---
title: Namespaces
---
[Skip to content](#_top)
[API Reference](https://developers.cloudflare.com/api)
[AI Search](https://developers.cloudflare.com/api/resources/ai_search)
Copy Markdown
Open in **Claude**Open in **ChatGPT**Open in **Cursor**
---
**Copy Markdown****View as Markdown**
# Namespaces
##### [List namespaces](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/list)
GET/accounts/{account\_id}/ai-search/namespaces
##### [Create a namespace](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/create)
POST/accounts/{account\_id}/ai-search/namespaces
##### [Get a namespace](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/read)
GET/accounts/{account\_id}/ai-search/namespaces/{name}
##### [Update a namespace](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/update)
PUT/accounts/{account\_id}/ai-search/namespaces/{name}
##### [Delete a namespace](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/delete)
DELETE/accounts/{account\_id}/ai-search/namespaces/{name}
##### [Multi-Instance Search](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/search)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/search
##### [Multi-Instance Chat Completions](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/methods/chat_completions)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/chat/completions
##### ModelsExpand Collapse
NamespaceListResponse object {created\_at, name, description, 2 more }
created\_at: string
formatdate-time
Link to this property
name: string
Link to this property
description: optional string
Optional description for the namespace. Max 256 characters.
maxLength256
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 6 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
instances\_allowed: optional array of string
Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit.
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_list_response%20%3E%20(schema)>)
NamespaceCreateResponse object {created\_at, name, description, 2 more }
created\_at: string
formatdate-time
Link to this property
name: string
Link to this property
description: optional string
Optional description for the namespace. Max 256 characters.
maxLength256
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 6 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
instances\_allowed: optional array of string
Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit.
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_create_response%20%3E%20(schema)>)
NamespaceReadResponse object {created\_at, name, description, 2 more }
created\_at: string
formatdate-time
Link to this property
name: string
Link to this property
description: optional string
Optional description for the namespace. Max 256 characters.
maxLength256
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 6 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
instances\_allowed: optional array of string
Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit.
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_read_response%20%3E%20(schema)>)
NamespaceUpdateResponse object {created\_at, name, description, 2 more }
created\_at: string
formatdate-time
Link to this property
name: string
Link to this property
description: optional string
Optional description for the namespace. Max 256 characters.
maxLength256
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 6 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
instances\_allowed: optional array of string
Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit.
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_update_response%20%3E%20(schema)>)
NamespaceDeleteResponse = unknown
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_delete_response%20%3E%20(schema)>)
NamespaceSearchResponse object {chunks, query\_kind, errors, search\_query }
chunks: array of object {id, instance\_id, score, 4 more }
id: string
Link to this property
instance\_id: string
Link to this property
score: number
maximum1
minimum0
Link to this property
text: string
Link to this property
type: string
Link to this property
item: optional object {key, metadata, timestamp }
key: string
Link to this property
metadata: optional map\[unknown]
Link to this property
timestamp: optional number
Link to this property
Link to this property
scoring\_details: optional object {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method: optional "rrf"or "max"
One of the following:
"rrf"
Link to this property
"max"
Link to this property
Link to this property
keyword\_rank: optional number
Link to this property
keyword\_score: optional number
minimum0
Link to this property
reranking\_score: optional number
maximum1
minimum0
Link to this property
vector\_rank: optional number
Link to this property
vector\_score: optional number
maximum1
minimum0
Link to this property
Link to this property
Link to this property
query\_kind: "text"or "image"or "multimodal"
One of the following:
"text"
Link to this property
"image"
Link to this property
"multimodal"
Link to this property
Link to this property
errors: optional array of object {instance\_id, message }
instance\_id: string
Link to this property
message: string
Link to this property
Link to this property
search\_query: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_search_response%20%3E%20(schema)>)
NamespaceChatCompletionsResponse object {choices, chunks, id, 3 more }
choices: array of object {message, index }
message: object {content, role }
content: stringor array of object {text, type } or object {image\_url, type } or object {file, type } or string
One of the following:
string
Link to this property
array of object {text, type } or object {image\_url, type } or object {file, type }
One of the following:
object {text, type }
text: string
minLength1
Link to this property
type: "text"
Link to this property
Link to this property
object {image\_url, type }
image\_url: object {url }
url: string
maxLength20971520
minLength1
Link to this property
Link to this property
type: "image\_url"
Link to this property
Link to this property
object {file, type }
file: object {filename, file\_data, file\_id }
filename: string
maxLength255
minLength1
Link to this property
file\_data: optional string
maxLength13981144
minLength1
Link to this property
file\_id: optional string
Link to this property
Link to this property
type: "file"
Link to this property
Link to this property
Link to this property
string
Link to this property
Link to this property
role: "system"or "developer"or "user"or 2 more
One of the following:
"system"
Link to this property
"developer"
Link to this property
"user"
Link to this property
"assistant"
Link to this property
"tool"
Link to this property
Link to this property
Link to this property
index: optional number
Link to this property
Link to this property
chunks: array of object {id, instance\_id, score, 4 more }
id: string
Link to this property
instance\_id: string
Link to this property
score: number
maximum1
minimum0
Link to this property
text: string
Link to this property
type: string
Link to this property
item: optional object {key, metadata, timestamp }
key: string
Link to this property
metadata: optional map\[unknown]
Link to this property
timestamp: optional number
Link to this property
Link to this property
scoring\_details: optional object {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method: optional "rrf"or "max"
One of the following:
"rrf"
Link to this property
"max"
Link to this property
Link to this property
keyword\_rank: optional number
Link to this property
keyword\_score: optional number
minimum0
Link to this property
reranking\_score: optional number
maximum1
minimum0
Link to this property
vector\_rank: optional number
Link to this property
vector\_score: optional number
maximum1
minimum0
Link to this property
Link to this property
Link to this property
id: optional string
Link to this property
errors: optional array of object {instance\_id, message }
instance\_id: string
Link to this property
message: string
Link to this property
Link to this property
model: optional string
Link to this property
object: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_chat_completions_response%20%3E%20(schema)>)
#### NamespacesInstances
##### [List AI Search instances.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/list)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances
##### [Create an AI Search instance (Search for Agents requires the default namespace).](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/create)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances
##### [Get an AI Search instance.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/read)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}
##### [Update an AI Search instance (Search for Agents metadata requires the default namespace).](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/update)
PUT/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}
##### [Delete an AI Search instance.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/delete)
DELETE/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}
##### [Get instance statistics.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/stats)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/stats
##### [Search](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/search)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/search
##### [Chat Completions](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/methods/chat_completions)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/chat/completions
##### ModelsExpand Collapse
InstanceListResponse object {id, ai\_gateway\_id, ai\_search\_model, 42 more }
