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/server/chunks/chunks_service.py

@@ -1,8 +1,9 @@
 from typing import TYPE_CHECKING, Literal
 
 from injector import inject, singleton
-from llama_index import ServiceContext, StorageContext, VectorStoreIndex
-from llama_index.schema import NodeWithScore
+from llama_index.core.indices import VectorStoreIndex
+from llama_index.core.schema import NodeWithScore
+from llama_index.core.storage import StorageContext
 from pydantic import BaseModel, Field
 
 from private_gpt.components.embedding.embedding_component import EmbeddingComponent
@@ -15,7 +16,7 @@ from private_gpt.open_ai.extensions.context_filter import ContextFilter
 from private_gpt.server.ingest.model import IngestedDoc
 
 if TYPE_CHECKING:
-    from llama_index.schema import RelatedNodeInfo
+    from llama_index.core.schema import RelatedNodeInfo
 
 
 class Chunk(BaseModel):
@@ -63,14 +64,13 @@ class ChunksService:
         node_store_component: NodeStoreComponent,
     ) -> None:
         self.vector_store_component = vector_store_component
+        self.llm_component = llm_component
+        self.embedding_component = embedding_component
         self.storage_context = StorageContext.from_defaults(
             vector_store=vector_store_component.vector_store,
             docstore=node_store_component.doc_store,
             index_store=node_store_component.index_store,
         )
-        self.query_service_context = ServiceContext.from_defaults(
-            llm=llm_component.llm, embed_model=embedding_component.embedding_model
-        )
 
     def _get_sibling_nodes_text(
         self, node_with_score: NodeWithScore, related_number: int, forward: bool = True
@@ -103,7 +103,8 @@ class ChunksService:
         index = VectorStoreIndex.from_vector_store(
             self.vector_store_component.vector_store,
             storage_context=self.storage_context,
-            service_context=self.query_service_context,
+            llm=self.llm_component.llm,
+            embed_model=self.embedding_component.embedding_model,
             show_progress=True,
         )
         vector_index_retriever = self.vector_store_component.get_retriever(