qtype 0.1.11__py3-none-any.whl → 0.1.12__py3-none-any.whl

docs/components/ChatContent.md

@@ -0,0 +1,7 @@
+### ChatContent
+
+No documentation available.
+
+- **type** (`PrimitiveTypeEnum`): The type of content, such as 'text', 'image', etc.
+- **content** (`Any`): The actual content, which can be a string, image data, etc.
+- **mime_type** (`str | None`): The MIME type of the content, if known.

docs/components/ChatMessage.md

@@ -0,0 +1,6 @@
+### ChatMessage
+
+A standard, built-in representation of a chat message.
+
+- **role** (`MessageRole`): The role of the message sender (e.g., 'user', 'assistant').
+- **blocks** (`list[ChatContent]`): The content blocks of the chat message, which can include text, images, or other media.

docs/components/ConstantPath.md

@@ -0,0 +1,5 @@
+### ConstantPath
+
+No documentation available.
+
+- **uri** (`str`): A constant Fsspec URI.

docs/components/CustomType.md

@@ -0,0 +1,7 @@
+### CustomType
+
+A simple declaration of a custom data type by the user.
+
+- **id** (`str`): (No documentation available.)
+- **description** (`str | None`): (No documentation available.)
+- **properties** (`dict[str, str]`): (No documentation available.)

docs/components/Decoder.md

@@ -0,0 +1,8 @@
+### Decoder
+
+Defines a step that decodes string data into structured outputs.
+If parsing fails, the step will raise an error and halt execution.
+Use conditional logic in your flow to handle potential parsing errors.
+
+- **type** (`Literal`): (No documentation available.)
+- **format** (`DecoderFormat`): Format in which the decoder processes data. Defaults to JSON.

docs/components/DecoderFormat.md

@@ -0,0 +1,8 @@
+### DecoderFormat
+
+Defines the format in which the decoder step processes data.
+
+- **json**: Defines the format in which the decoder step processes data.
+- **name**: The name of the Enum member.
+- **value**: The value of the Enum member.
+- **xml**: Defines the format in which the decoder step processes data.

docs/components/DocToTextConverter.md

@@ -0,0 +1,7 @@
+### DocToTextConverter
+
+Defines a step to convert raw documents (e.g., PDF, DOCX) loaded by a DocumentSource into plain text
+using an external tool like Docling or LlamaParse for pre-processing before chunking.
+The input and output are both RAGDocument, but the output after processing with have content of type markdown.
+
+- **type** (`Literal`): (No documentation available.)

docs/components/Document.md

@@ -0,0 +1,7 @@
+### Document
+
+Schema for any valid QType document structure.
+This allows validation of standalone lists of components, individual components,
+or full QType application specs. Supports modular composition and reuse.
+
+- **root** (`Application | AuthorizationProviderList | ModelList | ToolList | TypeList | VariableList`): (No documentation available.)

docs/components/DocumentEmbedder.md

@@ -0,0 +1,7 @@
+### DocumentEmbedder
+
+Embeds document chunks using a specified embedding model.
+
+- **type** (`Literal`): (No documentation available.)
+- **cardinality** (`Literal`): Consumes one chunk and emits one embedded chunk.
+- **model** (`Reference[EmbeddingModel] | str`): Embedding model to use for vectorization.

docs/components/DocumentIndex.md

@@ -0,0 +1,7 @@
+### DocumentIndex
+
+Document search index for text-based search (e.g., Elasticsearch, OpenSearch).
+
+- **type** (`Literal`): (No documentation available.)
+- **endpoint** (`str`): URL endpoint for the search cluster (e.g., https://my-cluster.es.amazonaws.com).
+- **id_field** (`str | None`): Field name to use as document ID. If not specified, auto-detects from: _id, id, doc_id, document_id, or uuid. If all are missing, a UUID is generated.

docs/components/DocumentSearch.md

@@ -0,0 +1,7 @@
+### DocumentSearch
+
+Performs document search against a document index.
+
+- **type** (`Literal`): (No documentation available.)
+- **index** (`Reference[DocumentIndex] | str`): Index to search against (object or ID reference).
+- **query_args** (`dict[str, Any]`): The arguments (other than 'query') to specify to the query shape (see https://docs.opensearch.org/latest/query-dsl/full-text/multi-match/).