id: string
Link to this property
ai\_gateway\_id: string
Link to this property
ai\_search\_model: string
Link to this property
cache: boolean
Link to this property
cache\_threshold: "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"
One of the following:
"super\_strict\_match"
Link to this property
"close\_enough"
Link to this property
"flexible\_friend"
Link to this property
"anything\_goes"
Link to this property
Link to this property
cache\_ttl: 600or 1800or 3600or 7 more
One of the following:
600
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
172800
Link to this property
259200
Link to this property
518400
Link to this property
Link to this property
chunk: boolean
Link to this property
chunk\_overlap: number
Link to this property
chunk\_size: number
Link to this property
created\_at: string
formatdate-time
Link to this property
created\_by: string
Link to this property
custom\_metadata: array of object {data\_type, field\_name }
data\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field\_name: string
Link to this property
Link to this property
embedding\_model: string
Link to this property
enable: boolean
Link to this property
engine\_version: number
Link to this property
fusion\_method: "max"or "rrf"
One of the following:
"max"
Link to this property
"rrf"
Link to this property
Link to this property
hybrid\_search\_enabled: boolean
Link to this property
index\_method: object {keyword, vector }
keyword: boolean
Link to this property
vector: boolean
Link to this property
Link to this property
indexing\_options: object {keyword\_tokenizer, use\_ocr }
keyword\_tokenizer: optional "porter"or "trigram"
One of the following:
"porter"
Link to this property
"trigram"
Link to this property
Link to this property
use\_ocr: optional boolean
Link to this property
Link to this property
last\_activity: string
formatdate-time
Link to this property
max\_num\_results: number
Link to this property
metadata: object {created\_from\_aisearch\_wizard, worker\_domain }
created\_from\_aisearch\_wizard: optional boolean
Link to this property
worker\_domain: optional string
Link to this property
Link to this property
modified\_at: string
formatdate-time
Link to this property
modified\_by: string
Link to this property
namespace: string
Link to this property
paused: boolean
Link to this property
public\_endpoint\_id: string
Link to this property
public\_endpoint\_params: object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Link to this property
Link to this property
custom\_domains: optional array of string
Link to this property
default\_domain\_enabled: optional boolean
Link to this property
enabled: optional boolean
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Link to this property
Link to this property
Link to this property
reranking: boolean
Link to this property
reranking\_model: string
Link to this property
retrieval\_options: object {boost\_by, keyword\_match\_mode }
boost\_by: optional array of object {field, dataType, direction }
field: string
maxLength64
minLength1
Link to this property
dataType: optional "number"or "datetime"or "text"or "boolean"
One of the following:
"number"
Link to this property
"datetime"
Link to this property
"text"
Link to this property
"boolean"
Link to this property
Link to this property
direction: optional "asc"or "desc"or "exists"or "not\_exists"
One of the following:
"asc"
Link to this property
"desc"
Link to this property
"exists"
Link to this property
"not\_exists"
Link to this property
Link to this property
Link to this property
keyword\_match\_mode: optional "and"or "or"
One of the following:
"and"
Link to this property
"or"
Link to this property
Link to this property
Link to this property
rewrite\_model: string
Link to this property
rewrite\_query: boolean
Link to this property
score\_threshold: number
Link to this property
source: string
Link to this property
source\_params: object {exclude\_items, include\_items, prefix, 2 more }
exclude\_items: optional array of string
Link to this property
include\_items: optional array of string
Link to this property
prefix: optional string
Link to this property
r2\_jurisdiction: optional string
Link to this property
web\_crawler: optional object {discover\_options, parse\_options, parse\_type }
discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more }
depth: optional number
maximum100000
minimum1
Link to this property
include\_external\_links: optional boolean
Link to this property
include\_subdomains: optional boolean
Link to this property
limit: optional number
Maximum number of pages to crawl. New values are capped at 100000; instances configured before that cap may report a higher stored value, which the crawler clamps at run time.
maximum100000
minimum1
Link to this property
max\_age: optional number
maximum604800
minimum0
Link to this property
source: optional "all"or "sitemaps"or "links"
One of the following:
"all"
Link to this property
"sitemaps"
Link to this property
"links"
Link to this property
Link to this property
Link to this property
parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }
content\_selector: optional array of object {path, selector }
path: string
maxLength200
minLength1
Link to this property
selector: string
maxLength200
minLength1
Link to this property
Link to this property
include\_headers: optional map\[string]
Link to this property
include\_images: optional boolean
Link to this property
specific\_sitemaps: optional array of string
Link to this property
use\_browser\_rendering: optional boolean
Link to this property
Link to this property
parse\_type: optional "sitemap"or "discover"
One of the following:
"sitemap"
Link to this property
"discover"
Link to this property
Link to this property
Link to this property
Link to this property
status: string
Link to this property
summarization: boolean
Link to this property
summarization\_model: string
Link to this property
sync\_interval: 900or 1800or 3600or 5 more
One of the following:
900
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
14400
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
Link to this property
system\_prompt\_ai\_search: string
Link to this property
system\_prompt\_index\_summarization: string
Link to this property
system\_prompt\_rewrite\_query: string
Link to this property
token\_id: string
Link to this property
type: "r2"or "web-crawler"
One of the following:
"r2"
Link to this property
"web-crawler"
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_list_response%20%3E%20(schema)>)
InstanceCreateResponse object {id, created\_at, modified\_at, 36 more }
id: string
AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
maxLength64
minLength1
Link to this property
created\_at: string
formatdate-time
Link to this property
modified\_at: string
formatdate-time
Link to this property
ai\_gateway\_id: optional string
Link to this property
ai\_search\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
cache: optional boolean
Link to this property
cache\_threshold: optional "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"
One of the following:
"super\_strict\_match"
Link to this property
"close\_enough"
Link to this property
"flexible\_friend"
Link to this property
"anything\_goes"
Link to this property
Link to this property
cache\_ttl: optional 600or 1800or 3600or 7 more
Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200 (72h), 518400 (6d).
One of the following:
600
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
172800
Link to this property
259200
Link to this property
518400
Link to this property
Link to this property
chunk\_overlap: optional number
maximum30
minimum0
Link to this property
chunk\_size: optional number
minimum64
Link to this property
created\_by: optional string
Link to this property
custom\_metadata: optional array of object {data\_type, field\_name }
data\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field\_name: string
maxLength64
minLength1
Link to this property
Link to this property
embedding\_model: optional string
Link to this property
enable: optional boolean
Link to this property
engine\_version: optional number
Link to this property
fusion\_method: optional "max"or "rrf"
One of the following:
"max"
Link to this property
"rrf"
Link to this property
Link to this property
Deprecatedhybrid\_search\_enabled: optional boolean
Deprecated — use index\_method instead. Defaults to true for new instances; set false to create a vector-only instance.
Link to this property
index\_method: optional object {keyword, vector }
Controls which storage backends are used during indexing. Defaults to vector and keyword indexing for new instances.
keyword: boolean
Enable keyword (BM25) storage backend.
Link to this property
vector: boolean
Enable vector (embedding) storage backend.
Link to this property
Link to this property
indexing\_options: optional object {keyword\_tokenizer, use\_ocr }
keyword\_tokenizer: optional "porter"or "trigram"
Tokenizer used for keyword search indexing. porter provides word-level tokenization with Porter stemming (good for natural language queries). trigram enables character-level substring matching (good for partial matches, code, identifiers). Changing this triggers a full re-index. Defaults to porter.
One of the following:
"porter"
Link to this property
"trigram"
Link to this property
Link to this property
use\_ocr: optional boolean
Enables OCR ingestion for PDFs and images. Changing this triggers a full re-index. Defaults to false.
