> ## 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.

# Writer

> Writer is a full-stack generative AI platform for enterprises, offering tools to build and deploy AI applications integrated with their suite of LLMs, graph-based RAG tools, and AI guardrails.

![Writer logo](https://mintcdn.com/composio-preview/DMB8UrgJmE7r-ZQ5/images/toolkits/writer.svg?fit=max\&auto=format\&n=DMB8UrgJmE7r-ZQ5\&q=85\&s=933453f49c62487aac5ea81d71c13867)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 23
* **Triggers:** 0
* **Slug:** `WRITER`
* **Version:** 20261101\_00

## Tools

> [accordion] Add File to Knowledge Graph
>
> **Slug:** `WRITER_ADD_FILE_TO_GRAPH`
>
> Tool to add a file to a knowledge graph for indexing and retrieval. Use when you need to add an uploaded file to an existing knowledge graph for RAG applications.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The unique identifier of the file to add to the knowledge graph
>
> **graph\_id** `string` *required*
>
> The unique identifier of the knowledge graph to add the file to
>
> #### 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] Analyze Images
>
> **Slug:** `WRITER_ANALYZE_IMAGES`
>
> Tool to analyze images using Writer's vision capabilities. Use when you need image understanding, text extraction from images, or visual question answering. Images must be uploaded via POST /v1/files before analysis.
>
> #### Input Parameters
>
> **model** `string` *required*
>
> The vision model to use for image analysis. Specify 'palmyra-vision' for Writer's vision model.
>
> **prompt** `string` *required*
>
> Text prompt describing what to analyze in the images. Use \{\{image\_name}} placeholders to reference images from the variables array.
>
> **variables** `array` *required*
>
> Array of image variables with their names and file IDs. Each image must be uploaded first via POST /v1/files to obtain a file\_id.
>
> #### 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] Ask Question to Knowledge Graph
>
> **Slug:** `WRITER_ASK_QUESTION_TO_KNOWLEDGE_GRAPH`
>
> Send a question to specified Knowledge Graphs, with optional context. Responses containing file sources may fail validation because the tool requires a URL for each source.
>
> #### Input Parameters
>
> **context** `array`
>
> Optional list of context key/value pairs to provide additional information
>
> **question** `string` *required*
>
> The question to ask the knowledge graph
>
> **graph\_ids** `array` *required*
>
> List of knowledge graph identifiers to target
>
> #### 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] Chat Completion
>
> **Slug:** `WRITER_CHAT_COMPLETION`
>
> Generate a non-streaming chat completion from a conversation history using a specified model.
>
> #### Input Parameters
>
> **n** `integer`
>
> Number of chat completion choices to generate
>
> **stop** `string`
>
> Up to 4 sequences where the API will stop generating further tokens
>
> **model** `string`
>
> Model identifier to use for the chat completion
>
> **top\_p** `number`
>
> Nucleus sampling probability threshold
>
> **stream** `boolean`
>
> Whether to stream back partial progress as server-sent events
>
> **messages** `array` *required*
>
> Conversation history in order. Required.
>
> **max\_tokens** `integer`
>
> Maximum number of tokens to generate
>
> **temperature** `number`
>
> Sampling temperature; higher values produce more random output
>
> **presence\_penalty** `number`
>
> Penalty for new tokens based on presence in the text so far
>
> **frequency\_penalty** `number`
>
> Penalty for new tokens based on their frequency in the text so far
>
> #### 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] Create Knowledge Graph
>
> **Slug:** `WRITER_CREATE_KNOWLEDGE_GRAPH`
>
> Create an empty Knowledge Graph that files can be added to. It is org-wide with an organization-scoped API key and assigned to the key's team with a team-scoped key.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the knowledge graph
>
> **description** `string`
>
> A short description clarifying the graph's purpose for the model
>
> #### 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] Delete File
>
> **Slug:** `WRITER_DELETE_FILE`
>
> Tool to delete a file by its ID. Use when you need to permanently remove a file from Writer with no recovery option available.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The unique identifier of the file to delete.
>
> #### 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] Delete Graph
>
> **Slug:** `WRITER_DELETE_GRAPH`
>
> Tool to delete a knowledge graph by its ID. Use when you need to remove a graph after confirming its identifier.
>
> #### Input Parameters
>
