rag.core.backends.llamaindex.backend¶

LlamaIndex ingest + query over a strategy-scoped Chroma directory.

Classes¶

LlamaIndexBackend

LlamaIndex VectorStoreIndex + Chroma backend.

Module Contents¶

class rag.core.backends.llamaindex.backend.LlamaIndexBackend[source]¶

LlamaIndex VectorStoreIndex + Chroma backend.

ingest(*, config: rag.core.config.RagConfig, rebuild: bool = True, embed_model: object | None = None) → rag.core.ingest.IngestResult[source]¶

Write PDFs into the LlamaIndex Chroma collection.

Parameters:

  • config (RagConfig) – Paths, chunking, and model settings.

  • rebuild (bool) – When True, delete the existing collection before writing.

  • embed_model (object or None) – Optional LlamaIndex embedder (tests inject a stub).

Returns:

Counts and paths for the run.

Return type:

IngestResult

ask(*, question: str, config: rag.core.config.RagConfig) → rag.core.query.QueryResult[source]¶

Answer a paper-level question from the LlamaIndex query engine.

Parameters:

  • question (str) – User question.

  • config (RagConfig) – Retrieval and model settings.

Returns:

Answer and citations.

Return type:

QueryResult

is_ready(*, config: rag.core.config.RagConfig) → bool[source]¶

Return True when the LlamaIndex Chroma collection is non-empty.

Parameters:

config (RagConfig) – Index configuration.

Returns:

True when at least one chunk is stored.

Return type:

bool