# MKA1

## Docs

- [Execute a saved agent](https://docs.mka1.com/api-reference/agent-runs/execute-a-saved-agent.md)
- [List runs for an agent](https://docs.mka1.com/api-reference/agent-runs/list-runs-for-an-agent.md)
- [Retrieve an agent run](https://docs.mka1.com/api-reference/agent-runs/retrieve-an-agent-run.md)
- [Create an agent](https://docs.mka1.com/api-reference/agents/create-an-agent.md)
- [Delete an agent](https://docs.mka1.com/api-reference/agents/delete-an-agent.md)
- [List agents](https://docs.mka1.com/api-reference/agents/list-agents.md)
- [Retrieve an agent](https://docs.mka1.com/api-reference/agents/retrieve-an-agent.md)
- [Update an agent](https://docs.mka1.com/api-reference/agents/update-an-agent.md)
- [Exchange API key for a JWT token](https://docs.mka1.com/api-reference/api-key/exchange-api-key-for-a-jwt-token.md): Exchange an API key for a JWT token
- [Cancel a batch](https://docs.mka1.com/api-reference/batches/cancel-a-batch.md): Cancels an in-progress batch. The batch status changes to cancelling, and remaining requests will not be processed.
- [Create a batch](https://docs.mka1.com/api-reference/batches/create-a-batch.md): Creates and executes a batch from an uploaded JSONL file of requests. Each line must have custom_id, method, url, and body fields.
- [Get a batch](https://docs.mka1.com/api-reference/batches/get-a-batch.md): Retrieves a batch by its ID.
- [List batches](https://docs.mka1.com/api-reference/batches/list-batches.md): Returns a paginated list of batches owned by the authenticated user.
- [Proxy Browser Port Request](https://docs.mka1.com/api-reference/browser/proxy-browser-port-request.md): Proxy an HTTP request to an exposed browser-session port through the gateway. Use the URL returned by `GET /sessions/{session_id}/url` as the base, then append CDP subpaths such as `json/version` or `json/list`. This low-level proxy is primarily intended for browser sessions on port `9222`.
- [[Deprecated] Chat completions for OpenAI SDK/client usage](https://docs.mka1.com/api-reference/chat-completions/[deprecated]-chat-completions-for-openai-sdkclient-usage.md): **Deprecated: Use the Responses API (`/api/v1/llm/responses`) instead.** OpenAI-compatible chat completion endpoint designed for use with the official OpenAI client libraries (Python, Node.js, etc.). Supports both streaming and non-streaming requests by setting the `stream` parameter. This endpoint…
- [[Deprecated] Streaming chat completions for generated SDK usage](https://docs.mka1.com/api-reference/chat-completions/[deprecated]-streaming-chat-completions-for-generated-sdk-usage.md): **Deprecated: Use the Responses API (`/api/v1/llm/responses`) instead.** Streaming chat completion endpoint designed for use with the generated TypeScript/JavaScript SDK from the OpenAPI specification. This endpoint uses ORPC's native streaming via async generators and returns Server-Sent Events (SS…
- [Create a conversation](https://docs.mka1.com/api-reference/conversations/create-a-conversation.md): Create a conversation to store and retrieve conversation state across Response API calls.
- [Create conversation items](https://docs.mka1.com/api-reference/conversations/create-conversation-items.md): Create items in a conversation with the given ID.
- [Delete a conversation](https://docs.mka1.com/api-reference/conversations/delete-a-conversation.md): Delete a conversation. Items in the conversation will not be deleted.
- [Delete a conversation item](https://docs.mka1.com/api-reference/conversations/delete-a-conversation-item.md): Delete an item from a conversation with the given ID.
- [Delete multiple conversation items](https://docs.mka1.com/api-reference/conversations/delete-multiple-conversation-items.md): Delete multiple items from a conversation with the given ID.
- [List conversation items](https://docs.mka1.com/api-reference/conversations/list-conversation-items.md): List all items for a conversation with the given ID.
- [List conversations](https://docs.mka1.com/api-reference/conversations/list-conversations.md): List all conversations for the authenticated user with pagination support.
- [Retrieve a conversation](https://docs.mka1.com/api-reference/conversations/retrieve-a-conversation.md): Get a conversation by ID.
- [Retrieve a conversation item](https://docs.mka1.com/api-reference/conversations/retrieve-a-conversation-item.md): Get a single item from a conversation with the given IDs.
- [Update a conversation](https://docs.mka1.com/api-reference/conversations/update-a-conversation.md): Update a conversation's metadata.
