Skip to content

Commit 90cd6ae

Browse files
daisyfaithaumaomarmosidkathayl
authored and
RebeccaTamachiro
committed
[BRAPI] json endpoint docs (#20981)
* json endpoint docs * reorder * docs: Update JSON endpoint documentation with new examples and structure * docs: Add links endpoint * minor edits * collapsed lines * title * Update json-endpoint.mdx added note about incurring workers ai usage when using json endpoint * Update json-endpoint.mdx fix collapsing and get rid of random highlighting * Update links-endpoint.mdx get rid of random highlighting --------- Co-authored-by: Omar Mohammad <[email protected]> Co-authored-by: Kathy <[email protected]>
1 parent a750714 commit 90cd6ae

File tree

3 files changed

+426
-1
lines changed

3 files changed

+426
-1
lines changed

‎src/content/docs/browser-rendering/rest-api/api-reference.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,5 +3,5 @@ pcx_content_type: navigation
33
title: Reference
44
external_link: /api/resources/browser_rendering/
55
sidebar:
6-
order: 8
6+
order: 15
77
---

‎src/content/docs/browser-rendering/rest-api/json-endpoint.mdx‎

Lines changed: 231 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,231 @@
1+
---
2+
pcx_content_type: how-to
3+
title: Capture structured data
4+
sidebar:
5+
order: 9
6+
---
7+
8+
The `/json` endpoint extracts structured data from a webpage. You can specify the expected output using either a `prompt` or a `response_format` parameter which accepts a JSON schema. The endpoint returns the extracted data in JSON format.
9+
10+
## Parameters
11+
12+
| Parameter | Mandatory | Note |
13+
| --------------- | --------- | ---------------------------------------------------------------------------- |
14+
| URL | yes | The URL of the webpage to extract data from. |
15+
| prompt | no | Must supply one of `prompt` or `response_format`. |
16+
| response_format | no | Must supply one of `prompt` or `response_format`. May include a JSON schema. |
17+
18+
:::note[Note]
19+
20+
The `/json` endpoint leverages [Workers AI](/workers-ai/) for data extraction. Using this endpoint incurs usage on Workers AI, which you can monitor usage through the Workers AI Dashboard.
21+
22+
:::
23+
24+
## Basic Usage
25+
26+
### With a Prompt and JSON schema
27+
28+
This example captures webpage data by providing both a prompt and a JSON schema. The prompt guides the extraction process, while the JSON schema defines the expected structure of the output.
29+
30+
```bash
31+
curl --request POST 'https://api.cloudflare.com/client/v4/accounts/CF_ACCOUNT_ID/browser-rendering/json' \
32+
--header 'authorization: Bearer CF_API_TOKEN' \
33+
--header 'content-type: application/json' \
34+
--data '{
35+
"url": "https://developers.cloudflare.com/",
36+
"prompt": "Get me the list of AI products",
37+
"response_format": {
38+
"type": "json_schema",
39+
"json_schema": {
40+
"type": "object",
41+
"properties": {
42+
"products": {
43+
"type": "array",
44+
"items": {
45+
"type": "object",
46+
"properties": {
47+
"name": {
48+
"type": "string"
49+
},
50+
"link": {
51+
"type": "string"
52+
}
53+
},
54+
"required": [
55+
"name"
56+
]
57+
}
58+
}
59+
}
60+
}
61+
}
62+
}'
63+
```
64+
65+
66+
```json output collapse={15-48}
67+
{
68+
"success": true,
69+
"result": {
70+
"products": [
71+
{
72+
"name": "Build a RAG app",
73+
"link": "https://developers.cloudflare.com/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/"
74+
},
75+
{
76+
"name": "Workers AI",
77+
"link": "https://developers.cloudflare.com/workers-ai/"
78+
},
79+
{
80+
"name": "Vectorize",
81+
"link": "https://developers.cloudflare.com/vectorize/"
82+
},
83+
{
84+
"name": "AI Gateway",
85+
