> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# BrainGraph

> BrainGraph builds a searchable knowledge graph from documents, recordings, web pages, and other source material for grounded AI workflows.

![BrainGraph logo](https://mintcdn.com/composio-preview/PudKL42NVsy5O-ND/images/toolkits/brain_graph.svg?fit=max\&auto=format\&n=PudKL42NVsy5O-ND\&q=85\&s=4d49b99c0c40ca25fb1fb2ea83413702)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 10
* **Triggers:** 0
* **Slug:** `BRAIN_GRAPH`
* **Version:** 20261101\_00

## Tools

> [accordion] Get Document Progress
>
> **Slug:** `BRAIN_GRAPH_GET_DOCUMENT_PROGRESS`
>
> Get the current transcription, processing, and analysis status for a BrainGraph document. Poll until transcript.status is analyzed; analysis is null while processing is incomplete.
>
> #### Input Parameters
>
> **document\_id** `integer` *required*
>
> Document ID returned by a BrainGraph upload or ingestion tool.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Ingest Web Page
>
> **Slug:** `BRAIN_GRAPH_INGEST_WEB_PAGE`
>
> Fetch readable content from a public web page and queue it for BrainGraph ingestion. This creates persistent data and consumes upload and URL-submission quota. After a timeout or other ambiguous failure, check for the document before retrying to avoid a duplicate and additional quota use.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Public HTTP(S) web-page URL to fetch. BrainGraph rejects private, loopback, and metadata-service addresses, including after redirects.
>
> **notes** `string`
>
> Optional context to guide extraction and later retrieval.
>
> **conversation\_date** `string`
>
> ISO 8601 date associated with the page content.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Ingest YouTube Video
>
> **Slug:** `BRAIN_GRAPH_INGEST_YOUTUBE_VIDEO`
>
> Submit a YouTube video for metadata, transcript, and speaker processing; the result may only confirm that processing was queued. Fresh ingestion creates persistent data and counts against the upload cap, while previously ingested videos return an existing record; submissions are rate-limited.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> YouTube watch, Shorts, embed, live, or youtu.be URL.
>
> **language** `string`
>
> Optional two-letter caption-track language code, such as en or es.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Brains
>
> **Slug:** `BRAIN_GRAPH_LIST_BRAINS`
>
> List the connected BrainGraph account's knowledge brains and identify the default brain for filtering or targeting other tools. Accounts without multiple brains enabled receive a 404 instead of a brain list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Documents
>
> **Slug:** `BRAIN_GRAPH_LIST_DOCUMENTS`
>
> List BrainGraph documents newest first, optionally matching filenames or notes, including failed ingestions, and restricting results to selected brains. Returns one page at a time.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum documents in this page (1-100).
>
> **query** `string`
>
> Case-insensitive substring to match against document filenames and notes.
>
> **cursor** `string`
>
> Opaque continuation cursor returned by a previous call; omit for the first page.
>
> **brain\_ids** `array`
>
> Brain IDs to include; omit to list documents across all brains.
>
> **include\_failed** `boolean`
>
> Include documents whose ingestion failed.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Graph Patterns
>
> **Slug:** `BRAIN_GRAPH_LIST_PATTERNS`
>
> Find recurring relationship-chain patterns in the connected BrainGraph knowledge graph, subject to a minimum occurrence count.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum patterns to return. BrainGraph does not provide a continuation mechanism for this endpoint.
>
> **min\_frequency** `integer`
>
> Minimum number of occurrences required for a recurring pattern.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Resolve Entity
>
> **Slug:** `BRAIN_GRAPH_RESOLVE_ENTITY`
>
> Resolve an entity name to a canonical BrainGraph record. If there is no single match, return an explicit ambiguous or not-found result rather than treating it as an HTTP error.
>
> #### Input Parameters
>
> **entity\_name** `string` *required*
>
> Entity name to resolve, such as a person, organization, project, or concept.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Brain
>
> **Slug:** `BRAIN_GRAPH_SEARCH_BRAIN`
>
> Search facts in the connected account's BrainGraph knowledge graph using a natural-language question, optionally restricted to selected brains.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Natural-language question or topic to search for in the knowledge graph.
>
> **brain\_ids** `array`
>
> Brain IDs to search. Omit to search all brains; this selection is ignored on single-brain accounts.
>
> **num\_results** `integer`
>
> Maximum number of matching facts to return (1-50).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Transcribe Audio
>
> **Slug:** `BRAIN_GRAPH_TRANSCRIBE_AUDIO`
>
> Upload an audio file or submit a direct public audio URL for diarized transcription and graph ingestion. This creates persistent data and consumes upload and transcription allowance. Do not retry automatically after an ambiguous failure because a retry can create a duplicate document.
>
> #### Input Parameters
>
> **file** `object`
>
> MP3, M4A, WAV, OGG, OGA, OPUS, WEBM, AAC, FLAC, or MP4 file supplied by the caller, up to approximately 150 MB.
>
> **notes** `string`
>
> Optional transcription or extraction context.
>
> **brain\_id** `string`
>
> Target brain ID; omit for the default Personal Brain.
>
> **filename** `string`
>
> Optional display filename for an uploaded file.
>
> **audio\_url** `string`
>
> Direct public HTTP(S) URL of an audio file, not a web player page. Provide exactly one of audio\_url or file.
>
> **conversation\_date** `string`
>
> ISO 8601 date associated with the recording.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Document
>
> **Slug:** `BRAIN_GRAPH_UPLOAD_DOCUMENT`
>
> Upload a document file supplied by the caller or plain text and queue it for BrainGraph ingestion. This creates persistent data and consumes the account's upload allowance. After a timeout or other ambiguous failure, check for the document before retrying to avoid a duplicate and additional quota use.
>
> #### Input Parameters
>
> **file** `object`
>
> PDF, DOCX, PPTX, TXT, MD, HTML, or EML file supplied by the caller, up to approximately 35 MB.
>
> **notes** `string`
>
> Optional context to guide extraction and later retrieval.
>
> **content** `string`
>
> Plain-text content to ingest through the JSON endpoint. Provide exactly one of content or file.
>
> **brain\_id** `string`
>
> Target brain ID; omit to use the default Personal Brain.
>
> **filename** `string`
>
> Display filename. Required when content is provided and optional as an override when a file is provided.
>
> **conversation\_date** `string`
>
> ISO 8601 date associated with the document or conversation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
