> For the complete documentation index, see [llms.txt](https://data-programs.gitbook.io/singularity/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://data-programs.gitbook.io/singularity/cli-reference/run/content-provider.md).

# Content Provider

{% code fullWidth="true" %}

```
NAME:
   singularity run content-provider - Start a content provider that serves retrieval requests

USAGE:
   singularity run content-provider [command options]

OPTIONS:
   --help, -h        show help
   --no-automigrate  skip automatic database migration and correctness checks on startup; only use if you run 'admin init' on every upgrade or manually before starting daemons (default: false)

   HTTP IPFS Gateway

   --enable-http-ipfs              Enable trustless IPFS gateway on /ipfs/ (default: true)
   --ipfs-cache-blocks value       Block cache capacity in blocks (~1MiB each); 0 sizes it to max-backend-reads * span-blocks * (1 + prefetch-spans) (default: derived)
   --ipfs-max-backend-reads value  Max concurrent source storage reads across all requests (default: 64)
   --ipfs-prefetch-spans value     Spans prefetched ahead on sequential access (default: 2)
   --ipfs-read-timeout value       Max duration of a single backend span read once it holds a connection slot (default: 2m0s)
   --ipfs-span-blocks value        Blocks (~1MiB each) fetched per backend read (default: 8)

   HTTP Piece Metadata Retrieval

   --enable-http-piece-metadata  Enable HTTP Piece Metadata, this is to be used with the download server (default: true)

   HTTP Piece Retrieval

   --enable-http-piece, --enable-http  Enable HTTP Piece retrieval (default: true)

   HTTP Retrieval

   --http-bind value  Address to bind the HTTP server to (default: "127.0.0.1:7777")

```

{% endcode %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://data-programs.gitbook.io/singularity/cli-reference/run/content-provider.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.