docs/components/DocumentSource.md

@@ -0,0 +1,12 @@
+### DocumentSource
+
+A source of documents that will be used in retrieval augmented generation.
+It uses LlamaIndex readers to load one or more raw Documents
+from a specified path or system (e.g., Google Drive, web page).
+See https://github.com/run-llama/llama_index/tree/main/llama-index-integrations/readers
+
+- **type** (`Literal`): (No documentation available.)
+- **reader_module** (`str`): Module path of the LlamaIndex Reader).
+- **args** (`dict[str, Any]`): Reader-specific arguments to pass to the Reader constructor.
+- **loader_args** (`dict[str, Any]`): Loader-specific arguments to pass to the load_data method.
+- **auth** (`Reference[AuthProviderType] | str | None`): AuthorizationProvider for accessing the source.

docs/components/DocumentSplitter.md

@@ -0,0 +1,10 @@
+### DocumentSplitter
+
+Configuration for chunking/splitting documents into embeddable nodes/chunks.
+
+- **type** (`Literal`): (No documentation available.)
+- **cardinality** (`Literal`): Consumes one document and emits 0...N nodes/chunks.
+- **splitter_name** (`str`): Name of the LlamaIndex TextSplitter class.
+- **chunk_size** (`int`): Size of each chunk.
+- **chunk_overlap** (`int`): Overlap between consecutive chunks.
+- **args** (`dict[str, Any]`): Additional arguments specific to the chosen splitter class.

docs/components/Echo.md

@@ -0,0 +1,8 @@
+### Echo
+
+Defines a step that echoes its inputs as outputs.
+Useful for debugging flows by inspecting variable values at a specific
+point in the execution pipeline. The step simply passes through all input
+variables as outputs without modification.
+
+- **type** (`Literal`): (No documentation available.)

docs/components/Embedding.md

@@ -0,0 +1,7 @@
+### Embedding
+
+A standard, built-in representation of a vector embedding.
+
+- **vector** (`list[float]`): The vector representation of the embedding.
+- **content** (`Any | None`): The original content that was embedded.
+- **metadata** (`dict[str, Any]`): Metadata associated with the embedding.

docs/components/EmbeddingModel.md

@@ -0,0 +1,6 @@
+### EmbeddingModel
+
+Describes an embedding model configuration, extending the base Model class.
+
+- **type** (`Literal`): (No documentation available.)
+- **dimensions** (`int`): Dimensionality of the embedding vectors produced by this model.

docs/components/FieldExtractor.md

@@ -0,0 +1,20 @@
+### FieldExtractor
+
+Extracts specific fields from input data using JSONPath expressions.
+This step uses JSONPath syntax to extract data from structured inputs
+(Pydantic models, dicts, lists). The input is first converted to a dict
+using model_dump() if it's a Pydantic model, then the JSONPath expression
+is evaluated.
+If the JSONPath matches multiple values, the step yields multiple output
+messages (1-to-many cardinality). If it matches a single value, it yields
+one output message. If it matches nothing, it raises an error.
+The extracted data is used to construct the output variable by passing it
+as keyword arguments to the output type's constructor.
+Example JSONPath expressions:
+- `$.field_name` - Extract a single field
+- `$.items[*]` - Extract all items from a list
+- `$.items[?(@.price > 10)]` - Filter items by condition
+
+- **type** (`Literal`): (No documentation available.)
+- **json_path** (`str`): JSONPath expression to extract data from the input. Uses jsonpath-ng syntax.
+- **fail_on_missing** (`bool`): Whether to raise an error if the JSONPath matches no data. If False, returns None.

docs/components/FileSource.md

@@ -0,0 +1,6 @@
+### FileSource
+
+File source that reads data from a file using fsspec-compatible URIs.
+
+- **type** (`Literal`): (No documentation available.)
+- **path** (`ConstantPath | Reference[Variable] | str`): Reference to a variable with an fsspec-compatible URI to read from, or the uri itself.

