Contextual Retrieval (#4029)

* contextual rag implementation

* WIP

* indexing test fix

* workaround for chunking errors, WIP on fixing massive memory cost

* mypy and test fixes

* reformatting

* fixed rebase

backend/onyx/seeding/load_docs.py

@@ -87,6 +87,9 @@ def _create_indexable_chunks(
             metadata_suffix_keyword="",
             mini_chunk_texts=None,
             large_chunk_reference_ids=[],
+            doc_summary="",
+            chunk_context="",
+            contextual_rag_reserved_tokens=0,
             embeddings=ChunkEmbedding(
                 full_embedding=preprocessed_doc["content_embedding"],
                 mini_chunk_embeddings=[],