> For the complete documentation index, see [llms.txt](https://help.blotato.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.blotato.com/start-with-an-ai-agent/llm/sources.md).

# Source extraction requests

Submit REST source extraction with an explicit source type and stop on completed or failed results.

Compact reference for agents making REST requests. All endpoint paths below are relative to `https://backend.blotato.com/v2`. For task instructions, read the [workflow guide](/agent-workflows/agent-workflows/sources.md). For tool calls, use the [MCP reference](/start-with-an-ai-agent/mcp/tools.md).

## Extracting content (sources)

```
POST /source-resolutions-v3

Body MUST contain a "source" object. Do NOT put fields at the top level.

source.sourceType (REQUIRED, no auto-detection):
- "text"             - Transform raw text (uses source.text)
- "article"          - Extract from article URL (uses source.url)
- "youtube"          - Extract from YouTube URL (uses source.url)
- "twitter"          - Extract from Twitter/X URL (uses source.url)
- "tiktok"           - Extract from TikTok URL (uses source.url)
- "perplexity-query" - AI web research (uses source.text)
- "audio"            - Extract from audio URL (uses source.url)
- "pdf"              - Extract from PDF URL (uses source.url)

CORRECT:
{
  "source": {
    "sourceType": "youtube",
    "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
  }
}

WRONG (missing "source" wrapper):
{ "sourceType": "youtube", "url": "..." }

Response: { "id": "src_123" }
Save response.id. Acceptance is not extraction completion.

Poll: GET /source-resolutions-v3/{id}
Wait at least 10 seconds between checks, within a bounded client wait budget.
Status values: "queued" | "processing" | "completed" | "failed"
"queued" or "processing": continue checking the saved ID within the wait budget.
"completed": response includes "content" and "title". Use the extracted content.
"failed": stop and report response.message. Do not continue as if content was extracted.
Timeout: report the saved ID and pending state. Resume lookup, not another create request.
```

Extraction does not generate media or publish a post. Continue only with the work requested by the user. See [Extract and adapt source content](/agent-workflows/agent-workflows/sources.md).

Return to the [agent reference index](/start-with-an-ai-agent/llm.md).


---

# 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://help.blotato.com/start-with-an-ai-agent/llm/sources.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.