docs/components/FileWriter.md

@@ -0,0 +1,7 @@
+### FileWriter
+
+File writer that writes data to a file using fsspec-compatible URIs.
+
+- **type** (`Literal`): (No documentation available.)
+- **path** (`ConstantPath | Reference[Variable] | str`): Reference to a variable with an fsspec-compatible URI to read from, or the uri itself.
+- **batch_config** (`BatchConfig`): Configuration for processing the input stream in batches. If omitted, the step processes items one by one.

docs/components/Flow.md

@@ -0,0 +1,14 @@
+### Flow
+
+Defines a flow of steps that can be executed in sequence or parallel.
+If input or output variables are not specified, they are inferred from
+the first and last step, respectively.
+
+- **id** (`str`): Unique ID of the flow.
+- **type** (`Literal`): (No documentation available.)
+- **description** (`str | None`): Optional description of the flow.
+- **steps** (`list[StepType | Reference[StepType]]`): List of steps or references to steps
+- **interface** (`FlowInterface | None`): (No documentation available.)
+- **variables** (`list[Variable]`): List of variables available at the application scope.
+- **inputs** (`list[Reference[Variable] | str]`): Input variables required by this step.
+- **outputs** (`list[Reference[Variable] | str]`): Resulting variables

docs/components/FlowInterface.md

@@ -0,0 +1,7 @@
+### FlowInterface
+
+Defines the public-facing contract for a Flow, guiding the UI
+and session management.
+
+- **type** (`Literal`): (No documentation available.)
+- **session_inputs** (`list[Reference[Variable] | str]`): A list of input variable IDs that are set once and then persisted across a session.

docs/components/Index.md

@@ -0,0 +1,8 @@
+### Index
+
+Base class for searchable indexes that can be queried by search steps.
+
+- **id** (`str`): Unique ID of the index.
+- **args** (`dict[str, Any]`): Index-specific configuration and connection parameters.
+- **auth** (`Reference[AuthProviderType] | str | None`): AuthorizationProvider for accessing the index.
+- **name** (`str`): Name of the index/collection/table.

docs/components/IndexUpsert.md

@@ -0,0 +1,6 @@
+### IndexUpsert
+
+No documentation available.
+
+- **type** (`Literal`): (No documentation available.)
+- **index** (`Reference[IndexType] | str`): Index to upsert into (object or ID reference).

docs/components/InvokeEmbedding.md

@@ -0,0 +1,7 @@
+### InvokeEmbedding
+
+Defines a step that generates embeddings using an embedding model.
+It takes input variables and produces output variables containing the embeddings.
+
+- **type** (`Literal`): (No documentation available.)
+- **model** (`Reference[EmbeddingModel] | str`): The embedding model to use.

docs/components/InvokeFlow.md

@@ -0,0 +1,8 @@
+### InvokeFlow
+
+Invokes a flow with input and output bindings.
+
+- **type** (`Literal`): (No documentation available.)
+- **flow** (`Reference[Flow] | str`): Flow to invoke.
+- **input_bindings** (`dict[Reference[Variable], str]`): Mapping from variable references to flow input variable IDs.
+- **output_bindings** (`dict[Reference[Variable], str]`): Mapping from variable references to flow output variable IDs.

docs/components/InvokeTool.md

@@ -0,0 +1,8 @@
+### InvokeTool
+
+Invokes a tool with input and output bindings.
+
+- **type** (`Literal`): (No documentation available.)
+- **tool** (`Reference[ToolType] | str`): Tool to invoke.
+- **input_bindings** (`dict[str, str]`): Mapping from variable references to tool input parameter names.
+- **output_bindings** (`dict[str, str]`): Mapping from variable references to tool output parameter names.

docs/components/LLMInference.md

@@ -0,0 +1,9 @@
+### LLMInference
+
+Defines a step that performs inference using a language model.
+It can take input variables and produce output variables based on the model's response.
+
+- **type** (`Literal`): (No documentation available.)
+- **memory** (`Reference[Memory] | str | None`): A reference to a Memory object to retain context across interactions.
+- **model** (`Reference[Model] | str`): The model to use for inference.
+- **system_message** (`str | None`): Optional system message to set the context for the model.

