rag.core.ingest
===============

.. py:module:: rag.core.ingest

.. autoapi-nested-parse::

   PDF ingest pipeline: load → chunk → embed → Chroma (LlamaIndex path).



Classes
-------

.. autoapisummary::

   rag.core.ingest.IngestResult


Functions
---------

.. autoapisummary::

   rag.core.ingest.build_embed_model
   rag.core.ingest.load_pdf_documents
   rag.core.ingest.ingest_llamaindex
   rag.core.ingest.ingest_papers


Module Contents
---------------

.. py:class:: IngestResult

   Summary of an ingest run.

   :ivar documents: Number of page-level documents written (PDFs with extractable text).
   :vartype documents: int
   :ivar nodes: Number of chunks written to Chroma.
   :vartype nodes: int
   :ivar chroma_dir: Persistence directory used.
   :vartype chroma_dir: Path
   :ivar collection_name: Chroma collection name.

   :vartype collection_name: str


   .. py:attribute:: documents
      :type:  int


   .. py:attribute:: nodes
      :type:  int


   .. py:attribute:: chroma_dir
      :type:  pathlib.Path


   .. py:attribute:: collection_name
      :type:  str


.. py:function:: build_embed_model(*, config: rag.core.config.RagConfig) -> llama_index.embeddings.huggingface.HuggingFaceEmbedding

   Construct the local HuggingFace embedding model.

   :param config: Provides ``embed_model_name``.
   :type config: RagConfig

   :returns: LlamaIndex embedding wrapper.
   :rtype: HuggingFaceEmbedding


.. py:function:: load_pdf_documents(*, pdf_paths: collections.abc.Sequence[pathlib.Path]) -> list[llama_index.core.Document]

   Extract per-page LlamaIndex documents from PDFs.

   :param pdf_paths: PDF files to load.
   :type pdf_paths: sequence of Path

   :returns: One LlamaIndex document per extractable page.
   :rtype: list of Document

   :raises FileNotFoundError: If no page yields extractable text.


.. py:function:: ingest_llamaindex(*, config: rag.core.config.RagConfig, embed_model: llama_index.core.embeddings.BaseEmbedding | None = None, rebuild: bool = True) -> IngestResult

   Ingest PDFs with LlamaIndex into persistent Chroma.

   :param config: Paths, chunking, and model settings.
   :type config: RagConfig
   :param embed_model: Optional pre-built embedder (tests can inject a stub).
   :type embed_model: BaseEmbedding or None
   :param rebuild: When True, delete the existing collection before writing.
   :type rebuild: bool

   :returns: Counts and paths for the run.
   :rtype: IngestResult


.. py:function:: ingest_papers(*, config: rag.core.config.RagConfig, embed_model: llama_index.core.embeddings.BaseEmbedding | None = None, rebuild: bool = True) -> IngestResult

   Ingest PDFs using ``config.strategy``.

   :param config: Paths, chunking, model settings, and orchestration strategy.
   :type config: RagConfig
   :param embed_model: Optional LlamaIndex embedder (ignored by other backends).
   :type embed_model: BaseEmbedding or None
   :param rebuild: When True, delete the existing collection before writing.
   :type rebuild: bool

   :returns: Counts and paths for the run.
   :rtype: IngestResult