_type": "code",
92+
"id": "69ea8139f6152b48",
93+
"metadata": {},
94+
"source": [
95+
"from langchain_oxylabs import OxylabsSearchAPIWrapper, OxylabsSearchRun\n",
96+
"\n",
97+
"oxylabs_wrapper = OxylabsSearchAPIWrapper()\n",
98+
"tool_ = OxylabsSearchRun(wrapper=oxylabs_wrapper)"
99+
],
100+
"outputs": [],
101+
"execution_count": null
102+
},
103+
{
104+
"cell_type": "markdown",
105+
"id": "636efff6267b9bc1",
106+
"metadata": {},
107+
"source": "## Invocation"
108+
},
109+
{
110+
"cell_type": "markdown",
111+
"id": "272f5fdaed5fa000",
112+
"metadata": {},
113+
"source": "### Invoke directly with args"
114+
},
115+
{
116+
"cell_type": "markdown",
117+
"id": "3c26724911f6cfdf",
118+
"metadata": {},
119+
"source": "The `OxylabsSearchRun` tool takes a single \"query\" argument, which should be a natural language query and returns combined string format result:"
120+
},
121+
{
122+
"cell_type": "code",
123+
"id": "b5f4d423cb3abf",
124+
"metadata": {},
125+
"source": [
126+
"tool_.invoke({\"query\": \"Restaurants in Paris.\"})"
127+
],
128+
"outputs": [],
129+
"execution_count": null
130+
},
131+
{
132+
"cell_type": "markdown",
133+
"id": "784aad18bba31062",
134+
"metadata": {},
135+
"source": "### Invoke with ToolCall"
136+
},
137+
{
138+
"cell_type": "code",
139+
"id": "8afd1652e2c4e7c9",
140+
"metadata": {},
141+
"source": [
142+
"tool_ = OxylabsSearchRun(\n",
143+
" wrapper=oxylabs_wrapper,\n",
144+
" kwargs={\n",
145+
" \"result_categories\": [\n",
146+
" \"local_information\",\n",
147+
" \"combined_search_result\",\n",
148+
" ]\n",
149+
" },\n",
150+
")"
151+
],
152+
"outputs": [],
153+
"execution_count": null
154+
},
155+
{
156+
"cell_type": "code",
157+
"id": "1b903fb2f8272df2",
158+
"metadata": {},
159+
"source": [
160+
"from pprint import pprint\n",
161+
"\n",
162+
"model_generated_tool_call = {\n",
163+
" \"args\": {\n",
164+
" \"query\": \"Visit restaurants in Vilnius.\",\n",
165+
" \"geo_location\": \"Vilnius,Lithuania\",\n",
166+
" },\n",
167+
" \"id\": \"1\",\n",
168+
" \"name\": \"oxylabs_search\",\n",
169+
" \"type\": \"tool_call\",\n",
170+
"}\n",
171+
"tool_call_result = tool_.invoke(model_generated_tool_call)\n",
172+
"\n",
173+
"# The content is a JSON string of results\n",
174+
"pprint(tool_call_result.content)"
175+
],
176+
"outputs": [],
177+
"execution_count": null
178+
},
179+
{
180+
"cell_type": "markdown",
181+
"id": "a436fc39ce17b6da",
182+
"metadata": {},
183+
"source": [
184+
"## Use within an agent\n",
185+
"Install the required dependencies."
186+
]
187+
},
188+
{
189+
"cell_type": "code",
190+
"id": "a6f23e65092e8d27",
191+
"metadata": {},
192+
"source": "%pip install -qU \"langchain[openai]\" langgraph",
193+
"outputs": [],
194+
"execution_count": null
195+
},
196+
{
197+
"cell_type": "code",
198+
"id": "21078a0c265759ff",
199+
"metadata": {},
200+
"source": [
201+
"import getpass\n",
202+
"import os\n",
203+
"\n",
204+
"from langchain.chat_models import init_chat_model\n",
205+
"\n",
206+
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter API key for OpenAI: \")\n",
207+
"llm = init_chat_model(\"gpt-4o-mini\", model_provider=\"openai\")"
208+
],
209+
"outputs": [],
210+
"execution_count": null
211+
},
212+
{
213+
"cell_type": "code",
214+
"id": "396548ee2f08fb30",
215+
"metadata": {},
216+
"source": [
217+
"from langgraph.prebuilt import create_react_agent\n",
218+
"\n",
219+
"# Initialize OxylabsSearchRun tool\n",
220+
"tool_ = OxylabsSearchRun(wrapper=oxylabs_wrapper)\n",
221+
"\n",
222+
"agent = create_react_agent(llm, [tool_])\n",
223+
"\n",
224+
"user_input = \"What happened in the latest Burning Man floods?\"\n",
225+
"\n",
226+
"for step in agent.stream(\n",
227+
" {\"messages\": user_input},\n",
228+
" stream_mode=\"values\",\n",
229+
"):\n",
230+
" step[\"messages\"][-1].pretty_print()"
231+
],
232+
"outputs": [],
233+
"execution_count": null
234+
},
235+
{
236+
"cell_type": "markdown",
237+
"id": "b10bbcf5ce299fd5",
238+
"metadata": {},
239+
"source": [
240+
"## JSON results\n",
241+
"`OxylabsSearchResults` tool can be used as an alternative to `OxylabsSearchRun` to retrieve results in a JSON format:"
242+
]
243+
},
244+
{
245+
"cell_type": "code",
246+
"id": "ef0d856f571c4938",
247+
"metadata": {},
248+
"source": [
249+
"import json\n",
250+
"\n",
251+
"from langchain_oxylabs import OxylabsSearchResults\n",
252+
"\n",
253+
"tool_ = OxylabsSearchResults(wrapper=oxylabs_wrapper)\n",
254+
"\n",
255+
"response_results = tool_.invoke({\"query\": \"What are the most famous artists?\"})\n",
256+
"response_results = json.loads(response_results)\n",
257+
"\n",
258+
"for result in response_results:\n",
259+
" for key, value in result.items():\n",
260+
" print(f\"{key}: {value}\")"
261+
],
262+
"outputs": [],
263+
"execution_count": null
264+
},
265+
{
266+
"cell_type": "markdown",
267+
"id": "7f16702d224dabb2",
268+
"metadata": {},
269+
"source": [
270+
"## API reference\n",
271+
"More information about this integration package can be found here: https://github.com/oxylabs/langchain-oxylabs\n",
272+
"\n",
273+
"Oxylabs Web Scraper API documentation: https://developers.oxylabs.io/scraper-apis/web-scraper-api\n"
274+
]
275+
}
276+
],
277+
"metadata": {
278+
"kernelspec": {
279+
"display_name": "Python 3",
280+
"language": "python",
281+
"name": "python3"
282+
},
283+
"language_info": {
284+
"codemirror_mode": {
285+
"name": "ipython",
286+
"version": 2
287+
},
288+
"file_extension": ".py",
289+
"mimetype": "text/x-python",
290+
"name": "python",
291+
"nbconvert_exporter": "python",
292+
"pygments_lexer": "ipython2",
293+
"version": "2.7.6"
294+
}
295+
},
296+
"nbformat": 4,
297+
"nbformat_minor": 5
298+
}

‎libs/packages.yml

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -564,4 +564,7 @@ packages:
564564
repo: memgraph/langchain-memgraph
565565
- name: langchain-vectara
566566
path: libs/vectara
567-
repo: vectara/langchain-vectara
567+
repo: vectara/langchain-vectara
568+
- name: langchain-oxylabs
569+
path: .
570+
repo: oxylabs/langchain-oxylabs

0 commit comments

Comments
 (0)