Wrangler CLI

`ai-search list`

List all AI Search instances

npx wrangler ai-search list

--namespacestring alias: --ndefault: default
The namespace to list instances from.
--jsonboolean default: false
Return output as clean JSON
--pagenumber default: 1
Page number of the results, can configure page size using "per-page"
--per-pagenumber
Number of instances to show per page

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search create`

Create a new AI Search instance

npx wrangler ai-search create [NAME]

[NAME]string required
The name of the AI Search instance to create (must be unique within its namespace).
--namespacestring alias: --n
The namespace to create the instance in.
--sourcestring
Data source identifier (R2 bucket name or web URL).
--typestring
The source type for the instance.
--parse-typestring
How website URLs are discovered (--type web-crawler only). 'sitemap' reads XML sitemaps; 'discover' follows links recursively. Defaults to 'sitemap'.
--source-jurisdictionstring
The R2 jurisdiction of the source bucket (e.g. eu, fedramp). Only valid with --type r2; omit for no specific jurisdiction.
--embedding-modelstring
Embedding model to use.
--generation-modelstring
LLM model for chat completions.
--chunk-sizenumber
Chunk size for document splitting (min: 64).
--chunk-overlapnumber
Overlap between document chunks.
--max-num-resultsnumber
Maximum search results per query.
--rerankingboolean
Enable reranking of search results.
--reranking-modelstring
Model to use for reranking.
--hybrid-searchboolean
Enable hybrid (keyword + vector) search.
--cacheboolean
Enable response caching.
--score-thresholdnumber
Minimum relevance score threshold (0-1).
--prefixstring
R2 key prefix to scope indexing.
--include-itemsarray
Glob patterns for items to include.
--exclude-itemsarray
Glob patterns for items to exclude.
--custom-metadataarray
Custom metadata fields, formatted as 'field_name:data_type'. data_type must be one of: text, number, boolean, datetime. Repeat the flag for multiple fields (e.g. --custom-metadata title:text --custom-metadata views:number).
--custom-metadata-schemastring
Path to a JSON file describing custom metadata fields. The file must contain an array of { "field_name", "data_type" } objects. Mutually exclusive with --custom-metadata.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search get`

Get details of an AI Search instance

npx wrangler ai-search get [NAME]

[NAME]string required
The name of the AI Search instance.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search update`

Update an AI Search instance configuration

npx wrangler ai-search update [NAME]

[NAME]string required
The name of the AI Search instance to update.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--embedding-modelstring
Update the embedding model.
--generation-modelstring
Update the LLM model for chat completions.
--chunk-sizenumber
Update the chunk size.
--chunk-overlapnumber
Update the chunk overlap.
--max-num-resultsnumber
Update max search results per query.
--rerankingboolean
Enable or disable reranking.
--reranking-modelstring
Update the reranking model.
--hybrid-searchboolean
Enable or disable hybrid search.
--cacheboolean
Enable or disable caching.
--score-thresholdnumber
Update the minimum relevance score threshold (0-1).
--pausedboolean
Pause or resume the instance.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search delete`

Delete an AI Search instance

npx wrangler ai-search delete [NAME]

[NAME]string required
The name of the AI Search instance to delete.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--forceboolean alias: --ydefault: false
Skip confirmation

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search stats`

Get usage statistics for an AI Search instance

npx wrangler ai-search stats [NAME]

[NAME]string required
The name of the AI Search instance.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search search`

Execute a semantic search query against an AI Search instance

npx wrangler ai-search search [NAME]

[NAME]string required
The name of the AI Search instance.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--querystring required
The search query text.
--max-num-resultsnumber
Override maximum number of results.
--score-thresholdnumber
Override minimum relevance score (0-1).
--rerankingboolean
Override reranking setting.
--filterarray
Metadata filter as key=value (repeatable, e.g. --filter type=docs --filter lang=en).
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search namespace list`

List all AI Search namespaces

npx wrangler ai-search namespace list

--jsonboolean default: false
Return output as clean JSON
--pagenumber default: 1
Page number of the results, can configure page size using "per-page"
--per-pagenumber
Number of namespaces to show per page
--searchstring
Filter namespaces whose name or description contains this string (case-insensitive).

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search namespace create`

Create a new AI Search namespace

npx wrangler ai-search namespace create [NAME]

[NAME]string required
The name of the AI Search namespace to create.
--descriptionstring
Optional description for the namespace (max 256 chars).
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search namespace get`

Get details of an AI Search namespace

npx wrangler ai-search namespace get [NAME]

[NAME]string required
The name of the AI Search namespace.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search namespace update`

Update an AI Search namespace

npx wrangler ai-search namespace update [NAME]

[NAME]string required
The name of the AI Search namespace to update.
--descriptionstring
Updated description for the namespace (max 256 chars).
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search namespace delete`

Delete an AI Search namespace

npx wrangler ai-search namespace delete [NAME]

[NAME]string required
The name of the AI Search namespace to delete.
--forceboolean alias: --ydefault: false
Skip confirmation

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search jobs list`

List indexing jobs for an AI Search instance

npx wrangler ai-search jobs list [NAME]

[NAME]string required
The name of the AI Search instance.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--jsonboolean default: false
Return output as clean JSON
--pagenumber default: 1
Page number of the results, can configure page size using "per-page"
--per-pagenumber
Number of jobs to show per page

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search jobs create`

Trigger a new indexing job for an AI Search instance

npx wrangler ai-search jobs create [NAME]

[NAME]string required
The name of the AI Search instance.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--descriptionstring
Optional description for the indexing job.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search jobs get`

Get details of an AI Search indexing job

npx wrangler ai-search jobs get [NAME] [JOB-ID]

[NAME]string required
The name of the AI Search instance.
[JOB-ID]string required
The ID of the indexing job.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--jsonboolean default: false
Return output as clean JSON

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search jobs cancel`

Cancel an in-progress AI Search indexing job

npx wrangler ai-search jobs cancel [NAME] [JOB-ID]

[NAME]string required
The name of the AI Search instance.
[JOB-ID]string required
The ID of the indexing job to cancel.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--forceboolean alias: --ydefault: false
Skip confirmation

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile

`ai-search jobs logs`

List log entries for an AI Search indexing job

npx wrangler ai-search jobs logs [NAME] [JOB-ID]

[NAME]string required
The name of the AI Search instance.
[JOB-ID]string required
The ID of the indexing job.
--namespacestring alias: --ndefault: default
The namespace the instance belongs to.
--jsonboolean default: false
Return output as clean JSON
--pagenumber default: 1
Page number of the results, can configure page size using "per-page"
--per-pagenumber
Number of log entries to show per page

Global flags

--vboolean alias: --version
Show version number
--cwdstring
Run as if Wrangler was started in the specified directory instead of the current working directory
--configstring alias: --c
Path to Wrangler configuration file
--envstring alias: --e
Environment to use for operations, and for selecting .env and .dev.vars files
--env-filestring
Path to an .env file to load - can be specified multiple times - values from earlier files are overridden by values in later files
--experimental-provisionboolean aliases: --x-provisiondefault: true
Experimental: Enable automatic resource provisioning
--experimental-auto-createboolean alias: --x-auto-createdefault: true
Automatically provision draft bindings with new resources
--install-skillsboolean default: false
Install Cloudflare skills for detected AI coding agents before running the command
--profilestring
Use a specific auth profile