Link to this property
Link to this property
last\_activity: optional string
formatdate-time
Link to this property
max\_num\_results: optional number
maximum50
minimum1
Link to this property
metadata: optional object {created\_from\_aisearch\_wizard, worker\_domain }
created\_from\_aisearch\_wizard: optional boolean
Link to this property
worker\_domain: optional string
Link to this property
Link to this property
modified\_by: optional string
Link to this property
namespace: optional string
Link to this property
paused: optional boolean
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
reranking: optional boolean
Link to this property
reranking\_model: optional string
Link to this property
retrieval\_options: optional object {boost\_by, keyword\_match\_mode }
boost\_by: optional array of object {field, direction }
Metadata fields to boost search results by. Each entry specifies a metadata field and an optional direction. Direction defaults to ‘asc’ for numeric/datetime fields and ‘exists’ for text/boolean fields. Fields must match ‘timestamp’ or a defined custom\_metadata field.
field: string
Metadata field name to boost by. Use ‘timestamp’ for document freshness, or any custom\_metadata field. Numeric and datetime fields support all four directions (asc, desc, exists, not\_exists); text/boolean fields only support exists/not\_exists.
maxLength64
minLength1
Link to this property
direction: optional "asc"or "desc"or "exists"or "not\_exists"
Boost direction. ‘desc’ = higher values rank higher (e.g. newer timestamps). ‘asc’ = lower values rank higher. ‘exists’ = boost chunks that have the field. ‘not\_exists’ = boost chunks that lack the field. Optional — defaults to ‘asc’ for numeric/datetime fields, ‘exists’ for text/boolean fields.
One of the following:
"asc"
Link to this property
"desc"
Link to this property
"exists"
Link to this property
"not\_exists"
Link to this property
Link to this property
Link to this property
keyword\_match\_mode: optional "and"or "or"
Controls which documents are candidates for BM25 scoring. ‘and’ restricts candidates to documents containing all query terms; ‘or’ includes any document containing at least one term, ranked by BM25 relevance. When omitted on an update, the existing stored value is preserved; when never set, search falls back to ‘and’.
One of the following:
"and"
Link to this property
"or"
Link to this property
Link to this property
Link to this property
rewrite\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
rewrite\_query: optional boolean
Link to this property
score\_threshold: optional number
maximum1
minimum0
Link to this property
source: optional string
Link to this property
source\_params: optional object {exclude\_items, include\_items, prefix, 2 more }
exclude\_items: optional array of string
List of path patterns to exclude. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /admin/\*\* matches /admin/users and /admin/settings/advanced). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
include\_items: optional array of string
List of path patterns to include. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /blog/\*\* matches /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
prefix: optional string
Link to this property
r2\_jurisdiction: optional string
Link to this property
web\_crawler: optional object {discover\_options, parse\_options, parse\_type }
discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more }
Options for parse\_type ‘discover’, where Browser Run discovers URLs by link following and sitemaps. Ignored for ‘sitemap’.
depth: optional number
Maximum link-follow depth from the seed URL.
maximum100000
minimum1
Link to this property
include\_external\_links: optional boolean
Follow links that point outside the source domain. Must stay false — discover crawls are restricted to the zone you own.
Link to this property
include\_subdomains: optional boolean
Follow links to subdomains of the source host.
Link to this property
limit: optional number
Maximum number of pages to crawl (1-100000).
maximum100000
minimum1
Link to this property
max\_age: optional number
Maximum content age in seconds to accept (0–604800).
maximum604800
minimum0
Link to this property
source: optional "all"or "sitemaps"or "links"
Where the crawler looks for URLs: ‘sitemaps’ reads sitemap XML only, ‘links’ follows page links only, ‘all’ does both.
One of the following:
"all"
Link to this property
"sitemaps"
Link to this property
"links"
Link to this property
Link to this property
Link to this property
parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }
content\_selector: optional array of object {path, selector }
List of path-to-selector mappings for extracting specific content from crawled pages. Each entry pairs a URL glob pattern with a CSS selector. The first matching path wins. Only the matched HTML fragment is stored and indexed. Omit the field to disable content selection — empty arrays are rejected.
path: string
Glob pattern to match against the page URL path. Uses standard glob syntax: \* matches within a segment, \*\* crosses directories.
maxLength200
minLength1
Link to this property
selector: string
CSS selector to extract content from pages matching the path pattern. Must not contain disallowed characters (;, \`, $, {, }, ). Must target a single element; if multiple elements match, the selector is ignored and the full page is used.
maxLength200
minLength1
Link to this property
Link to this property
include\_headers: optional map\[string]
Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230 token characters (no spaces, colons, or control characters); values must be HTAB + printable ASCII (no CR/LF).
Link to this property
include\_images: optional boolean
Link to this property
specific\_sitemaps: optional array of string
List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’.
Link to this property
use\_browser\_rendering: optional boolean
Link to this property
Link to this property
parse\_type: optional "sitemap"or "discover"
How URLs are discovered. ‘sitemap’ reads XML sitemaps; ‘discover’ follows links recursively and requires the source to be a Verified zone on this account.
One of the following:
"sitemap"
Link to this property
"discover"
Link to this property
Link to this property
Link to this property
Link to this property
status: optional string
Link to this property
sync\_interval: optional 900or 1800or 3600or 5 more
Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800 (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).
One of the following:
900
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
14400
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
Link to this property
token\_id: optional string
formatuuid
Link to this property
type: optional "r2"or "web-crawler"
Source type. When omitted or null with a non-blank source, HTTP(S) URLs infer web-crawler and existing R2 bucket names infer r2. A missing or blank source without a type uses managed upload-only storage.
One of the following:
"r2"
Link to this property
"web-crawler"
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_create_response%20%3E%20(schema)>)
InstanceReadResponse object {id, created\_at, modified\_at, 36 more }
id: string
AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
maxLength64
minLength1
Link to this property
created\_at: string
formatdate-time
Link to this property
modified\_at: string
formatdate-time
Link to this property
ai\_gateway\_id: optional string
Link to this property
ai\_search\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
cache: optional boolean
Link to this property
cache\_threshold: optional "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"
One of the following:
"super\_strict\_match"
Link to this property
"close\_enough"
Link to this property
"flexible\_friend"
Link to this property
"anything\_goes"
Link to this property
Link to this property
cache\_ttl: optional 600or 1800or 3600or 7 more
Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200 (72h), 518400 (6d).
One of the following:
600
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
172800
Link to this property
259200
Link to this property
518400
Link to this property
Link to this property
chunk\_overlap: optional number
maximum30
minimum0
Link to this property
chunk\_size: optional number
minimum64
Link to this property
created\_by: optional string
Link to this property
custom\_metadata: optional array of object {data\_type, field\_name }
data\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field\_name: string
maxLength64
minLength1
Link to this property
Link to this property
embedding\_model: optional string
Link to this property
enable: optional boolean
Link to this property
engine\_version: optional number
Link to this property
fusion\_method: optional "max"or "rrf"
One of the following:
"max"
Link to this property
"rrf"
Link to this property
Link to this property
Deprecatedhybrid\_search\_enabled: optional boolean
Deprecated — use index\_method instead. Defaults to true for new instances; set false to create a vector-only instance.
Link to this property
index\_method: optional object {keyword, vector }
Controls which storage backends are used during indexing. Defaults to vector and keyword indexing for new instances.
keyword: boolean
Enable keyword (BM25) storage backend.
Link to this property
vector: boolean
Enable vector (embedding) storage backend.
Link to this property
Link to this property
indexing\_options: optional object {keyword\_tokenizer, use\_ocr }
keyword\_tokenizer: optional "porter"or "trigram"
Tokenizer used for keyword search indexing. porter provides word-level tokenization with Porter stemming (good for natural language queries). trigram enables character-level substring matching (good for partial matches, code, identifiers). Changing this triggers a full re-index. Defaults to porter.
One of the following:
"porter"
Link to this property
"trigram"
Link to this property
Link to this property
use\_ocr: optional boolean
Enables OCR ingestion for PDFs and images. Changing this triggers a full re-index. Defaults to false.
Link to this property
Link to this property
last\_activity: optional string
formatdate-time
Link to this property
max\_num\_results: optional number
maximum50
minimum1
Link to this property
metadata: optional object {created\_from\_aisearch\_wizard, worker\_domain }
created\_from\_aisearch\_wizard: optional boolean
Link to this property
worker\_domain: optional string
Link to this property
Link to this property
modified\_by: optional string
Link to this property
namespace: optional string
Link to this property
paused: optional boolean
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
reranking: optional boolean
Link to this property
reranking\_model: optional string
Link to this property
retrieval\_options: optional object {boost\_by, keyword\_match\_mode }
boost\_by: optional array of object {field, direction }
Metadata fields to boost search results by. Each entry specifies a metadata field and an optional direction. Direction defaults to ‘asc’ for numeric/datetime fields and ‘exists’ for text/boolean fields. Fields must match ‘timestamp’ or a defined custom\_metadata field.
field: string
Metadata field name to boost by. Use ‘timestamp’ for document freshness, or any custom\_metadata field. Numeric and datetime fields support all four directions (asc, desc, exists, not\_exists); text/boolean fields only support exists/not\_exists.
maxLength64
minLength1
Link to this property
direction: optional "asc"or "desc"or "exists"or "not\_exists"
Boost direction. ‘desc’ = higher values rank higher (e.g. newer timestamps). ‘asc’ = lower values rank higher. ‘exists’ = boost chunks that have the field. ‘not\_exists’ = boost chunks that lack the field. Optional — defaults to ‘asc’ for numeric/datetime fields, ‘exists’ for text/boolean fields.
One of the following:
"asc"
Link to this property
"desc"
Link to this property
"exists"
Link to this property
"not\_exists"
Link to this property
Link to this property
Link to this property
keyword\_match\_mode: optional "and"or "or"
Controls which documents are candidates for BM25 scoring. ‘and’ restricts candidates to documents containing all query terms; ‘or’ includes any document containing at least one term, ranked by BM25 relevance. When omitted on an update, the existing stored value is preserved; when never set, search falls back to ‘and’.
One of the following:
"and"
Link to this property
"or"
Link to this property
Link to this property
Link to this property
rewrite\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
rewrite\_query: optional boolean
Link to this property
score\_threshold: optional number
maximum1
minimum0
Link to this property
source: optional string
Link to this property
source\_params: optional object {exclude\_items, include\_items, prefix, 2 more }
exclude\_items: optional array of string
List of path patterns to exclude. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /admin/\*\* matches /admin/users and /admin/settings/advanced). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
include\_items: optional array of string
List of path patterns to include. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /blog/\*\* matches /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
prefix: optional string
Link to this property
r2\_jurisdiction: optional string
Link to this property
web\_crawler: optional object {discover\_options, parse\_options, parse\_type }
discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more }
Options for parse\_type ‘discover’, where Browser Run discovers URLs by link following and sitemaps. Ignored for ‘sitemap’.
depth: optional number
Maximum link-follow depth from the seed URL.
maximum100000
minimum1
Link to this property
include\_external\_links: optional boolean
Follow links that point outside the source domain. Must stay false — discover crawls are restricted to the zone you own.
Link to this property
include\_subdomains: optional boolean
Follow links to subdomains of the source host.
Link to this property
limit: optional number
Maximum number of pages to crawl (1-100000).
maximum100000
minimum1
Link to this property
max\_age: optional number
Maximum content age in seconds to accept (0–604800).
maximum604800
minimum0
Link to this property
source: optional "all"or "sitemaps"or "links"
Where the crawler looks for URLs: ‘sitemaps’ reads sitemap XML only, ‘links’ follows page links only, ‘all’ does both.
One of the following:
"all"
Link to this property
"sitemaps"
Link to this property
"links"
Link to this property
Link to this property
Link to this property
parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }
content\_selector: optional array of object {path, selector }
List of path-to-selector mappings for extracting specific content from crawled pages. Each entry pairs a URL glob pattern with a CSS selector. The first matching path wins. Only the matched HTML fragment is stored and indexed. Omit the field to disable content selection — empty arrays are rejected.
path: string
Glob pattern to match against the page URL path. Uses standard glob syntax: \* matches within a segment, \*\* crosses directories.
maxLength200
minLength1
Link to this property
selector: string
CSS selector to extract content from pages matching the path pattern. Must not contain disallowed characters (;, \`, $, {, }, ). Must target a single element; if multiple elements match, the selector is ignored and the full page is used.
maxLength200
minLength1
Link to this property
Link to this property
include\_headers: optional map\[string]
Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230 token characters (no spaces, colons, or control characters); values must be HTAB + printable ASCII (no CR/LF).
Link to this property
include\_images: optional boolean
Link to this property
specific\_sitemaps: optional array of string
List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’.
Link to this property
use\_browser\_rendering: optional boolean
Link to this property
Link to this property
parse\_type: optional "sitemap"or "discover"
How URLs are discovered. ‘sitemap’ reads XML sitemaps; ‘discover’ follows links recursively and requires the source to be a Verified zone on this account.
One of the following:
"sitemap"
Link to this property
"discover"
Link to this property
Link to this property
Link to this property
Link to this property
status: optional string
Link to this property
sync\_interval: optional 900or 1800or 3600or 5 more
Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800 (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).
One of the following:
900
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
14400
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
Link to this property
token\_id: optional string
formatuuid
Link to this property
type: optional "r2"or "web-crawler"
Source type. When omitted or null with a non-blank source, HTTP(S) URLs infer web-crawler and existing R2 bucket names infer r2. A missing or blank source without a type uses managed upload-only storage.
One of the following:
"r2"
Link to this property
"web-crawler"
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_read_response%20%3E%20(schema)>)
InstanceUpdateResponse object {id, created\_at, modified\_at, 36 more }
id: string
AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
maxLength64
minLength1
Link to this property
created\_at: string
formatdate-time
Link to this property
modified\_at: string
formatdate-time
Link to this property
ai\_gateway\_id: optional string
Link to this property
ai\_search\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
cache: optional boolean
Link to this property
cache\_threshold: optional "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"
One of the following:
"super\_strict\_match"
Link to this property
"close\_enough"
Link to this property
"flexible\_friend"
Link to this property
"anything\_goes"
Link to this property
Link to this property
cache\_ttl: optional 600or 1800or 3600or 7 more
Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200 (72h), 518400 (6d).
One of the following:
600
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
172800
Link to this property
259200
Link to this property
518400
Link to this property
Link to this property
chunk\_overlap: optional number
maximum30
minimum0
Link to this property
chunk\_size: optional number
minimum64
Link to this property
created\_by: optional string
Link to this property
custom\_metadata: optional array of object {data\_type, field\_name }
data\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field\_name: string
maxLength64
minLength1
Link to this property
Link to this property
embedding\_model: optional string
Link to this property
enable: optional boolean
Link to this property
engine\_version: optional number
Link to this property
fusion\_method: optional "max"or "rrf"
One of the following:
"max"
Link to this property
"rrf"
Link to this property
Link to this property
Deprecatedhybrid\_search\_enabled: optional boolean
Deprecated — use index\_method instead. Defaults to true for new instances; set false to create a vector-only instance.