docs/components/ListType.md

@@ -0,0 +1,5 @@
+### ListType
+
+Represents a list type with a specific element type.
+
+- **element_type** (`PrimitiveTypeEnum | str`): Type of elements in the list (primitive type or custom type reference)

docs/components/Memory.md

@@ -0,0 +1,8 @@
+### Memory
+
+Session or persistent memory used to store relevant conversation or state data across steps or turns.
+
+- **id** (`str`): Unique ID of the memory block.
+- **token_limit** (`int`): Maximum number of tokens to store in memory.
+- **chat_history_token_ratio** (`float`): Ratio of chat history tokens to total memory tokens.
+- **token_flush_size** (`int`): Size of memory to flush when it exceeds the token limit.

docs/components/MessageRole.md

@@ -0,0 +1,14 @@
+### MessageRole
+
+An enumeration.
+
+- **assistant**: An enumeration.
+- **chatbot**: An enumeration.
+- **developer**: An enumeration.
+- **function**: An enumeration.
+- **model**: An enumeration.
+- **name**: The name of the Enum member.
+- **system**: An enumeration.
+- **tool**: An enumeration.
+- **user**: An enumeration.
+- **value**: The value of the Enum member.

docs/components/Model.md

@@ -0,0 +1,10 @@
+### Model
+
+Describes a generative model configuration, including provider and model ID.
+
+- **type** (`Literal`): (No documentation available.)
+- **id** (`str`): Unique ID for the model.
+- **auth** (`Reference[AuthProviderType] | str | None`): AuthorizationProvider used for model access.
+- **inference_params** (`dict[str, Any]`): Optional inference parameters like temperature or max_tokens.
+- **model_id** (`str | None`): The specific model name or ID for the provider. If None, id is used
+- **provider** (`Literal`): Name of the provider, e.g., openai or anthropic.

docs/components/ModelList.md

@@ -0,0 +1,5 @@
+### ModelList
+
+Schema for a standalone list of models.
+
+- **root** (`list[Annotated]`): (No documentation available.)

docs/components/OAuth2AuthProvider.md

@@ -0,0 +1,9 @@
+### OAuth2AuthProvider
+
+OAuth2 authentication provider.
+
+- **type** (`Literal`): (No documentation available.)
+- **client_id** (`str`): OAuth2 client ID.
+- **client_secret** (`str | SecretReference`): OAuth2 client secret.
+- **token_url** (`str`): Token endpoint URL.
+- **scopes** (`list[str]`): OAuth2 scopes required.

docs/components/PrimitiveTypeEnum.md

@@ -0,0 +1,21 @@
+### PrimitiveTypeEnum
+
+Represents the type of data a user or system input can accept within the DSL.
+
+- **audio**: Represents the type of data a user or system input can accept within the DSL.
+- **boolean**: Represents the type of data a user or system input can accept within the DSL.
+- **bytes**: Represents the type of data a user or system input can accept within the DSL.
+- **citation_document**: Represents the type of data a user or system input can accept within the DSL.
+- **citation_url**: Represents the type of data a user or system input can accept within the DSL.
+- **date**: Represents the type of data a user or system input can accept within the DSL.
+- **datetime**: Represents the type of data a user or system input can accept within the DSL.
+- **file**: Represents the type of data a user or system input can accept within the DSL.
+- **float**: Represents the type of data a user or system input can accept within the DSL.
+- **image**: Represents the type of data a user or system input can accept within the DSL.
+- **int**: Represents the type of data a user or system input can accept within the DSL.
+- **name**: The name of the Enum member.
+- **text**: Represents the type of data a user or system input can accept within the DSL.
+- **thinking**: Represents the type of data a user or system input can accept within the DSL.
+- **time**: Represents the type of data a user or system input can accept within the DSL.
+- **value**: The value of the Enum member.
+- **video**: Represents the type of data a user or system input can accept within the DSL.

docs/components/PromptTemplate.md

@@ -0,0 +1,7 @@
+### PromptTemplate
+
+Defines a prompt template with a string format and variable bindings.
+This is used to generate prompts dynamically based on input variables.
+
+- **type** (`Literal`): (No documentation available.)
+- **template** (`str`): String template for the prompt with variable placeholders.

docs/components/PythonFunctionTool.md

@@ -0,0 +1,7 @@
+### PythonFunctionTool
+
+Tool that calls a Python function.
+
+- **type** (`Literal`): (No documentation available.)
+- **function_name** (`str`): Name of the Python function to call.
+- **module_path** (`str`): Optional module path where the function is defined.

