feat: Upgrade to LlamaIndex to 0.10 (#1663)

* Extract optional dependencies

* Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity

* Support Ollama embeddings

* Upgrade to llamaindex 0.10.14. Remove legacy use of ServiceContext in ContextChatEngine

* Fix vector retriever filters

private_gpt/components/vector_store/batched_chroma.py

@@ -1,12 +1,28 @@
+from collections.abc import Generator
 from typing import Any
 
-from llama_index.schema import BaseNode, MetadataMode
-from llama_index.vector_stores import ChromaVectorStore
-from llama_index.vector_stores.chroma import chunk_list
-from llama_index.vector_stores.utils import node_to_metadata_dict
+from llama_index.core.schema import BaseNode, MetadataMode
+from llama_index.core.vector_stores.utils import node_to_metadata_dict
+from llama_index.vector_stores.chroma import ChromaVectorStore  # type: ignore
 
 
-class BatchedChromaVectorStore(ChromaVectorStore):
+def chunk_list(
+    lst: list[BaseNode], max_chunk_size: int
+) -> Generator[list[BaseNode], None, None]:
+    """Yield successive max_chunk_size-sized chunks from lst.
+
+    Args:
+        lst (List[BaseNode]): list of nodes with embeddings
+        max_chunk_size (int): max chunk size
+
+    Yields:
+        Generator[List[BaseNode], None, None]: list of nodes with embeddings
+    """
+    for i in range(0, len(lst), max_chunk_size):
+        yield lst[i : i + max_chunk_size]
+
+
+class BatchedChromaVectorStore(ChromaVectorStore):  # type: ignore
     """Chroma vector store, batching additions to avoid reaching the max batch limit.
 
     In this vector store, embeddings are stored within a ChromaDB collection.

private_gpt/components/vector_store/vector_store_component.py

@@ -2,11 +2,14 @@ import logging
 import typing
 
 from injector import inject, singleton
-from llama_index import VectorStoreIndex
-from llama_index.indices.vector_store import VectorIndexRetriever
-from llama_index.vector_stores.types import VectorStore
+from llama_index.core.indices.vector_store import VectorIndexRetriever, VectorStoreIndex
+from llama_index.core.vector_stores.types import (
+    FilterCondition,
+    MetadataFilter,
+    MetadataFilters,
+    VectorStore,
+)
 
-from private_gpt.components.vector_store.batched_chroma import BatchedChromaVectorStore
 from private_gpt.open_ai.extensions.context_filter import ContextFilter
 from private_gpt.paths import local_data_path
 from private_gpt.settings.settings import Settings
@@ -14,34 +17,36 @@ from private_gpt.settings.settings import Settings
 logger = logging.getLogger(__name__)
 
 
-@typing.no_type_check
-def _chromadb_doc_id_metadata_filter(
+def _doc_id_metadata_filter(
     context_filter: ContextFilter | None,
-) -> dict | None:
-    if context_filter is None or context_filter.docs_ids is None:
-        return {}  # No filter
-    elif len(context_filter.docs_ids) < 1:
-        return {"doc_id": "-"}  # Effectively filtering out all docs
-    else:
-        doc_filter_items = []
-        if len(context_filter.docs_ids) > 1:
-            doc_filter = {"$or": doc_filter_items}
-            for doc_id in context_filter.docs_ids:
-                doc_filter_items.append({"doc_id": doc_id})
-        else:
-            doc_filter = {"doc_id": context_filter.docs_ids[0]}
-        return doc_filter
+) -> MetadataFilters:
+    filters = MetadataFilters(filters=[], condition=FilterCondition.OR)
+
+    if context_filter is not None and context_filter.docs_ids is not None:
+        for doc_id in context_filter.docs_ids:
+            filters.filters.append(MetadataFilter(key="doc_id", value=doc_id))
+
+    return filters
 
 
 @singleton
 class VectorStoreComponent:
+    settings: Settings
     vector_store: VectorStore
 
     @inject
     def __init__(self, settings: Settings) -> None:
+        self.settings = settings
         match settings.vectorstore.database:
             case "pgvector":
-                from llama_index.vector_stores import PGVectorStore
+                try:
+                    from llama_index.vector_stores.postgres import (  # type: ignore
+                        PGVectorStore,
+                    )
+                except ImportError as e:
+                    raise ImportError(
+                        "Postgres dependencies not found, install with `poetry install --extras vector-stores-postgres`"
+                    ) from e
 
                 if settings.pgvector is None:
                     raise ValueError(
@@ -61,11 +66,13 @@ class VectorStoreComponent:
                     from chromadb.config import (  # type: ignore
                         Settings as ChromaSettings,
                     )
+
+                    from private_gpt.components.vector_store.batched_chroma import (
+                        BatchedChromaVectorStore,
+                    )
                 except ImportError as e:
                     raise ImportError(
-                        "'chromadb' is not installed."
-                        "To use PrivateGPT with Chroma, install the 'chroma' extra."
-                        "`poetry install --extras chroma`"
+                        "ChromaDB dependencies not found, install with `poetry install --extras vector-stores-chroma`"
                     ) from e
 
                 chroma_settings = ChromaSettings(anonymized_telemetry=False)
@@ -85,8 +92,15 @@ class VectorStoreComponent:
                 )
 
             case "qdrant":
-                from llama_index.vector_stores.qdrant import QdrantVectorStore
-                from qdrant_client import QdrantClient
+                try:
+                    from llama_index.vector_stores.qdrant import (  # type: ignore
+                        QdrantVectorStore,
+                    )
+                    from qdrant_client import QdrantClient  # type: ignore
+                except ImportError as e:
+                    raise ImportError(
+                        "Qdrant dependencies not found, install with `poetry install --extras vector-stores-qdrant`"
+                    ) from e
 
                 if settings.qdrant is None:
                     logger.info(
@@ -112,20 +126,20 @@ class VectorStoreComponent:
                     f"Vectorstore database {settings.vectorstore.database} not supported"
                 )
 
-    @staticmethod
     def get_retriever(
+        self,
         index: VectorStoreIndex,
         context_filter: ContextFilter | None = None,
         similarity_top_k: int = 2,
     ) -> VectorIndexRetriever:
-        # This way we support qdrant (using doc_ids) and chroma (using where clause)
+        # This way we support qdrant (using doc_ids) and the rest (using filters)
         return VectorIndexRetriever(
             index=index,
             similarity_top_k=similarity_top_k,
             doc_ids=context_filter.docs_ids if context_filter else None,
-            vector_store_kwargs={
-                "where": _chromadb_doc_id_metadata_filter(context_filter)
-            },
+            filters=_doc_id_metadata_filter(context_filter)
+            if self.settings.vectorstore.database != "qdrant"
+            else None,
         )
 
     def close(self) -> None: