> ## Documentation Index > Fetch the complete documentation index at: https://morphik.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Query Completion > Generate completion using relevant chunks as context. ## OpenAPI ````yaml https://app.stainless.com/api/spec/documented/morphik/openapi.documented.yml post /query openapi: 3.1.0 info: title: FastAPI version: 0.1.0 servers: [] security: [] paths: /query: post: summary: Query Completion description: Generate completion using relevant chunks as context. operationId: query_completion_query_post parameters: - name: authorization in: header required: false schema: anyOf: - type: string - type: 'null' title: Authorization requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CompletionQueryRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CompletionResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: JavaScript source: |- import Morphik from 'morphik'; const client = new Morphik({ apiKey: process.env['MORPHIK_API_KEY'], // This is the default and can be omitted }); const response = await client.query.generateCompletion(); console.log(response.completion); - lang: cURL source: |- curl https://api.morphik.ai/query \ -H 'Content-Type: application/json' \ -H "Authorization: Bearer $MORPHIK_API_KEY" \ -d '{}' components: schemas: CompletionQueryRequest: properties: query: anyOf: - type: string minLength: 1 - type: 'null' title: Query description: >- Natural-language query used to retrieve relevant chunks or documents. query_image: anyOf: - type: string - type: 'null' title: Query Image description: >- Base64-encoded image to use as query for Morphik multimodal retrieval. Requires use_colpali=True. Mutually exclusive with 'query'. filters: anyOf: - additionalProperties: true type: object - type: 'null' title: Filters description: >- Metadata filters supporting logical operators ($and/$or/$not/$nor) and field predicates ($eq/$ne/$gt/$gte/$lt/$lte/$in/$nin/$exists/$type/$regex/$contains). k: type: integer exclusiveMinimum: 0 title: K description: Maximum number of chunks or documents to return. default: 4 min_score: type: number title: Min Score description: Minimum similarity score a result must meet before it is returned. default: 0 use_reranking: anyOf: - type: boolean - type: 'null' title: Use Reranking description: >- When provided, overrides the workspace reranking configuration for this request. use_colpali: anyOf: - type: boolean - type: 'null' title: Use Colpali description: >- When provided, uses Morphik's finetuned ColPali style embeddings (recommended to be True for high quality retrieval). output_format: anyOf: - $ref: '#/components/schemas/OutputFormat' - type: 'null' description: >- How to return image chunks: base64 (default), url, or text (markdown format) default: base64 padding: type: integer minimum: 0 title: Padding description: >- Number of additional chunks/pages to retrieve before and after matched chunks (ColPali only) default: 0 folder_name: anyOf: - type: string - items: type: string type: array - type: 'null' title: Folder Name description: >- Optional folder scope. Accepts a folder PATH (e.g., '/Company/Reports') or list of paths. folder_depth: anyOf: - type: integer - type: 'null' title: Folder Depth description: >- Folder scope depth. 0 or None = exact folder only, -1 = include all descendants, n > 0 = include descendants up to n levels deeper. end_user_id: anyOf: - type: string - type: 'null' title: End User Id description: Optional end-user scope for the operation max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens description: Maximum number of tokens allowed in the generated completion. temperature: anyOf: - type: number - type: 'null' title: Temperature description: >- Sampling temperature passed to the completion model (None uses provider default). prompt_overrides: anyOf: - $ref: '#/components/schemas/QueryPromptOverrides' - type: 'null' description: >- Optional customizations for entity extraction, resolution, and query prompts schema: anyOf: - {} - additionalProperties: true type: object - type: 'null' title: Schema description: >- Schema for structured output, can be a Pydantic model or JSON schema dict chat_id: anyOf: - type: string - type: 'null' title: Chat Id description: Optional chat session ID for persisting conversation history stream_response: anyOf: - type: boolean - type: 'null' title: Stream Response description: Whether to stream the response back in chunks default: false llm_config: anyOf: - additionalProperties: true type: object - type: 'null' title: Llm Config description: >- LiteLLM-compatible model configuration (e.g., model name, API key, base URL) inline_citations: anyOf: - type: boolean - type: 'null' title: Inline Citations description: >- Whether to include inline citations with filename and page number in the response default: false type: object title: CompletionQueryRequest description: Request model for completion generation CompletionResponse: properties: completion: anyOf: - type: string - $ref: '#/components/schemas/StructuredCompletion' title: Completion usage: additionalProperties: type: integer type: object title: Usage finish_reason: anyOf: - type: string - type: 'null' title: Finish Reason sources: items: $ref: '#/components/schemas/ChunkSource' type: array title: Sources default: [] metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata type: object required: - completion - usage title: CompletionResponse description: Response from completion generation HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError OutputFormat: type: string enum: - base64 - url - text title: OutputFormat description: Output format for image chunks in retrieval results. QueryPromptOverrides: properties: entity_extraction: anyOf: - $ref: '#/components/schemas/EntityExtractionPromptOverride' - type: 'null' description: >- Overrides for entity extraction prompts - controls how entities are identified in text during queries entity_resolution: anyOf: - $ref: '#/components/schemas/EntityResolutionPromptOverride' - type: 'null' description: >- Overrides for entity resolution prompts - controls how variant forms are grouped during queries query: anyOf: - $ref: '#/components/schemas/QueryPromptOverride' - type: 'null' description: >- Overrides for query prompts - controls response generation style, format, and tone additionalProperties: false type: object title: QueryPromptOverrides description: >- Container for query-related prompt overrides. Use this class when customizing prompts for query operations, which may include customizations for entity extraction, entity resolution, and the query/response generation itself. This is the most feature-complete override class, supporting all customization