Link to this property
index\_method: optional object {keyword, vector }
Controls which storage backends are used during indexing. Defaults to vector and keyword indexing for new instances.
keyword: boolean
Enable keyword (BM25) storage backend.
Link to this property
vector: boolean
Enable vector (embedding) storage backend.
Link to this property
Link to this property
indexing\_options: optional object {keyword\_tokenizer, use\_ocr }
keyword\_tokenizer: optional "porter"or "trigram"
Tokenizer used for keyword search indexing. porter provides word-level tokenization with Porter stemming (good for natural language queries). trigram enables character-level substring matching (good for partial matches, code, identifiers). Changing this triggers a full re-index. Defaults to porter.
One of the following:
"porter"
Link to this property
"trigram"
Link to this property
Link to this property
use\_ocr: optional boolean
Enables OCR ingestion for PDFs and images. Changing this triggers a full re-index. Defaults to false.
Link to this property
Link to this property
last\_activity: optional string
formatdate-time
Link to this property
max\_num\_results: optional number
maximum50
minimum1
Link to this property
metadata: optional object {created\_from\_aisearch\_wizard, worker\_domain }
created\_from\_aisearch\_wizard: optional boolean
Link to this property
worker\_domain: optional string
Link to this property
Link to this property
modified\_by: optional string
Link to this property
namespace: optional string
Link to this property
paused: optional boolean
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
reranking: optional boolean
Link to this property
reranking\_model: optional string
Link to this property
retrieval\_options: optional object {boost\_by, keyword\_match\_mode }
boost\_by: optional array of object {field, direction }
Metadata fields to boost search results by. Each entry specifies a metadata field and an optional direction. Direction defaults to ‘asc’ for numeric/datetime fields and ‘exists’ for text/boolean fields. Fields must match ‘timestamp’ or a defined custom\_metadata field.
field: string
Metadata field name to boost by. Use ‘timestamp’ for document freshness, or any custom\_metadata field. Numeric and datetime fields support all four directions (asc, desc, exists, not\_exists); text/boolean fields only support exists/not\_exists.
maxLength64
minLength1
Link to this property
direction: optional "asc"or "desc"or "exists"or "not\_exists"
Boost direction. ‘desc’ = higher values rank higher (e.g. newer timestamps). ‘asc’ = lower values rank higher. ‘exists’ = boost chunks that have the field. ‘not\_exists’ = boost chunks that lack the field. Optional — defaults to ‘asc’ for numeric/datetime fields, ‘exists’ for text/boolean fields.
One of the following:
"asc"
Link to this property
"desc"
Link to this property
"exists"
Link to this property
"not\_exists"
Link to this property
Link to this property
Link to this property
keyword\_match\_mode: optional "and"or "or"
Controls which documents are candidates for BM25 scoring. ‘and’ restricts candidates to documents containing all query terms; ‘or’ includes any document containing at least one term, ranked by BM25 relevance. When omitted on an update, the existing stored value is preserved; when never set, search falls back to ‘and’.
One of the following:
"and"
Link to this property
"or"
Link to this property
Link to this property
Link to this property
rewrite\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
rewrite\_query: optional boolean
Link to this property
score\_threshold: optional number
maximum1
minimum0
Link to this property
source: optional string
Link to this property
source\_params: optional object {exclude\_items, include\_items, prefix, 2 more }
exclude\_items: optional array of string
List of path patterns to exclude. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /admin/\*\* matches /admin/users and /admin/settings/advanced). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
include\_items: optional array of string
List of path patterns to include. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /blog/\*\* matches /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
prefix: optional string
Link to this property
r2\_jurisdiction: optional string
Link to this property
web\_crawler: optional object {discover\_options, parse\_options, parse\_type }
discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more }
Options for parse\_type ‘discover’, where Browser Run discovers URLs by link following and sitemaps. Ignored for ‘sitemap’.
depth: optional number
Maximum link-follow depth from the seed URL.
maximum100000
minimum1
Link to this property
include\_external\_links: optional boolean
Follow links that point outside the source domain. Must stay false — discover crawls are restricted to the zone you own.
Link to this property
include\_subdomains: optional boolean
Follow links to subdomains of the source host.
Link to this property
limit: optional number
Maximum number of pages to crawl (1-100000).
maximum100000
minimum1
Link to this property
max\_age: optional number
Maximum content age in seconds to accept (0–604800).
maximum604800
minimum0
Link to this property
source: optional "all"or "sitemaps"or "links"
Where the crawler looks for URLs: ‘sitemaps’ reads sitemap XML only, ‘links’ follows page links only, ‘all’ does both.
One of the following:
"all"
Link to this property
"sitemaps"
Link to this property
"links"
Link to this property
Link to this property
Link to this property
parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }
content\_selector: optional array of object {path, selector }
List of path-to-selector mappings for extracting specific content from crawled pages. Each entry pairs a URL glob pattern with a CSS selector. The first matching path wins. Only the matched HTML fragment is stored and indexed. Omit the field to disable content selection — empty arrays are rejected.
path: string
Glob pattern to match against the page URL path. Uses standard glob syntax: \* matches within a segment, \*\* crosses directories.
maxLength200
minLength1
Link to this property
selector: string
CSS selector to extract content from pages matching the path pattern. Must not contain disallowed characters (;, \`, $, {, }, ). Must target a single element; if multiple elements match, the selector is ignored and the full page is used.
maxLength200
minLength1
Link to this property
Link to this property
include\_headers: optional map\[string]
Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230 token characters (no spaces, colons, or control characters); values must be HTAB + printable ASCII (no CR/LF).
Link to this property
include\_images: optional boolean
Link to this property
specific\_sitemaps: optional array of string
List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’.
Link to this property
use\_browser\_rendering: optional boolean
Link to this property
Link to this property
parse\_type: optional "sitemap"or "discover"
How URLs are discovered. ‘sitemap’ reads XML sitemaps; ‘discover’ follows links recursively and requires the source to be a Verified zone on this account.
One of the following:
"sitemap"
Link to this property
"discover"
Link to this property
Link to this property
Link to this property
Link to this property
status: optional string
Link to this property
sync\_interval: optional 900or 1800or 3600or 5 more
Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800 (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).
One of the following:
900
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
14400
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
Link to this property
token\_id: optional string
formatuuid
Link to this property
type: optional "r2"or "web-crawler"
Source type. When omitted or null with a non-blank source, HTTP(S) URLs infer web-crawler and existing R2 bucket names infer r2. A missing or blank source without a type uses managed upload-only storage.
One of the following:
"r2"
Link to this property
"web-crawler"
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_update_response%20%3E%20(schema)>)
InstanceDeleteResponse object {id, created\_at, modified\_at, 36 more }
id: string
AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
maxLength64
minLength1
Link to this property
created\_at: string
formatdate-time
Link to this property
modified\_at: string
formatdate-time
Link to this property
ai\_gateway\_id: optional string
Link to this property
ai\_search\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
cache: optional boolean
Link to this property
cache\_threshold: optional "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"
One of the following:
"super\_strict\_match"
Link to this property
"close\_enough"
Link to this property
"flexible\_friend"
Link to this property
"anything\_goes"
Link to this property
Link to this property
cache\_ttl: optional 600or 1800or 3600or 7 more
Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200 (72h), 518400 (6d).
One of the following:
600
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
172800
Link to this property
259200
Link to this property
518400
Link to this property
Link to this property
chunk\_overlap: optional number
maximum30
minimum0
Link to this property
chunk\_size: optional number
minimum64
Link to this property
created\_by: optional string
Link to this property
custom\_metadata: optional array of object {data\_type, field\_name }
data\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field\_name: string
maxLength64
minLength1
Link to this property
Link to this property
embedding\_model: optional string
Link to this property
enable: optional boolean
Link to this property
engine\_version: optional number
Link to this property
fusion\_method: optional "max"or "rrf"
One of the following:
"max"
Link to this property
"rrf"
Link to this property
Link to this property
Deprecatedhybrid\_search\_enabled: optional boolean
Deprecated — use index\_method instead. Defaults to true for new instances; set false to create a vector-only instance.
Link to this property
index\_method: optional object {keyword, vector }
Controls which storage backends are used during indexing. Defaults to vector and keyword indexing for new instances.
keyword: boolean
Enable keyword (BM25) storage backend.
Link to this property
vector: boolean
Enable vector (embedding) storage backend.
Link to this property
Link to this property
indexing\_options: optional object {keyword\_tokenizer, use\_ocr }
keyword\_tokenizer: optional "porter"or "trigram"
Tokenizer used for keyword search indexing. porter provides word-level tokenization with Porter stemming (good for natural language queries). trigram enables character-level substring matching (good for partial matches, code, identifiers). Changing this triggers a full re-index. Defaults to porter.
One of the following:
"porter"
Link to this property
"trigram"
Link to this property
Link to this property
use\_ocr: optional boolean
Enables OCR ingestion for PDFs and images. Changing this triggers a full re-index. Defaults to false.
Link to this property
Link to this property
last\_activity: optional string
formatdate-time
Link to this property
max\_num\_results: optional number
maximum50
minimum1
Link to this property
metadata: optional object {created\_from\_aisearch\_wizard, worker\_domain }
created\_from\_aisearch\_wizard: optional boolean
Link to this property
worker\_domain: optional string
Link to this property
Link to this property
modified\_by: optional string
Link to this property
namespace: optional string
Link to this property
paused: optional boolean
Link to this property
public\_endpoint\_id: optional string
Link to this property
public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }
authorized\_hosts: optional array of string
Link to this property
chat\_completions\_endpoint: optional object {disabled }
disabled: optional boolean
Disable chat completions endpoint for this public endpoint
Link to this property
Link to this property
custom\_domains: optional array of string
Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged).
Link to this property
default\_domain\_enabled: optional boolean
When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true.
Link to this property
enabled: optional boolean
Link to this property
mcp: optional object {description, disabled }
description: optional string
Link to this property
disabled: optional boolean
Disable MCP endpoint for this public endpoint
Link to this property
Link to this property
rate\_limit: optional object {period\_ms, requests, technique }
period\_ms: optional number
maximum3600000
minimum60000
Link to this property
requests: optional number
minimum1
Link to this property
technique: optional "fixed"or "sliding"
One of the following:
"fixed"
Link to this property
"sliding"
Link to this property
Link to this property
Link to this property
search\_endpoint: optional object {disabled }
disabled: optional boolean
Disable search endpoint for this public endpoint
Link to this property
Link to this property
Link to this property
reranking: optional boolean
Link to this property
reranking\_model: optional string
Link to this property
retrieval\_options: optional object {boost\_by, keyword\_match\_mode }
boost\_by: optional array of object {field, direction }
Metadata fields to boost search results by. Each entry specifies a metadata field and an optional direction. Direction defaults to ‘asc’ for numeric/datetime fields and ‘exists’ for text/boolean fields. Fields must match ‘timestamp’ or a defined custom\_metadata field.
field: string
Metadata field name to boost by. Use ‘timestamp’ for document freshness, or any custom\_metadata field. Numeric and datetime fields support all four directions (asc, desc, exists, not\_exists); text/boolean fields only support exists/not\_exists.
maxLength64
minLength1
Link to this property
direction: optional "asc"or "desc"or "exists"or "not\_exists"
Boost direction. ‘desc’ = higher values rank higher (e.g. newer timestamps). ‘asc’ = lower values rank higher. ‘exists’ = boost chunks that have the field. ‘not\_exists’ = boost chunks that lack the field. Optional — defaults to ‘asc’ for numeric/datetime fields, ‘exists’ for text/boolean fields.
One of the following:
"asc"
Link to this property
"desc"
Link to this property
"exists"
Link to this property
"not\_exists"
Link to this property
Link to this property
Link to this property
keyword\_match\_mode: optional "and"or "or"
Controls which documents are candidates for BM25 scoring. ‘and’ restricts candidates to documents containing all query terms; ‘or’ includes any document containing at least one term, ranked by BM25 relevance. When omitted on an update, the existing stored value is preserved; when never set, search falls back to ‘and’.
One of the following:
"and"
Link to this property
"or"
Link to this property
Link to this property
Link to this property
rewrite\_model: optional string
A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model.
Link to this property
rewrite\_query: optional boolean
Link to this property
score\_threshold: optional number
maximum1
minimum0
Link to this property
source: optional string
Link to this property
source\_params: optional object {exclude\_items, include\_items, prefix, 2 more }
exclude\_items: optional array of string
List of path patterns to exclude. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /admin/\*\* matches /admin/users and /admin/settings/advanced). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
include\_items: optional array of string
List of path patterns to include. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /blog/\*\* matches /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact support to raise it.
Link to this property
prefix: optional string
Link to this property
r2\_jurisdiction: optional string
Link to this property
web\_crawler: optional object {discover\_options, parse\_options, parse\_type }
discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more }
Options for parse\_type ‘discover’, where Browser Run discovers URLs by link following and sitemaps. Ignored for ‘sitemap’.
depth: optional number
Maximum link-follow depth from the seed URL.
maximum100000
minimum1
Link to this property
include\_external\_links: optional boolean
Follow links that point outside the source domain. Must stay false — discover crawls are restricted to the zone you own.
Link to this property
include\_subdomains: optional boolean
Follow links to subdomains of the source host.
Link to this property
limit: optional number
Maximum number of pages to crawl (1-100000).
maximum100000
minimum1
Link to this property
max\_age: optional number
Maximum content age in seconds to accept (0–604800).
maximum604800
minimum0
Link to this property
source: optional "all"or "sitemaps"or "links"
Where the crawler looks for URLs: ‘sitemaps’ reads sitemap XML only, ‘links’ follows page links only, ‘all’ does both.
One of the following:
"all"
Link to this property
"sitemaps"
Link to this property
"links"
Link to this property
Link to this property
Link to this property
parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }
content\_selector: optional array of object {path, selector }
List of path-to-selector mappings for extracting specific content from crawled pages. Each entry pairs a URL glob pattern with a CSS selector. The first matching path wins. Only the matched HTML fragment is stored and indexed. Omit the field to disable content selection — empty arrays are rejected.
path: string
Glob pattern to match against the page URL path. Uses standard glob syntax: \* matches within a segment, \*\* crosses directories.
maxLength200
minLength1
Link to this property
selector: string
CSS selector to extract content from pages matching the path pattern. Must not contain disallowed characters (;, \`, $, {, }, ). Must target a single element; if multiple elements match, the selector is ignored and the full page is used.
maxLength200
minLength1
Link to this property
Link to this property
include\_headers: optional map\[string]
Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230 token characters (no spaces, colons, or control characters); values must be HTAB + printable ASCII (no CR/LF).
Link to this property
include\_images: optional boolean
Link to this property
specific\_sitemaps: optional array of string
List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’.