- [Create text embeddings](https://docs.mka1.com/api-reference/embeddings/create-text-embeddings.md): Generates vector embeddings for single or multiple text inputs. Returns floating-point vectors along with token usage statistics.
- [List available embedding models](https://docs.mka1.com/api-reference/embeddings/list-available-embedding-models.md): Returns a list of available embedding models with their limits. Use this endpoint to discover which models are available and their constraints (batch size, input length) before making embedding requests.
- [Run Code](https://docs.mka1.com/api-reference/execution/run-code.md): Execute source code in the session workspace using a supported runtime and return the execution result.
- [Run Command](https://docs.mka1.com/api-reference/execution/run-command.md): Run a command in the session workspace and return stdout, stderr, exit code, and changed files.
- [Create reusable extraction schema template](https://docs.mka1.com/api-reference/extract/create-reusable-extraction-schema-template.md): Creates and stores a reusable JSON Schema template for structured data extraction.
- [Delete extraction schema by ID](https://docs.mka1.com/api-reference/extract/delete-extraction-schema-by-id.md): Remove a stored extraction schema.
- [Extract data using saved schema template](https://docs.mka1.com/api-reference/extract/extract-data-using-saved-schema-template.md): Extracts structured data from files using a previously saved extraction schema template.
- [Extract structured data with inline JSON Schema](https://docs.mka1.com/api-reference/extract/extract-structured-data-with-inline-json-schema.md): Extracts structured data from files using a custom inline JSON schema.
- [Get extraction schema by ID](https://docs.mka1.com/api-reference/extract/get-extraction-schema-by-id.md): Retrieve a stored extraction schema and its metadata.
- [Update extraction schema by ID](https://docs.mka1.com/api-reference/extract/update-extraction-schema-by-id.md): Update an existing extraction schema and its metadata.
- [Batch retrieve feedback for multiple completions](https://docs.mka1.com/api-reference/feedback/batch-retrieve-feedback-for-multiple-completions.md): Retrieves feedback for multiple chat completions in a single batch request.
- [Batch retrieve feedback for multiple responses](https://docs.mka1.com/api-reference/feedback/batch-retrieve-feedback-for-multiple-responses.md): Retrieves feedback for multiple agent responses in a single batch request.
- [Get feedback export status](https://docs.mka1.com/api-reference/feedback/get-feedback-export-status.md): Checks the status and progress of the currently running or most recently completed feedback export job.
- [Retrieve feedback by completion ID](https://docs.mka1.com/api-reference/feedback/retrieve-feedback-by-completion-id.md): Retrieves the existing feedback rating and description for a specific chat completion.
- [Retrieve feedback by response ID](https://docs.mka1.com/api-reference/feedback/retrieve-feedback-by-response-id.md): Retrieves the existing feedback rating and description for a specific agent response.
- [Start feedback export](https://docs.mka1.com/api-reference/feedback/start-feedback-export.md): Starts a background job to export all feedback data to parquet files in S3/R2. Only one export can run simultaneously.
- [Submit feedback for chat completion](https://docs.mka1.com/api-reference/feedback/submit-feedback-for-chat-completion.md): Submit user feedback for a specific chat completion to track satisfaction and model performance. Each completion can only receive feedback once.
- [Submit feedback for response](https://docs.mka1.com/api-reference/feedback/submit-feedback-for-response.md): Submit user feedback for a specific agent response to track satisfaction and model performance. Each response can only receive feedback once.
- [Update existing completion feedback](https://docs.mka1.com/api-reference/feedback/update-existing-completion-feedback.md): Updates or modifies existing feedback for a specific chat completion. Useful for allowing users to revise their initial submissions.
- [Update existing response feedback](https://docs.mka1.com/api-reference/feedback/update-existing-response-feedback.md): Updates or modifies existing feedback for a specific agent response. Useful for allowing users to revise their initial submissions.
- [Delete file](https://docs.mka1.com/api-reference/files/delete-file.md): Delete a file from storage. This will also remove it from any vector stores.
- [List files](https://docs.mka1.com/api-reference/files/list-files.md): Returns a list of files that have been uploaded.
- [Retrieve file](https://docs.mka1.com/api-reference/files/retrieve-file.md): Returns information about a specific file.
- [Retrieve file content](https://docs.mka1.com/api-reference/files/retrieve-file-content.md): Returns the raw binary contents of the specified file with appropriate Content-Type header.
- [Upload file](https://docs.mka1.com/api-reference/files/upload-file.md): Upload a file that can be used with Assistants, Vector Stores, and other features. Files are uploaded to S3 for durable storage.
- [Cancel a fine-tuning job](https://docs.mka1.com/api-reference/fine-tuning/cancel-a-fine-tuning-job.md): Immediately cancel a fine-tuning job.
- [Create a fine-tuning job](https://docs.mka1.com/api-reference/fine-tuning/create-a-fine-tuning-job.md): Creates a fine-tuning job which begins the process of training a new model from a given dataset.
- [List fine-tuning checkpoints](https://docs.mka1.com/api-reference/fine-tuning/list-fine-tuning-checkpoints.md): List checkpoints for a fine-tuning job.
- [List fine-tuning events](https://docs.mka1.com/api-reference/fine-tuning/list-fine-tuning-events.md): Get status updates for a fine-tuning job.
- [List fine-tuning jobs](https://docs.mka1.com/api-reference/fine-tuning/list-fine-tuning-jobs.md): List your organization's fine-tuning jobs.
- [Pause a fine-tuning job](https://docs.mka1.com/api-reference/fine-tuning/pause-a-fine-tuning-job.md): Pause a running fine-tuning job.
- [Resume a fine-tuning job](https://docs.mka1.com/api-reference/fine-tuning/resume-a-fine-tuning-job.md): Resume a paused fine-tuning job.
- [Retrieve a fine-tuning job](https://docs.mka1.com/api-reference/fine-tuning/retrieve-a-fine-tuning-job.md): Get info about a fine-tuning job.
- [Create Store](https://docs.mka1.com/api-reference/graphrag/create-store.md)
- [Delete Store](https://docs.mka1.com/api-reference/graphrag/delete-store.md)
- [Ingest Documents](https://docs.mka1.com/api-reference/graphrag/ingest-documents.md)
- [Inspect Graph](https://docs.mka1.com/api-reference/graphrag/inspect-graph.md)
- [Query Store](https://docs.mka1.com/api-reference/graphrag/query-store.md)
- [Get guardrails settings](https://docs.mka1.com/api-reference/guardrails/get-guardrails-settings.md): Retrieve the current guardrails configuration for the authenticated user. Returns all configured guardrails including ban words, prompt injection detection, and leakage detection settings.
- [Test content against guardrails](https://docs.mka1.com/api-reference/guardrails/test-content-against-guardrails.md): Test a piece of content against the configured guardrails without making an actual API call. Useful for debugging and validating guardrail configurations. Returns a report indicating whether the content passed and which guardrail was triggered if any.
- [Update guardrails settings](https://docs.mka1.com/api-reference/guardrails/update-guardrails-settings.md): Update the guardrails configuration for the authenticated user. Configure multiple guardrail modes including ban words (custom word list), prompt injection detection, and system prompt leakage detection. Each guardrail can be individually enabled/disabled with custom thresholds and rejection message…
- [Generate images from text descriptions](https://docs.mka1.com/api-reference/images/generate-images-from-text-descriptions.md): Creates AI-generated images from text descriptions.
- [API overview](https://docs.mka1.com/api-reference/introduction.md)
- [Add a model to the registry](https://docs.mka1.com/api-reference/models/add-a-model-to-the-registry.md): Adds a new database-sourced model to the registry. YAML models cannot be overridden.
- [Check health of a specific model](https://docs.mka1.com/api-reference/models/check-health-of-a-specific-model.md): Probes the model's provider endpoint and updates health status.
- [Get a specific registry model](https://docs.mka1.com/api-reference/models/get-a-specific-registry-model.md): Returns full model definition and health status for a specific model.
- [List all registry models](https://docs.mka1.com/api-reference/models/list-all-registry-models.md): Lists all models in the registry with full details including source and health status.
- [List available models](https://docs.mka1.com/api-reference/models/list-available-models.md): Lists the currently available models. Provides basic information about each model including its ID and owner.
- [Remove a database model from the registry](https://docs.mka1.com/api-reference/models/remove-a-database-model-from-the-registry.md): Removes a database-sourced model. YAML models cannot be removed.
- [Retrieve a model](https://docs.mka1.com/api-reference/models/retrieve-a-model.md): Retrieves a model instance, providing basic information about the model such as the owner and supported capabilities.
- [Update a database model in the registry](https://docs.mka1.com/api-reference/models/update-a-database-model-in-the-registry.md): Partially updates a database-sourced model. Only provided fields are changed; omitted fields are preserved. YAML models cannot be updated.
- [Create a new version](https://docs.mka1.com/api-reference/prompts/create-a-new-version.md): Creates a new version of a prompt. The new version automatically becomes the active version. Fields not provided are carried forward from the previous version.
- [Create a prompt](https://docs.mka1.com/api-reference/prompts/create-a-prompt.md): Creates a new prompt with its first version. The template supports {{variable}} placeholders.
- [Delete a prompt](https://docs.mka1.com/api-reference/prompts/delete-a-prompt.md): Deletes a prompt and all its versions.
- [Get a prompt](https://docs.mka1.com/api-reference/prompts/get-a-prompt.md): Retrieves a prompt by its ID, including the active template. Pass `version` to get a specific version's template. Pass `variables` as a JSON-encoded map to render the template with substitutions.
- [Get a specific version](https://docs.mka1.com/api-reference/prompts/get-a-specific-version.md): Retrieves a specific version of a prompt by version number.
- [List prompts](https://docs.mka1.com/api-reference/prompts/list-prompts.md): Returns a paginated list of prompts owned by the authenticated user.
- [List versions](https://docs.mka1.com/api-reference/prompts/list-versions.md): Returns the version history of a prompt, ordered by version number.
- [Rollback to a version](https://docs.mka1.com/api-reference/prompts/rollback-to-a-version.md): Sets the active version of a prompt to a previous version. This does not delete newer versions — it only changes which version is active.
- [Update a prompt](https://docs.mka1.com/api-reference/prompts/update-a-prompt.md): Updates prompt metadata. To update the template content, create a new version instead.
- [Check user permission](https://docs.mka1.com/api-reference/resource-authorization/check-user-permission.md): Check whether the authenticated caller has a specific role on a resource.
- [Create a new resource](https://docs.mka1.com/api-reference/resource-authorization/create-a-new-resource.md): Create an LLM resource and assign the authenticated caller as owner. If overwrite is true, existing direct relationships for the resource are replaced.
- [Delete a resource](https://docs.mka1.com/api-reference/resource-authorization/delete-a-resource.md): Delete an LLM resource and all of its direct permissions. Only owners can delete resources.
- [Grant permission to a user or make public](https://docs.mka1.com/api-reference/resource-authorization/grant-permission-to-a-user-or-make-public.md): Grant a role to a user for a resource, or grant public access by using "*" as userId. Only owners can grant permissions. Public access is allowed only for writer and reader roles.
- [List resources the user has access to](https://docs.mka1.com/api-reference/resource-authorization/list-resources-the-user-has-access-to.md): List resources of a specific type where the authenticated caller has the specified role. Returns direct relationships only (not computed).
- [List users with permissions](https://docs.mka1.com/api-reference/resource-authorization/list-users-with-permissions.md): List users with a specific role on a resource. Returns direct relationships only (not computed). The authenticated caller must have at least reader access.
- [Revoke permission from a user or remove public access](https://docs.mka1.com/api-reference/resource-authorization/revoke-permission-from-a-user-or-remove-public-access.md): Revoke a role from a user for a resource, or remove public access by using "*" as userId. Only owners can revoke permissions.
- [Cancel an in-progress background response](https://docs.mka1.com/api-reference/responses/cancel-an-in-progress-background-response.md): Cancels an agent response that is currently processing in the background.
- [Compact a conversation](https://docs.mka1.com/api-reference/responses/compact-a-conversation.md): Creates a compacted summary of the conversation history for a response, reducing context size while preserving key information. Returns a compacted response object.
- [Create an agent-powered response with tool support](https://docs.mka1.com/api-reference/responses/create-an-agent-powered-response-with-tool-support.md): Creates a new AI agent response using advanced language models with autonomous tool usage capabilities.
- [List all responses with pagination](https://docs.mka1.com/api-reference/responses/list-all-responses-with-pagination.md): Retrieves a paginated list of all agent responses for the authenticated user.
- [List paginated input items for a response](https://docs.mka1.com/api-reference/responses/list-paginated-input-items-for-a-response.md): Retrieves a paginated list of all input items provided when creating the specified agent response.
- [Permanently delete a response and its data](https://docs.mka1.com/api-reference/responses/permanently-delete-a-response-and-its-data.md): Permanently deletes an agent response and all associated data.
- [Retrieve response by ID with status and results](https://docs.mka1.com/api-reference/responses/retrieve-response-by-id-with-status-and-results.md): Retrieves a previously created agent response by its unique ID. When stream=true, returns Server-Sent Events for real-time updates on in-progress background responses.
- [Update a response](https://docs.mka1.com/api-reference/responses/update-a-response.md): Update a response's metadata.
- [Create Session](https://docs.mka1.com/api-reference/sessions/create-session.md): Create a sandbox session and return a session token, provider, and base sandbox URL. Set `session_kind` to `browser` to start a browser-backed session instead of a standard command/code sandbox. Set `queue_if_full` to `true` to queue the request instead of failing when runner capacity is temporarily…
- [Get Session](https://docs.mka1.com/api-reference/sessions/get-session.md): Return the current state, features, and runner metadata for a sandbox session.
- [Get Session URL](https://docs.mka1.com/api-reference/sessions/get-session-url.md): Resolve a gateway URL for a port exposed by the sandbox session. For `browser` sessions, omit `port` or set it to `9222` to get the browser proxy base URL; then use that URL directly with a CDP client such as Playwright/Puppeteer or append `/json/version` to inspect the browser endpoint over plain H…
- [List Sessions](https://docs.mka1.com/api-reference/sessions/list-sessions.md): List sandbox sessions visible to the authenticated caller.
- [Terminate Session](https://docs.mka1.com/api-reference/sessions/terminate-session.md): Stop a sandbox session and release the backing sandbox resources.
- [Create skill](https://docs.mka1.com/api-reference/skills/create-skill.md): Create a new skill by uploading files. The uploaded files must include a SKILL.md manifest. Accepts multipart form data with individual files or a single zip archive.
- [Create skill version](https://docs.mka1.com/api-reference/skills/create-skill-version.md): Create a new immutable version of a skill by uploading files. The uploaded files must include a SKILL.md manifest.
- [Delete skill](https://docs.mka1.com/api-reference/skills/delete-skill.md): Delete a skill and all its versions.
- [Delete skill version](https://docs.mka1.com/api-reference/skills/delete-skill-version.md): Delete a specific version of a skill.
- [Download skill content](https://docs.mka1.com/api-reference/skills/download-skill-content.md): Download the zip bundle for a skill's default version.
- [Download skill version content](https://docs.mka1.com/api-reference/skills/download-skill-version-content.md): Download the zip bundle for a specific skill version.
- [List preconfigured skills](https://docs.mka1.com/api-reference/skills/list-preconfigured-skills.md): Returns the list of preconfigured skills that ship with the gateway. These can be referenced in shell tool definitions as { type: 'preconfigured', name: '...' }.
- [List skill versions](https://docs.mka1.com/api-reference/skills/list-skill-versions.md): Returns a paginated list of versions for a skill.
- [List skills](https://docs.mka1.com/api-reference/skills/list-skills.md): Returns a paginated list of skills.
- [Retrieve skill](https://docs.mka1.com/api-reference/skills/retrieve-skill.md): Returns information about a specific skill.
- [Retrieve skill version](https://docs.mka1.com/api-reference/skills/retrieve-skill-version.md): Returns information about a specific skill version.
- [Update skill](https://docs.mka1.com/api-reference/skills/update-skill.md): Update the default version pointer for a skill.
- [Generate LiveKit room token](https://docs.mka1.com/api-reference/speech/generate-livekit-room-token.md): Generates a LiveKit access token for joining a real-time voice room. The token includes encrypted credentials and model configuration for the voice agent.
- [Speech to text transcription](https://docs.mka1.com/api-reference/speech/speech-to-text-transcription.md): Convert audio to text using advanced speech recognition.
- [Streaming text to speech](https://docs.mka1.com/api-reference/speech/streaming-text-to-speech.md): Convert text to speech with real-time streaming audio delivery.
- [Text to speech](https://docs.mka1.com/api-reference/speech/text-to-speech.md): Convert text to speech with automatic language detection.
- [Create Indices](https://docs.mka1.com/api-reference/tables/create-indices.md): Create indices on the specified table.
- [Create Table](https://docs.mka1.com/api-reference/tables/create-table.md): Create a new table with the specified schema.
- [Delete Data](https://docs.mka1.com/api-reference/tables/delete-data.md): Delete data from a table using a filter expression. https://lancedb.github.io/lancedb/guides/tables/#deleting-from-a-table
- [Delete Table](https://docs.mka1.com/api-reference/tables/delete-table.md): Delete a table.
- [Drop Index](https://docs.mka1.com/api-reference/tables/drop-index.md): Drop an index on the specified field.
- [Get Table Schema](https://docs.mka1.com/api-reference/tables/get-table-schema.md): Get table schema and metadata.
- [Insert Data](https://docs.mka1.com/api-reference/tables/insert-data.md): Insert data into the specified table.
- [List Indices](https://docs.mka1.com/api-reference/tables/list-indices.md): List all indices on the specified table.