> **graph\_id** `string` *required*
>
> Unique identifier of the graph to delete.
>
> #### 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] Detect AI Content
>
> **Slug:** `WRITER_DETECT_AI_CONTENT`
>
> Analyze text for AI-generated content and return a classification label and score. Input must contain at least 350 characters excluding newline characters.
>
> #### Input Parameters
>
> **input** `string` *required*
>
> The text to analyze for AI content. Must have at least 350 characters (excluding newline characters).
>
> #### 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] Download File
>
> **Slug:** `WRITER_DOWNLOAD_FILE`
>
> Tool to download the binary content of a file. Use when you need to retrieve file data from the Writer platform. The response contains the file in its original format.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The ID of the file to download.
>
> #### 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] Get File
>
> **Slug:** `WRITER_GET_FILE`
>
> Tool to retrieve detailed information about a specific file by its ID. Use when you need to check a file's metadata, processing status, or associated knowledge graphs.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The ID of the file to retrieve
>
> #### 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 Applications
>
> **Slug:** `WRITER_LIST_APPLICATIONS`
>
> List a page of no-code agent applications, with an optional page size and cursor for retrieving subsequent pages.
>
> #### Input Parameters
>
> **after** `string`
>
> Cursor for pagination. Use the last\_id from a previous response to get the next page.
>
> **limit** `integer`
>
> Maximum number of applications to return (for pagination).
>
> #### 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 Files
>
> **Slug:** `WRITER_LIST_FILES`
>
> Tool to list all uploaded files. Use when you need to retrieve a paginated set of user files, optionally filtered by status, graph, or type. Use after uploading files to inspect available files.
>
> #### Input Parameters
>
> **after** `string`
>
> Cursor for returning the next page of results; set to the last file ID of the prior page.
>
> **limit** `integer`
>
> Max number of files to return (1-100). Defaults to 50.
>
> **order** `string ("asc" | "desc")`
>
> Sorting order for results: 'asc' (oldest first) or 'desc' (newest first).
>
> **before** `string`
>
> Cursor for returning the previous page of results; set to the first file ID of the prior page.
>
> **status** `string ("in_progress" | "completed" | "failed")`
>
> Filter files by status.
>
> **graph\_id** `string`
>
> Filter files by a specific knowledge graph ID.
>
> **file\_types** `string`
>
> Comma-separated list of file extensions to include, e.g. 'pdf,docx,jpg'.
>
> #### 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 Knowledge Graphs
>
> **Slug:** `WRITER_LIST_GRAPHS`
>
> List a page of Writer Knowledge Graphs. With an organization-scoped API key, results include only org-wide graphs; with a team-scoped key, they include only that team's graphs.
>
> #### Input Parameters
>
> **after** `string`
>
> ID of last object from previous page for forward pagination.
>
> **limit** `integer`
>
> Number of items per page. Default: 50, max: 100.
>
> **order** `string`
>
> Sort order: 'asc' or 'desc'. Default: 'desc'.
>
> **before** `string`
>
> ID of first object from previous page for backward pagination.
>
> #### 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 Models
>
> **Slug:** `WRITER_LIST_MODELS`
>
> Tool to list all available language models. Use when you need to discover which models can be used for completions.
>
> #### 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] Medical Text Comprehension
>
> **Slug:** `WRITER_MEDICAL_COMPREHEND`
>
> Extract medical entities and any returned concepts from unstructured clinical text using the Entities response type.
>
> #### Input Parameters
>
> **text** `string` *required*
>
> The clinical or medical text to analyze (max 20,000 characters).
>
> #### 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] Parse PDF
>
> **Slug:** `WRITER_PARSE_PDF`
>
> Parse a previously uploaded PDF into text or markdown using Writer's deprecated PDF parser endpoint, which Writer scheduled for removal on December 22, 2025.
>
> #### Input Parameters
>
> **format** `string ("text" | "markdown")` *required*
>
> Output format for the parsed PDF content: 'text' for plain text or 'markdown' for markdown-formatted output.
>
> **file\_id** `string` *required*
>
> The ID of the PDF file to parse. Obtained from a prior file upload.
>
> #### 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] Remove File From Graph
>
> **Slug:** `WRITER_REMOVE_FILE_FROM_GRAPH`