Link to this property
use\_browser\_rendering: optional boolean
Link to this property
Link to this property
parse\_type: optional "sitemap"or "discover"
How URLs are discovered. ‘sitemap’ reads XML sitemaps; ‘discover’ follows links recursively and requires the source to be a Verified zone on this account.
One of the following:
"sitemap"
Link to this property
"discover"
Link to this property
Link to this property
Link to this property
Link to this property
status: optional string
Link to this property
sync\_interval: optional 900or 1800or 3600or 5 more
Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800 (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).
One of the following:
900
Link to this property
1800
Link to this property
3600
Link to this property
7200
Link to this property
14400
Link to this property
21600
Link to this property
43200
Link to this property
86400
Link to this property
Link to this property
token\_id: optional string
formatuuid
Link to this property
type: optional "r2"or "web-crawler"
Source type. When omitted or null with a non-blank source, HTTP(S) URLs infer web-crawler and existing R2 bucket names infer r2. A missing or blank source without a type uses managed upload-only storage.
One of the following:
"r2"
Link to this property
"web-crawler"
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_delete_response%20%3E%20(schema)>)
InstanceStatsResponse object {completed, degraded, engine, 8 more }
completed: optional number
Link to this property
degraded: optional boolean
True when status counts are unavailable (e.g. legacy stats query exceeded D1 statement-size limit). Counts are omitted in this case.
Link to this property
engine: optional object {r2, vectorize }
Engine-specific metadata. Present only for managed (v3) instances.
r2: optional object {metadataSizeBytes, objectCount, payloadSizeBytes }
R2 bucket storage usage in bytes.
metadataSizeBytes: number
Link to this property
objectCount: number
Link to this property
payloadSizeBytes: number
Link to this property
Link to this property
vectorize: optional object {dimensions, vectorsCount }
Vectorize index metadata (dimensions, vector count).
dimensions: number
Link to this property
vectorsCount: number
Link to this property
Link to this property
Link to this property
error: optional number
Link to this property
file\_embed\_errors: optional map\[unknown]
Link to this property
index\_source\_errors: optional map\[unknown]
Link to this property
last\_activity: optional string
formatdate-time
Link to this property
outdated: optional number
Link to this property
queued: optional number
Link to this property
running: optional number
Link to this property
skipped: optional number
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_stats_response%20%3E%20(schema)>)
InstanceSearchResponse object {chunks, query\_kind, search\_query }
chunks: array of object {id, score, text, 3 more }
id: string
Link to this property
score: number
maximum1
minimum0
Link to this property
text: string
Link to this property
type: string
Link to this property
item: optional object {key, metadata, timestamp }
key: string
Link to this property
metadata: optional map\[unknown]
Link to this property
timestamp: optional number
Link to this property
Link to this property
scoring\_details: optional object {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method: optional "rrf"or "max"
One of the following:
"rrf"
Link to this property
"max"
Link to this property
Link to this property
keyword\_rank: optional number
Link to this property
keyword\_score: optional number
minimum0
Link to this property
reranking\_score: optional number
maximum1
minimum0
Link to this property
vector\_rank: optional number
Link to this property
vector\_score: optional number
maximum1
minimum0
Link to this property
Link to this property
Link to this property
query\_kind: "text"or "image"or "multimodal"
One of the following:
"text"
Link to this property
"image"
Link to this property
"multimodal"
Link to this property
Link to this property
search\_query: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_search_response%20%3E%20(schema)>)
InstanceChatCompletionsResponse object {choices, chunks, id, 2 more }
choices: array of object {message, index }
message: object {content, role }
content: stringor array of object {text, type } or object {image\_url, type } or object {file, type } or string
One of the following:
string
Link to this property
array of object {text, type } or object {image\_url, type } or object {file, type }
One of the following:
object {text, type }
text: string
minLength1
Link to this property
type: "text"
Link to this property
Link to this property
object {image\_url, type }
image\_url: object {url }
url: string
maxLength20971520
minLength1
Link to this property
Link to this property
type: "image\_url"
Link to this property
Link to this property
object {file, type }
file: object {filename, file\_data, file\_id }
filename: string
maxLength255
minLength1
Link to this property
file\_data: optional string
maxLength13981144
minLength1
Link to this property
file\_id: optional string
Link to this property
Link to this property
type: "file"
Link to this property
Link to this property
Link to this property
string
Link to this property
Link to this property
role: "system"or "developer"or "user"or 2 more
One of the following:
"system"
Link to this property
"developer"
Link to this property
"user"
Link to this property
"assistant"
Link to this property
"tool"
Link to this property
Link to this property
Link to this property
index: optional number
Link to this property
Link to this property
chunks: array of object {id, score, text, 3 more }
id: string
Link to this property
score: number
maximum1
minimum0
Link to this property
text: string
Link to this property
type: string
Link to this property
item: optional object {key, metadata, timestamp }
key: string
Link to this property
metadata: optional map\[unknown]
Link to this property
timestamp: optional number
Link to this property
Link to this property
scoring\_details: optional object {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method: optional "rrf"or "max"
One of the following:
"rrf"
Link to this property
"max"
Link to this property
Link to this property
keyword\_rank: optional number
Link to this property
keyword\_score: optional number
minimum0
Link to this property
reranking\_score: optional number
maximum1
minimum0
Link to this property
vector\_rank: optional number
Link to this property
vector\_score: optional number
maximum1
minimum0
Link to this property
Link to this property
Link to this property
id: optional string
Link to this property
model: optional string
Link to this property
object: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_chat_completions_response%20%3E%20(schema)>)
#### NamespacesInstancesJobs
##### [List Jobs](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/list)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs
##### [Create new job](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/create)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs
##### [Get a Job Details](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/get)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id}
##### [Cancel an indexing job.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/update)
PATCH/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id}
##### [List Job Logs](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/logs)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id}/logs
##### ModelsExpand Collapse
JobListResponse object {id, source, description, 4 more }
id: string
Link to this property
source: "user"or "schedule"
One of the following:
"user"
Link to this property
"schedule"
Link to this property
Link to this property
description: optional string
Link to this property
end\_reason: optional string
Link to this property
ended\_at: optional string
Link to this property
last\_seen\_at: optional string
Link to this property
started\_at: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_list_response%20%3E%20(schema)>)
JobCreateResponse object {id, source, description, 4 more }
id: string
Link to this property
source: "user"or "schedule"
One of the following:
"user"
Link to this property
"schedule"
Link to this property
Link to this property
description: optional string
Link to this property
end\_reason: optional string
Link to this property
ended\_at: optional string
Link to this property
last\_seen\_at: optional string
Link to this property
started\_at: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_create_response%20%3E%20(schema)>)
JobGetResponse object {id, source, description, 4 more }
id: string
Link to this property
source: "user"or "schedule"
One of the following:
"user"
Link to this property
"schedule"
Link to this property
Link to this property
description: optional string
Link to this property
end\_reason: optional string
Link to this property
ended\_at: optional string
Link to this property
last\_seen\_at: optional string
Link to this property
started\_at: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_get_response%20%3E%20(schema)>)
JobUpdateResponse object {id, source, description, 4 more }
id: string
Link to this property
source: "user"or "schedule"
One of the following:
"user"
Link to this property
"schedule"
Link to this property
Link to this property
description: optional string
Link to this property
end\_reason: optional string
Link to this property
ended\_at: optional string
Link to this property
last\_seen\_at: optional string
Link to this property
started\_at: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_update_response%20%3E%20(schema)>)
JobLogsResponse = array of object {id, created\_at, message, message\_type }
id: number
Link to this property
created\_at: number
Link to this property
message: string
Link to this property
message\_type: number
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_logs_response%20%3E%20(schema)>)
#### NamespacesInstancesItems
##### [Items List.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/list)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items
##### [Upload Item.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/upload)
POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items
##### [Create or Update Item.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/create_or_update)
PUT/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items
##### [Get Item.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/get)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}
##### [Sync Item.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/sync)
PATCH/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}
##### [Delete Item.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/delete)
DELETE/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}
##### [Download Item Content.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/download)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/download
##### [Item Logs.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/logs)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/logs
##### [List Item Chunks.](https://developers.cloudflare.com/api/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/chunks)
GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/chunks
##### ModelsExpand Collapse
ItemListResponse object {id, checksum, chunks\_count, 10 more }
id: string
Link to this property
checksum: string
Link to this property
chunks\_count: number
Link to this property
created\_at: string
formatdate-time
Link to this property
file\_size: number
Link to this property
key: string
Link to this property
last\_seen\_at: string
formatdate-time
Link to this property
metadata: map\[stringor numberor boolean]
Built-in, configured filterable, and retained source metadata for the item.