- [Search](https://docs.mka1.com/api-reference/tables/search.md): Perform search operations on a table.
- [Classify text into predefined categories](https://docs.mka1.com/api-reference/text-classification/classify-text-into-predefined-categories.md): Classifies text content into one of the provided predefined labels.
- [Add Texts](https://docs.mka1.com/api-reference/text-store/add-texts.md): Add texts to a store with a group identifier
- [Create Store](https://docs.mka1.com/api-reference/text-store/create-store.md): Create a new text store
- [Delete Store](https://docs.mka1.com/api-reference/text-store/delete-store.md): Delete a text store and all its data
- [Delete Texts](https://docs.mka1.com/api-reference/text-store/delete-texts.md): Delete texts from a store by specific texts or group identifiers
- [Search Texts](https://docs.mka1.com/api-reference/text-store/search-texts.md): Search for similar texts in a store
- [Get classify usage](https://docs.mka1.com/api-reference/usage/get-classify-usage.md): Retrieve usage metrics for classify operations.
- [Get completions usage](https://docs.mka1.com/api-reference/usage/get-completions-usage.md): Retrieve usage metrics for chat completions, aggregated from the ChatCompletion table.
- [Get conversations usage](https://docs.mka1.com/api-reference/usage/get-conversations-usage.md): Retrieve usage metrics for conversation operations.
- [Get embeddings usage](https://docs.mka1.com/api-reference/usage/get-embeddings-usage.md): Retrieve usage metrics for embedding operations.
- [Get extract usage](https://docs.mka1.com/api-reference/usage/get-extract-usage.md): Retrieve usage metrics for extract operations.
- [Get responses usage](https://docs.mka1.com/api-reference/usage/get-responses-usage.md): Retrieve usage metrics for agent responses, aggregated from the Response table.
- [Get vector stores usage](https://docs.mka1.com/api-reference/usage/get-vector-stores-usage.md): Retrieve usage metrics for vector storage operations.
- [Add a file to a vector store](https://docs.mka1.com/api-reference/vector-stores/add-a-file-to-a-vector-store.md): Adds a file to a vector store for semantic search indexing.
- [Batch add multiple files to vector store](https://docs.mka1.com/api-reference/vector-stores/batch-add-multiple-files-to-vector-store.md): Adds multiple files to a vector store in a single batch operation.
- [Cancel batch file processing](https://docs.mka1.com/api-reference/vector-stores/cancel-batch-file-processing.md): Cancels an in-progress file batch operation.
- [Create a vector store](https://docs.mka1.com/api-reference/vector-stores/create-a-vector-store.md): Creates a new vector store for storing and searching through document embeddings.
- [Delete a vector store](https://docs.mka1.com/api-reference/vector-stores/delete-a-vector-store.md): Permanently deletes a vector store and its associated embeddings.
- [List files in a batch](https://docs.mka1.com/api-reference/vector-stores/list-files-in-a-batch.md): Retrieves a paginated list of all files within a specific batch operation.
- [List files in a vector store](https://docs.mka1.com/api-reference/vector-stores/list-files-in-a-vector-store.md): Retrieves a paginated list of all files in a specific vector store.
- [List vector stores](https://docs.mka1.com/api-reference/vector-stores/list-vector-stores.md): Retrieves a paginated list of all vector stores for the authenticated user.
- [Modify a vector store](https://docs.mka1.com/api-reference/vector-stores/modify-a-vector-store.md): Updates the properties of an existing vector store.
- [Remove file from vector store](https://docs.mka1.com/api-reference/vector-stores/remove-file-from-vector-store.md): Removes a file from a vector store and deletes its associated embeddings.
- [Retrieve a vector store](https://docs.mka1.com/api-reference/vector-stores/retrieve-a-vector-store.md): Retrieves a vector store by its ID.
- [Retrieve a vector store file](https://docs.mka1.com/api-reference/vector-stores/retrieve-a-vector-store-file.md): Retrieves detailed information about a specific file within a vector store.
- [Retrieve file batch status](https://docs.mka1.com/api-reference/vector-stores/retrieve-file-batch-status.md): Retrieves the status of a specific file batch operation within a vector store.
- [Retrieve parsed file content](https://docs.mka1.com/api-reference/vector-stores/retrieve-parsed-file-content.md): Retrieves the complete parsed contents of a file within a vector store.
- [Search a vector store](https://docs.mka1.com/api-reference/vector-stores/search-a-vector-store.md): Performs semantic search within a vector store to find the most relevant document chunks for a query.