>
> Tool to remove a file from a Knowledge Graph. Use when you need to unlink a specific file from a graph by providing both graph and file identifiers.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The ID of the file to remove from the graph.
>
> **graph\_id** `string` *required*
>
> The ID of the graph from which to remove the file.
>
> #### 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] Retrieve Knowledge Graph
>
> **Slug:** `WRITER_RETRIEVE_GRAPH`
>
> Retrieve a Writer Knowledge Graph by its ID to inspect details of an existing graph, such as its name, description, creation time, and file processing status. Access is subject to the scope of the API key.
>
> #### Input Parameters
>
> **graph\_id** `string` *required*
>
> Unique identifier of the knowledge graph to retrieve
>
> #### 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] Text Generation
>
> **Slug:** `WRITER_TEXT_GENERATION`
>
> Tool to generate text based on a given prompt. Use when you need model-driven completions after crafting a prompt.
>
> #### Input Parameters
>
> **stop** `array`
>
> Sequences where the API will stop generating.
>
> **model** `string` *required*
>
> The name of the model to use for generation. Available models include: palmyra-x-003-instruct, palmyra-x4, palmyra-x5, palmyra-creative, palmyra-fin, palmyra-med, palmyra-vision.
>
> **top\_p** `number`
>
> Nucleus sampling parameter between 0 and 1.
>
> **prompt** `string` *required*
>
> The text prompt for the model.
>
> **max\_tokens** `integer`
>
> Maximum number of tokens in the generated output.
>
> **temperature** `number`
>
> Sampling temperature between 0 and 2.
>
> #### 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] Translate Text
>
> **Slug:** `WRITER_TRANSLATE_TEXT`
>
> Tool to translate text from one language to another with support for formality, length control, and profanity masking. Use when you need to convert text between different languages.
>
> #### Input Parameters
>
> **text** `string` *required*
>
> The text to translate (maximum 100,000 words)
>
> **model** `string ("palmyra-translate")` *required*
>
> Translation model to use
>
> **formality** `boolean` *required*
>
> Apply formal language style to the translation (support varies by language)
>
> **length\_control** `boolean` *required*
>
> Control the length of the output translation (support varies by language)
>
> **mask\_profanity** `boolean` *required*
>
> Mask profane words in the translated text (support varies by language)
>
> **source\_language\_code** `string` *required*
>
> Source language ISO-639-1 code (e.g., en for English, es for Spanish, fr for French)
>
> **target\_language\_code** `string` *required*
>
> Target language ISO-639-1 code (e.g., en for English, es for Spanish, fr for French)
>
> #### 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] Update Knowledge Graph
>
> **Slug:** `WRITER_UPDATE_GRAPH`
>
> Tool to update an existing knowledge graph. Use after confirming the graph\_id. Specify at least one of name or description to modify.
>
> #### Input Parameters
>
> **name** `string`
>
> New name for the graph
>
> **graph\_id** `string` *required*
>
> The unique identifier of the graph to update
>
> **description** `string`
>
> New description for the graph
>
> #### 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 File
>
> **Slug:** `WRITER_UPLOAD_FILE`
>
> Submit a file to Writer using a multipart upload for file-based operations.
>
> #### Input Parameters
>
> **file** `object` *required*
>
> The file to upload.
>
> #### 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] Web Search
>
> **Slug:** `WRITER_WEB_SEARCH`
>
> Tool to perform a web search. Use when you need relevant web page results for a given query.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> The search query string
>
> **topic** `string ("general" | "news")`
>
> Search category: 'general' (default) for broader web search, 'news' for current events and news articles
>
> **time\_range** `string ("day" | "week" | "month" | "year" | "d" | "w" | "m" | "y")`
>
> Content recency filter: 'day'/'d', 'week'/'w', 'month'/'m', or 'year'/'y'
>
> **max\_results** `integer`
>
> Maximum number of results to return (cannot exceed 20)
>
> **search\_depth** `string ("basic" | "advanced")`
>
> Search depth: 'basic' (default, fewer results) or 'advanced' (deeper search)
>
> **include\_answer** `boolean`
>
> Include a generated answer based on results (default: true)
>
> **exclude\_domains** `array`
>
> Exclude specific domains from results
>
> **include\_domains** `array`
>
> Restrict results to specific domains
>
> #### 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
