Query Cache

Source information for a chunk used in completion

Chunk Number

Document Id

Score

ChunkSource

Location

Message

Error Type

ValidationError

CompletionResponse

HTTPValidationError

Morphik Documentation

What is Morphik?

Getting Started

Get the most out of Morphik by customizing it to your needs

Configure Morphik

An overview of Retrieval Augmented Generation with Vector Similarity Search

Introduction to RAG

An overview of rules based ingestion in DataBridge

Rules

Using Late-interaction and Contrastive learning to achieve state-of-the-art performance in visual retrieval

Retrieving Images

Leveraging graph-based relationships for improved context and retrieval in RAG systems

Knowledge Graphs and Graph RAG

Learn how to use the Morphik UI interface

Morphik UI

Learn how to use the Morphik command-line interface

Morphik Shell

Learn how to use the Morphik Python SDK or REST API

Code

Health Check

Readiness check that verifies the application is initialized.

Readiness Check

Ingest a text document.

Args:
    request: IngestTextRequest containing:
        - content: Text content to ingest
        - filename: Optional filename to help determine content type
        - metadata: Optional metadata dictionary
        - rules: Optional list of rules. Each rule should be either:
               - MetadataExtractionRule: {"type": "metadata_extraction", "schema": {...}}
               - NaturalLanguageRule: {"type": "natural_language", "prompt": "..."}
    auth: Authentication context

Returns:
    Document: Metadata of ingested document

Ingest Text

Ingest a file document.

Args:
    file: File to ingest
    metadata: JSON string of metadata
    rules: JSON string of rules list. Each rule should be either:
           - MetadataExtractionRule: {"type": "metadata_extraction", "schema": {...}}
           - NaturalLanguageRule: {"type": "natural_language", "prompt": "..."}
    auth: Authentication context

Returns:
    Document: Metadata of ingested document

Ingest File

Batch ingest multiple files.

Args:
    files: List of files to ingest
    metadata: JSON string of metadata (either a single dict or list of dicts)
    rules: JSON string of rules list. Can be either:
           - A single list of rules to apply to all files
           - A list of rule lists, one per file
    use_colpali: Whether to use ColPali-style embedding
    parallel: Whether to process files in parallel
    auth: Authentication context

Returns:
    BatchIngestResponse containing:
        - documents: List of successfully ingested documents
        - errors: List of errors encountered during ingestion

Batch Ingest Files

Retrieve Chunks

Retrieve Documents

Retrieve multiple documents by their IDs in a single batch operation.

Batch Get Documents

Retrieve specific chunks by their document ID and chunk number in a single batch operation.

Batch Get Chunks

Generate completion using relevant chunks as context.

When graph_name is provided, the query will leverage the knowledge graph 
to enhance retrieval by finding relevant entities and their connected documents.

Query Completion

List Documents

Get Document

Delete a document and all associated data.

This endpoint deletes a document and all its associated data, including:
- Document metadata
- Document content in storage
- Document chunks and embeddings in vector store

Args:
    document_id: ID of the document to delete
    auth: Authentication context (must have write access to the document)

Returns:
    Deletion status

Delete Document

Get Document By Filename

Update a document with new text content using the specified strategy.

Args:
    document_id: ID of the document to update
    request: Text content and metadata for the update
    update_strategy: Strategy for updating the document (default: 'add')
    
Returns:
    Document: Updated document metadata

Update Document Text

Update a document with content from a file using the specified strategy.

Args:
    document_id: ID of the document to update
    file: File to add to the document
    metadata: JSON string of metadata to merge with existing metadata
    rules: JSON string of rules to apply to the content
    update_strategy: Strategy for updating the document (default: 'add')
    use_colpali: Whether to use multi-vector embedding

Returns:
    Document: Updated document metadata

Update Document File

Update only a document's metadata.

Args:
    document_id: ID of the document to update
    metadata: New metadata to merge with existing metadata

Returns:
    Document: Updated document metadata

Update Document Metadata

Get usage statistics for the authenticated user.

Get Usage Stats

Get Recent Usage

Create a new cache with specified configuration.

Create Cache

Get Cache

Update cache with new documents matching its filter.

Update Cache

Add Docs To Cache

Create a graph from documents. 
 This endpoint extracts entities and relationships from documents matching the specified filters or document IDs and creates a graph. Args:    request: CreateGraphRequest containing:
        - name: Name of the graph to create
        - filters: Optional metadata filters to determine which documents to include - documents: Optional list of specific document IDs to include
    auth: Authentication context

Returns:
    Graph: The created graph object

Create Graph

Get a graph by name.

This endpoint retrieves a graph by its name if the user has access to it.

Args:
    name: Name of the graph to retrieve
    auth: Authentication context

Returns:
    Graph: The requested graph object

Get Graph

List all graphs the user has access to.

This endpoint retrieves all graphs the user has access to.

Args:
    auth: Authentication context

Returns:
    List[Graph]: List of graph objects

List Graphs

Update an existing graph with new documents.

This endpoint processes additional documents based on the original graph filters 
and/or new filters/document IDs, extracts entities and relationships, and 
updates the graph with new information.

Args:
    name: Name of the graph to update
    request: UpdateGraphRequest containing:
        - additional_filters: Optional additional metadata filters to determine which new documents to include
        - additional_documents: Optional list of additional document IDs to include
    auth: Authentication context

Returns:
    Graph: The updated graph object

Update Graph

Generate a local URI for development. This endpoint is unprotected.

Generate Local Uri

Generate a URI for cloud hosted applications.

Generate Cloud Uri

Upgrade User Tier

Main client for document operations in Morphik

Morphik

close

ingest_text

ingest_file

retrieve_chunks

Retrieve relevant documents from DataBridge

retrieve_docs

Generate completion using relevant chunks as context

query

list_documents

get_document

get_document_by_filename

update_document_with_text

Update a document with content from a file

update_document_with_file

update_document_metadata

Update a document identified by filename with new text content

update_document_by_filename_with_text

Update a document identified by filename with content from a file

update_document_by_filename_with_file

Update a document's metadata using filename to identify the document

update_document_by_filename_metadata

Retrieve multiple documents by their IDs in a single batch operation

batch_get_documents

Retrieve specific chunks by their document ID and chunk number

batch_get_chunks

create_graph

get_graph

list_graphs

Create a new cache with specified configuration

API Reference

Query Cache

Headers

Path Parameters

Query Parameters

Response