- [Update file attributes](https://docs.mka1.com/api-reference/vector-stores/update-file-attributes.md): Updates the metadata attributes attached to a file within a vector store.
- [Download Workspace File](https://docs.mka1.com/api-reference/workspace/download-workspace-file.md): Download raw bytes from a file in the session workspace.
- [Get Workspace Manifest](https://docs.mka1.com/api-reference/workspace/get-workspace-manifest.md): List files currently stored in the session workspace, including paths, sizes, and etags.
- [Upload Workspace File](https://docs.mka1.com/api-reference/workspace/upload-workspace-file.md): Upload raw bytes into the session workspace at the given path.
- [Advanced conversations with tools](https://docs.mka1.com/docs/advanced-conversations.md): A complete 12-turn dialogue with web search, corrections, contradictions, and coherence verification — showing every request and full response.
- [Advanced Voice Mode](https://docs.mka1.com/docs/advanced-voice-mode.md): Build real-time voice sessions with the MKA1 API using LiveKit. Configure LLM options, tools, STT tuning, and conversation continuity.
- [Authentication](https://docs.mka1.com/docs/authentication.md): Authenticate to the MKA1 API with your API key, decide when to send X-On-Behalf-Of, and exchange an API key for a short-lived JWT.
- [Authentication and tenant isolation](https://docs.mka1.com/docs/authentication-deep-dive.md): Demonstrate segregated tenants in the MKA1 API with separate API keys, separate quotas, separate policies, and tenant-scoped resource access.
- [Authorization](https://docs.mka1.com/docs/authorization.md): Control access to LLM resources with role-based authorization. Assign owner, writer, or reader roles to users and verify permissions before every action.
- [Authorship procedure](https://docs.mka1.com/docs/authorship-procedure.md): The procedure for updating authorship with each new version.
- [Background responses](https://docs.mka1.com/docs/background-responses.md): Run long-running responses in the background and retrieve results by polling or streaming.
- [Batch processing](https://docs.mka1.com/docs/batch-processing.md): Send large volumes of requests asynchronously using the Batch API. Process chat completions, embeddings, and image generations in bulk with a 24-hour completion window.
- [Authenticate the CLI](https://docs.mka1.com/docs/cli/authentication.md): Configure the mka1 CLI with your API key using flags, environment variables, the OS keychain, or a config file — and attach X-On-Behalf-Of for multi-user integrations.
- [Commands](https://docs.mka1.com/docs/cli/commands.md): Tour the mka1 CLI command tree with worked examples for Responses, Conversations, Files, Vector Stores, Extract, Speech, Agents, and more.
- [Debug and inspect](https://docs.mka1.com/docs/cli/diagnostics.md): Preview mka1 CLI requests with --dry-run, trace them live with --debug, explore the command tree interactively, and enable agent mode for AI coding tools.
- [CLI overview](https://docs.mka1.com/docs/cli/introduction.md): Install the mka1 CLI, enable shell completion, and run your first MKA1 API command from the terminal.
- [Format and filter output](https://docs.mka1.com/docs/cli/output-formats.md): Switch the mka1 CLI between pretty, JSON, YAML, table, and TOON output. Transform results with jq, stream SSE events, and control color.
- [Pass request bodies](https://docs.mka1.com/docs/cli/request-body.md): Build mka1 CLI requests with individual flags, the --body JSON shortcut, or stdin piping — and understand how the three inputs combine.
- [Manage conversations](https://docs.mka1.com/docs/conversations.md): Store conversation state in the MKA1 API, add message items, and continue a response flow without resending the full history.
- [Data encryption](https://docs.mka1.com/docs/data-encryption.md): See which encryption controls are active in the deployed MKA1 environment, how we validate them, and the evidence captured from production.
- [Evaluate regional localization and ambiguity handling](https://docs.mka1.com/docs/evaluating-local-language-and-ambiguity.md): Run neutral evaluations that prove spontaneous regional localization and clarification behavior with the MKA1 SDK.
- [Evaluating text stores](https://docs.mka1.com/docs/evaluating-text-stores.md): Benchmark retrieval accuracy and latency for the MKA1 Text Store and Tables APIs using the BEIR SciFact dataset.
- [Extract structured data](https://docs.mka1.com/docs/extract-structured-data.md): Define a reusable extraction schema in the MKA1 API and extract structured fields from files.
- [Use files and vector stores](https://docs.mka1.com/docs/files-and-vector-stores.md): Upload files to the MKA1 API, index them in a vector store, and run semantic search over the resulting document chunks.