docs/components/RAGChunk.md

@@ -0,0 +1,7 @@
+### RAGChunk
+
+A standard, built-in representation of a chunk of a document used in Retrieval-Augmented Generation (RAG).
+
+- **chunk_id** (`str`): An unique identifier for the chunk.
+- **document_id** (`str`): The identifier of the parent document.
+- **vector** (`list[float] | None`): Optional vector embedding for the chunk.

docs/components/RAGDocument.md

@@ -0,0 +1,10 @@
+### RAGDocument
+
+A standard, built-in representation of a document used in Retrieval-Augmented Generation (RAG).
+
+- **content** (`Any`): The main content of the document.
+- **file_id** (`str`): An unique identifier for the file.
+- **file_name** (`str`): The name of the file.
+- **uri** (`str | None`): The URI where the document can be found.
+- **metadata** (`dict[str, Any]`): Metadata associated with the document.
+- **type** (`PrimitiveTypeEnum`): The type of the document content (e.g., 'text', 'image').

docs/components/RAGSearchResult.md

@@ -0,0 +1,8 @@
+### RAGSearchResult
+
+A standard, built-in representation of a search result from a RAG vector search.
+Note: doc_id is duplicated from content.document_id for convenience.
+
+- **content** (`RAGChunk`): The RAG chunk returned as a search result.
+- **doc_id** (`str`): The document ID (duplicated from content.document_id).
+- **score** (`float`): The similarity score of the chunk with respect to the query.

docs/components/Reranker.md

@@ -0,0 +1,5 @@
+### Reranker
+
+Reranks a list of documents based on relevance to a query using an LLM.
+
+- **type** (`Literal`): (No documentation available.)

docs/components/SQLSource.md

@@ -0,0 +1,8 @@
+### SQLSource
+
+SQL database source that executes queries and emits rows.
+
+- **type** (`Literal`): (No documentation available.)
+- **query** (`str`): SQL query to execute. Inputs are injected as params.
+- **connection** (`str | SecretReference`): Database connection string or reference to auth provider. Typically in SQLAlchemy format.
+- **auth** (`Reference[AuthProviderType] | str | None`): Optional AuthorizationProvider for database authentication.

docs/components/Search.md

@@ -0,0 +1,7 @@
+### Search
+
+Base class for search operations against indexes.
+
+- **filters** (`dict[str, Any]`): Optional filters to apply during search.
+- **index** (`Reference[IndexType] | str`): Index to search against (object or ID reference).
+- **default_top_k** (`int | None`): Number of top results to retrieve if not provided in the inputs.

docs/components/SearchResult.md

@@ -0,0 +1,7 @@
+### SearchResult
+
+A standard, built-in representation of a search result.
+
+- **content** (`Any`): The content of the search result.
+- **doc_id** (`str`): The identifier of the document from which the result was retrieved.
+- **score** (`float`): The relevance score of the search result with respect to the query.

docs/components/SecretManager.md

@@ -0,0 +1,7 @@
+### SecretManager
+
+Base class for secret manager configurations.
+
+- **id** (`str`): Unique ID for this secret manager configuration.
+- **type** (`str`): The type of secret manager.
+- **auth** (`Reference[AuthProviderType] | str`): AuthorizationProvider used to access this secret manager.

docs/components/SecretReference.md

@@ -0,0 +1,7 @@
+### SecretReference
+
+A reference to a secret in the application's configured SecretManager.
+This value is resolved at runtime by the interpreter.
+
+- **secret_name** (`str`): The name, ID, or ARN of the secret to fetch (e.g., 'my-project/db-password').
+- **key** (`str | None`): Optional key if the secret is a JSON blob or map (e.g., a specific key in a K8s secret).

docs/components/Source.md

@@ -0,0 +1,6 @@
+### Source
+
+Base class for data sources
+
+- **id** (`str`): Unique ID of the data source.
+- **cardinality** (`Literal`): Sources always emit 0...N instances of the outputs.