One of the following:
string
Link to this property
number
Link to this property
boolean
Link to this property
Link to this property
namespace: string
Link to this property
next\_action: "INDEX"or "DELETE"
One of the following:
"INDEX"
Link to this property
"DELETE"
Link to this property
Link to this property
source\_id: string
Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items.
Link to this property
status: "queued"or "running"or "completed"or 3 more
One of the following:
"queued"
Link to this property
"running"
Link to this property
"completed"
Link to this property
"error"
Link to this property
"skipped"
Link to this property
"outdated"
Link to this property
Link to this property
error: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_list_response%20%3E%20(schema)>)
ItemUploadResponse object {id, checksum, chunks\_count, 11 more }
id: string
Link to this property
checksum: string
Link to this property
chunks\_count: number
Link to this property
created\_at: string
formatdate-time
Link to this property
file\_size: number
Link to this property
key: string
Link to this property
last\_seen\_at: string
formatdate-time
Link to this property
metadata: map\[stringor numberor boolean]
Built-in, configured filterable, and retained source metadata for the item.
One of the following:
string
Link to this property
number
Link to this property
boolean
Link to this property
Link to this property
namespace: string
Link to this property
next\_action: "INDEX"or "DELETE"
One of the following:
"INDEX"
Link to this property
"DELETE"
Link to this property
Link to this property
source\_id: string
Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items.
Link to this property
status: "queued"or "running"or "completed"or 3 more
One of the following:
"queued"
Link to this property
"running"
Link to this property
"completed"
Link to this property
"error"
Link to this property
"skipped"
Link to this property
"outdated"
Link to this property
Link to this property
error: optional string
Link to this property
warnings: optional array of object {code, expected\_type, field } or object {code, field }
One of the following:
object {code, expected\_type, field }
code: "custom\_metadata\_value\_not\_indexed"
Link to this property
expected\_type: "text"or "number"or "boolean"or "datetime"
One of the following:
"text"
Link to this property
"number"
Link to this property
"boolean"
Link to this property
"datetime"
Link to this property
Link to this property
field: string
maxLength512
Link to this property
Link to this property
object {code, field }
code: "custom\_metadata\_field\_not\_filterable"
Link to this property
field: string
maxLength512
Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_upload_response%20%3E%20(schema)>)
ItemCreateOrUpdateResponse object {id, checksum, chunks\_count, 10 more }
id: string
Link to this property
checksum: string
Link to this property
chunks\_count: number
Link to this property
created\_at: string
formatdate-time
Link to this property
file\_size: number
Link to this property
key: string
Link to this property
last\_seen\_at: string
formatdate-time
Link to this property
metadata: map\[stringor numberor boolean]
Built-in, configured filterable, and retained source metadata for the item.
One of the following:
string
Link to this property
number
Link to this property
boolean
Link to this property
Link to this property
namespace: string
Link to this property
next\_action: "INDEX"or "DELETE"
One of the following:
"INDEX"
Link to this property
"DELETE"
Link to this property
Link to this property
source\_id: string
Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items.
Link to this property
status: "queued"or "running"or "completed"or 3 more
One of the following:
"queued"
Link to this property
"running"
Link to this property
"completed"
Link to this property
"error"
Link to this property
"skipped"
Link to this property
"outdated"
Link to this property
Link to this property
error: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_create_or_update_response%20%3E%20(schema)>)
ItemGetResponse object {id, checksum, chunks\_count, 10 more }
id: string
Link to this property
checksum: string
Link to this property
chunks\_count: number
Link to this property
created\_at: string
formatdate-time
Link to this property
file\_size: number
Link to this property
key: string
Link to this property
last\_seen\_at: string
formatdate-time
Link to this property
metadata: map\[stringor numberor boolean]
Built-in, configured filterable, and retained source metadata for the item.
One of the following:
string
Link to this property
number
Link to this property
boolean
Link to this property
Link to this property
namespace: string
Link to this property
next\_action: "INDEX"or "DELETE"
One of the following:
"INDEX"
Link to this property
"DELETE"
Link to this property
Link to this property
source\_id: string
Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items.
Link to this property
status: "queued"or "running"or "completed"or 3 more
One of the following:
"queued"
Link to this property
"running"
Link to this property
"completed"
Link to this property
"error"
Link to this property
"skipped"
Link to this property
"outdated"
Link to this property
Link to this property
error: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_get_response%20%3E%20(schema)>)
ItemSyncResponse object {id, checksum, chunks\_count, 10 more }
id: string
Link to this property
checksum: string
Link to this property
chunks\_count: number
Link to this property
created\_at: string
formatdate-time
Link to this property
file\_size: number
Link to this property
key: string
Link to this property
last\_seen\_at: string
formatdate-time
Link to this property
metadata: map\[stringor numberor boolean]
Built-in, configured filterable, and retained source metadata for the item.
One of the following:
string
Link to this property
number
Link to this property
boolean
Link to this property
Link to this property
namespace: string
Link to this property
next\_action: "INDEX"or "DELETE"
One of the following:
"INDEX"
Link to this property
"DELETE"
Link to this property
Link to this property
source\_id: string
Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items.
Link to this property
status: "queued"or "running"or "completed"or 3 more
One of the following:
"queued"
Link to this property
"running"
Link to this property
"completed"
Link to this property
"error"
Link to this property
"skipped"
Link to this property
"outdated"
Link to this property
Link to this property
error: optional string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_sync_response%20%3E%20(schema)>)
ItemDeleteResponse object {key }
key: string
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_delete_response%20%3E%20(schema)>)
ItemLogsResponse = array of object {action, chunkCount, errorType, 4 more }
action: string
Link to this property
chunkCount: number
Link to this property
errorType: string
Link to this property
fileKey: string
Link to this property
message: string
Link to this property
processingTimeMs: number
Link to this property
timestamp: string
formatdate-time
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_logs_response%20%3E%20(schema)>)
ItemChunksResponse = array of object {id, item, text, 2 more }
id: string
Link to this property
item: object {key, metadata, timestamp }
key: string
Link to this property
metadata: optional map\[unknown]
Link to this property
timestamp: optional number
Link to this property
Link to this property
text: string
Link to this property
end\_byte: optional number
Link to this property
start\_byte: optional number
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_chunks_response%20%3E%20(schema)>)