types. Available customizations: - entity_extraction: Customize how entities are identified in text - entity_resolution: Customize how entity variants are grouped - query: Customize response generation style, format, and tone Each type has its own required placeholders. See the specific class documentation for details and examples. StructuredCompletion: properties: {} additionalProperties: true type: object title: StructuredCompletion description: Structured completion object for schema-based responses ChunkSource: properties: document_id: type: string title: Document Id chunk_number: type: integer title: Chunk Number score: anyOf: - type: number - type: 'null' title: Score type: object required: - document_id - chunk_number title: ChunkSource description: Source information for a chunk used in completion ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError EntityExtractionPromptOverride: properties: prompt_template: anyOf: - type: string - type: 'null' title: Prompt Template description: >- Custom prompt template, MUST include both {content} and {examples} placeholders. The {content} placeholder will be replaced with the text to analyze, and {examples} will be replaced with formatted examples. examples: anyOf: - items: $ref: '#/components/schemas/EntityExtractionExample' type: array - type: 'null' title: Examples description: >- Examples of entities to extract, used to guide the LLM toward domain-specific entity types and patterns. type: object title: EntityExtractionPromptOverride description: >- Configuration for customizing entity extraction prompts. This allows you to override both the prompt template used for entity extraction and provide domain-specific examples of entities to be extracted. If only examples are provided (without a prompt_template), they will be incorporated into the default prompt. If only prompt_template is provided, it will be used with default examples (if any). Required placeholders: - {content}: Will be replaced with the text to analyze for entity extraction - {examples}: Will be replaced with formatted examples of entities to extract Example prompt template: ``` Extract entities from the following text. Look for entities similar to these examples: {examples} Text to analyze: {content} Extracted entities (in JSON format): ``` EntityResolutionPromptOverride: properties: prompt_template: anyOf: - type: string - type: 'null' title: Prompt Template description: >- Custom prompt template that MUST include both {entities_str} and {examples_json} placeholders. The {entities_str} placeholder will be replaced with the extracted entities, and {examples_json} will be replaced with JSON-formatted examples of entity resolution groups. examples: anyOf: - items: $ref: '#/components/schemas/EntityResolutionExample' type: array - type: 'null' title: Examples description: >- Examples of entity resolution groups showing how variants of the same entity should be resolved to their canonical forms. This is particularly useful for domain-specific terminology, abbreviations, and naming conventions. type: object title: EntityResolutionPromptOverride description: >- Configuration for customizing entity resolution prompts. Entity resolution identifies and groups variant forms of the same entity. This override allows you to customize how this process works by providing a custom prompt template and/or domain-specific examples. If only examples are provided (without a prompt_template), they will be incorporated into the default prompt. If only prompt_template is provided, it will be used with default examples (if any). Required placeholders: - {entities_str}: Will be replaced with the extracted entities - {examples_json}: Will be replaced with JSON-formatted examples of entity resolution groups Example prompt template: ``` I have extracted the following entities: {entities_str} Below are examples of how different entity references can be grouped together: {examples_json} Group the above entities by resolving which mentions refer to the same entity. Return the results in JSON format. ``` QueryPromptOverride: properties: prompt_template: anyOf: - type: string - type: 'null' title: Prompt Template description: >- Custom prompt template for generating responses to queries. REQUIRED PLACEHOLDERS: {question} and {context} must be included in the template. The {question} placeholder will be replaced with the user query, and {context} will be replaced with the retrieved content. Use this to control response style, format, and tone. system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: >- Custom system prompt that replaces Morphik's default query agent instructions. Use this to fully control the assistant's behavior when generating responses. type: object title: QueryPromptOverride description: >- Configuration for customizing query prompts. This allows you to customize how responses are generated during query operations. Query prompts guide the LLM on how to format and style responses, what tone to use, and how to incorporate retrieved information into the response. Required placeholders: - {question}: Will be replaced with the user's query - {context}: Will be replaced with the retrieved content/context Example prompt template: ``` Answer the following question based on the provided information. Question: {question} Context: {context} Answer: ``` EntityExtractionExample: properties: label: type: string title: Label description: The entity label (e.g., 'John Doe', 'Apple Inc.') type: type: string title: Type description: The entity type (e.g., 'PERSON', 'ORGANIZATION', 'PRODUCT') properties: anyOf: - additionalProperties: true type: object - type: 'null' title: Properties description: 'Optional properties of the entity (e.g., {''role'': ''CEO'', ''age'': 42})' type: object required: - label - type title: EntityExtractionExample description: >- Example entity for guiding entity extraction. Used to provide domain-specific examples to the LLM of what entities to extract. These examples help steer the extraction process toward entities relevant to your domain. EntityResolutionExample: properties: canonical: type: string title: Canonical description: The canonical (standard/preferred) form of the entity variants: items: type: string type: array title: Variants description: List of variant forms that should resolve to the canonical form type: object required: - canonical - variants title: EntityResolutionExample description: >- Example for entity resolution, showing how variants should be grouped. Entity resolution is the process of identifying when different references (variants) in text refer to the same real-world entity. These examples help the LLM understand domain-specific patterns for resolving entities. ````