docs/components/Step.md

@@ -0,0 +1,9 @@
+### Step
+
+Base class for components that take inputs and produce outputs.
+
+- **id** (`str`): Unique ID of this component.
+- **type** (`str`): Type of the step component.
+- **cardinality** (`StepCardinality`): Does this step emit 1 (one) or 0...N (many) instances of the outputs?
+- **inputs** (`list[Reference[Variable] | str]`): References to the variables required by this step.
+- **outputs** (`list[Reference[Variable] | str]`): References to the variables where output is stored.

docs/components/TelemetrySink.md

@@ -0,0 +1,9 @@
+### TelemetrySink
+
+Defines an observability endpoint for collecting telemetry data from the QType runtime.
+
+- **id** (`str`): Unique ID of the telemetry sink configuration.
+- **provider** (`Literal`): (No documentation available.)
+- **auth** (`Reference[AuthProviderType] | str | None`): AuthorizationProvider used to authenticate telemetry data transmission.
+- **endpoint** (`str | SecretReference`): URL endpoint where telemetry data will be sent.
+- **args** (`dict[str, Any]`): Additional configuration arguments specific to the telemetry sink type.

docs/components/Tool.md

@@ -0,0 +1,9 @@
+### Tool
+
+Base class for callable functions or external operations available to the model or as a step in a flow.
+
+- **id** (`str`): Unique ID of this component.
+- **name** (`str`): Name of the tool function.
+- **description** (`str`): Description of what the tool does.
+- **inputs** (`dict[str, ToolParameter]`): Input parameters required by this tool.
+- **outputs** (`dict[str, ToolParameter]`): Output parameters produced by this tool.

docs/components/ToolList.md

@@ -0,0 +1,5 @@
+### ToolList
+
+Schema for a standalone list of tools.
+
+- **root** (`list[Annotated]`): (No documentation available.)

docs/components/ToolParameter.md

@@ -0,0 +1,6 @@
+### ToolParameter
+
+Defines a tool input or output parameter with type and optional flag.
+
+- **type** (`VariableType | str`): (No documentation available.)
+- **optional** (`bool`): Whether this parameter is optional

docs/components/TypeList.md

@@ -0,0 +1,5 @@
+### TypeList
+
+Schema for a standalone list of type definitions.
+
+- **root** (`list[CustomType]`): (No documentation available.)

docs/components/Variable.md

@@ -0,0 +1,6 @@
+### Variable
+
+Schema for a variable that can serve as input, output, or parameter within the DSL.
+
+- **id** (`str`): Unique ID of the variable. Referenced in prompts or steps.
+- **type** (`VariableType | str`): Type of data expected or produced. Either a CustomType or domain specific type.

docs/components/VariableList.md

@@ -0,0 +1,5 @@
+### VariableList
+
+Schema for a standalone list of variables.
+
+- **root** (`list[Variable]`): (No documentation available.)

docs/components/VectorIndex.md

@@ -0,0 +1,7 @@
+### VectorIndex
+
+Vector database index for similarity search using embeddings.
+
+- **type** (`Literal`): (No documentation available.)
+- **module** (`str`): Python module path for the vector store implementation (e.g., 'llama_index.vector_stores.qdrant.QdrantVectorStore').
+- **embedding_model** (`Reference[EmbeddingModel] | str`): Embedding model used to vectorize queries and documents.

docs/components/VectorSearch.md

@@ -0,0 +1,6 @@
+### VectorSearch
+
+Performs vector similarity search against a vector index.
+
+- **type** (`Literal`): (No documentation available.)
+- **index** (`Reference[VectorIndex] | str`): Index to search against (object or ID reference).

docs/components/VertexAuthProvider.md

@@ -0,0 +1,9 @@
+### VertexAuthProvider
+
+Google Vertex authentication provider supporting gcloud profile or service account.
+
+- **type** (`Literal`): (No documentation available.)
+- **profile_name** (`str | None`): Local gcloud profile name (if using existing CLI credentials).
+- **project_id** (`str | None`): Explicit GCP project ID override (if different from profile).
+- **service_account_file** (`str | None`): Path to a service account JSON key file.
+- **region** (`str | None`): Vertex region (e.g., us-central1).

docs/components/Writer.md

@@ -0,0 +1,5 @@
+### Writer
+
+Base class for things that write data in batches.
+
+- **id** (`str`): Unique ID of the data writer.