- [Fine-tune a model](https://docs.mka1.com/docs/fine-tuning.md): Upload fine-tuning data, create a fine-tuning job, monitor training progress, and use the resulting model with the `@meetkai/mka1` SDK.
- [Generate a response](https://docs.mka1.com/docs/generate-a-response.md): Use the MKA1 API Responses resource to generate text, send structured messages, and continue multi-turn exchanges.
- [GitOps with atomic rollback](https://docs.mka1.com/docs/gitops-atomic-rollback.md): How MKA1 uses Git as the single source of truth and Helm atomic deploys to guarantee automatic rollback on failure.
- [GraphRAG evaluation](https://docs.mka1.com/docs/graphrag.md): A benchmark comparison of GraphRAG and traditional RAG on multi-hop retrieval questions.
- [HSM-backed keys and TLS 1.3](https://docs.mka1.com/docs/hsm-tls-validation.md): How MKA1 uses AWS KMS hardware security modules and enforces TLS 1.3 for cryptographic key management across data at rest and in transit.
- [Getting Started](https://docs.mka1.com/docs/introduction.md): Request your MKA1 API key and send your first Responses API request with the MKA1 SDK, OpenAI SDK, C# SDK, Python SDK, or curl.
- [Long-term memory](https://docs.mka1.com/docs/long-term-memory.md): Use the history tool to give models persistent memory across sessions, enabling recall of past conversations per end-user.
- [Making deep research with subagents](https://docs.mka1.com/docs/making-deep-research-with-subagents.md): Build a deep research workflow on the MKA1 API by using a parent response to delegate parallel web research to child responses and synthesize compact research memos.
- [Manage agents](https://docs.mka1.com/docs/managing-agents.md): Create reusable agent definitions, execute them later, and inspect persisted run history.
- [Use MCP tools](https://docs.mka1.com/docs/mcp-tools.md): Connect an MCP server to the MKA1 API Responses resource, limit allowed tools, and optionally require end-user approval.
- [Multichannel conversational](https://docs.mka1.com/docs/multichannel-conversational.md): Demonstrate WhatsApp and web channels sharing one stored MKA1 API conversation with unified JSONL audit logs.
- [Multimodal input](https://docs.mka1.com/docs/multimodal-input.md): Send images, audio, documents, and mixed content to the MKA1 API for vision, transcription, OCR, and multimodal reasoning.
- [Multimodal output](https://docs.mka1.com/docs/multimodal-output.md): Generate audio speech and images from the MKA1 API using the Responses resource.
- [Prompt repository](https://docs.mka1.com/docs/prompt-repository.md): Manage versioned prompt templates with change history, rollback, and variable rendering through the Prompts API.
- [Specialized pt-BR embeddings](https://docs.mka1.com/docs/pt-br-embeddings.md): Technical report on mk-embeddings-pt — a Brazilian Portuguese embedding model with MTEB benchmark results, semantic quality metrics, and comparison to multilingual baselines.
- [Rate limiting](https://docs.mka1.com/docs/rate-limiting.md): Per-key rate limits with configurable quotas per second, minute, hour, or day. Includes real HTTP 429 demonstration and retry patterns.
- [Index and search text](https://docs.mka1.com/docs/search.md): Use the Text Store for preconfigured vector search, or Tables for low-level control over schema, indices, and search operations.
- [Signed artifacts and supply chain](https://docs.mka1.com/docs/signed-artifacts.md): How MKA1 ensures container image integrity through immutable artifact tagging, controlled CI/CD pipelines, and private registry enforcement.
- [Spawn subagents using the Responses API](https://docs.mka1.com/docs/spawn-subagents-using-the-responses-api.md): Use a function tool on the MKA1 API Responses resource to let one response spawn child responses and continue after they all return.
- [Speech](https://docs.mka1.com/docs/speech.md): Transcribe audio and generate speech with the MKA1 API. Use speaker-labeled segments when you need multi-speaker separation.
- [Streaming output latency](https://docs.mka1.com/docs/streaming-output-latency.md): Client-observed benchmark of first streamed text token latency for the MKA1 Responses API.
- [Usage auditing](https://docs.mka1.com/docs/usage-auditing.md): Track per-user usage, correlate requests at the API edge, and structure per-unit audit events for misuse detection.
- [Validate auto routing](https://docs.mka1.com/docs/validate-auto-routing.md): Verify Responses auto routing in production, inspect the routing decision, and compare live results against expected tiers.

## OpenAPI Specs

- [speakeasy](https://apigw.mka1.com/speakeasy.json)
- [openapi](https://docs.mka1.com/api-reference/openapi.json)