"link": "https://developers.cloudflare.com/ai-gateway/"
86+
},
87+
{
88+
"name": "AI Playground",
89+
"link": "https://playground.ai.cloudflare.com/"
90+
}
91+
]
92+
}
93+
}
94+
```
95+
96+
### With only a prompt
97+
98+
In this example, only a prompt is provided. The endpoint will use the prompt to extract the data, but the response will not be structured according to a JSON schema.
99+
This is useful for simple extractions where you don't need a specific format.
100+
101+
```bash
102+
curl --request POST 'https://api.cloudflare.com/client/v4/accounts/CF_ACCOUNT_ID/browser-rendering/json' \
103+
--header 'authorization: Bearer CF_API_TOKEN' \
104+
--header 'content-type: application/json' \
105+
--data '{
106+
"url": "https://developers.cloudflare.com/",
107+
"prompt": "get me the list of AI products"
108+
}'
109+
```
110+
111+
112+
```json output
113+
114+
"success": true,
115+
"result": {
116+
"AI Products": [
117+
"Build a RAG app",
118+
"Workers AI",
119+
"Vectorize",
120+
"AI Gateway",
121+
"AI Playground"
122+
]
123+
}
124+
}
125+
```
126+
127+
### With only a JSON schema (no prompt)
128+
129+
In this case, you supply a JSON schema via the `response_format` parameter. The schema defines the structure of the extracted data.
130+
131+
```bash
132+
curl --request POST 'https://api.cloudflare.com/client/v4/accounts/CF_ACCOUNT_ID/browser-rendering/json' \
133+
--header 'authorization: Bearer CF_API_TOKEN' \
134+
--header 'content-type: application/json' \
135+
--data '"response_format": {
136+
"type": "json_schema",
137+
"json_schema": {
138+
"type": "object",
139+
"properties": {
140+
"products": {
141+
"type": "array",
142+
"items": {
143+
"type": "object",
144+
"properties": {
145+
"name": {
146+
"type": "string"
147+
},
148+
"link": {
149+
"type": "string"
150+
}
151+
},
152+
"required": [
153+
"name"
154+
]
155+
}
156+
}
157+
}
158+
}
159+
}'
160+
```
161+
162+
163+
```json output collapse={13-68}
164+
{
165+
"success": true,
166+
"result": {
167+
"products": [
168+
{
169+
"name": "Workers",
170+
"link": "https://developers.cloudflare.com/workers/"
171+
},
172+
{
173+
"name": "Pages",
174+
"link": "https://developers.cloudflare.com/pages/"
175+
},
176+
{
177+
"name": "R2",
178+
"link": "https://developers.cloudflare.com/r2/"
179+
},
180+
{
181+
"name": "Images",
182+
"link": "https://developers.cloudflare.com/images/"
183+
},
184+
{
185+
"name": "Stream",
186+
"link": "https://developers.cloudflare.com/stream/"
187+
},
188+
{
189+
"name": "Build a RAG app",
190+
"link": "https://developers.cloudflare.com/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/"
191+
},
192+
{
193+
"name": "Workers AI",
194+
"link": "https://developers.cloudflare.com/workers-ai/"
195+
},
196+
{
197+
"name": "Vectorize",
198+
"link": "https://developers.cloudflare.com/vectorize/"
199+
},
200+
{
201+
"name": "AI Gateway",
202+
"link": "https://developers.cloudflare.com/ai-gateway/"
203+
},
204+
{
205+
"name": "AI Playground",
206+
"link": "https://playground.ai.cloudflare.com/"
207+
},
208+
{
209+
"name": "Access",
210+
"link": "https://developers.cloudflare.com/cloudflare-one/policies/access/"
211+
},
212+
{
213+
"name": "Tunnel",
214+
"link": "https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/"
215+
},
216+
{
217+
"name": "Gateway",
218+
"link": "https://developers.cloudflare.com/cloudflare-one/policies/gateway/"
219+
},
220+
{
221+
"name": "Browser Isolation",
222+
"link": "https://developers.cloudflare.com/cloudflare-one/policies/browser-isolation/"
223+
},
224+
{
225+
"name": "Replace your VPN",
226+
"link": "https://developers.cloudflare.com/learning-paths/replace-vpn/concepts/"
227+
}
228+
]
229+
}
230+
}
231+
```

0 commit comments

Comments
 (0)