nat.plugins.rag.models#

Classes#

RAGResultBase

Base model for RAG tool results.

RAGSearchResult

RAG search result.

RAGGenerateResult

RAG generation result.

Module Contents#

class RAGResultBase(/, **data: Any)#

Bases: pydantic.BaseModel

Base model for RAG tool results.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config#

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class RAGSearchResult(/, **data: Any)#

Bases: RAGResultBase

RAG search result.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

citations: nvidia_rag.rag_server.response_generator.Citations#
class RAGGenerateResult(/, **data: Any)#

Bases: RAGResultBase

RAG generation result.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

answer: str#
citations: nvidia_rag.rag_server.response_generator.Citations | None = None#