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/ingest/ingest_service.py

@@ -4,11 +4,8 @@ from pathlib import Path
 from typing import AnyStr, BinaryIO
 
 from injector import inject, singleton
-from llama_index import (
-    ServiceContext,
-    StorageContext,
-)
-from llama_index.node_parser import SentenceWindowNodeParser
+from llama_index.core.node_parser import SentenceWindowNodeParser
+from llama_index.core.storage import StorageContext
 
 from private_gpt.components.embedding.embedding_component import EmbeddingComponent
 from private_gpt.components.ingest.ingest_component import get_ingestion_component
@@ -40,17 +37,12 @@ class IngestService:
             index_store=node_store_component.index_store,
         )
         node_parser = SentenceWindowNodeParser.from_defaults()
-        self.ingest_service_context = ServiceContext.from_defaults(
-            llm=self.llm_service.llm,
-            embed_model=embedding_component.embedding_model,
-            node_parser=node_parser,
-            # Embeddings done early in the pipeline of node transformations, right
-            # after the node parsing
-            transformations=[node_parser, embedding_component.embedding_model],
-        )
 
         self.ingest_component = get_ingestion_component(
-            self.storage_context, self.ingest_service_context, settings=settings()
+            self.storage_context,
+            embed_model=embedding_component.embedding_model,
+            transformations=[node_parser, embedding_component.embedding_model],
+            settings=settings(),
         )
 
     def _ingest_data(self, file_name: str, file_data: AnyStr) -> list[IngestedDoc]:

private_gpt/server/ingest/ingest_watcher.py

@@ -3,10 +3,9 @@ from pathlib import Path
 from typing import Any
 
 from watchdog.events import (
-    DirCreatedEvent,
-    DirModifiedEvent,
     FileCreatedEvent,
     FileModifiedEvent,
+    FileSystemEvent,
     FileSystemEventHandler,
 )
 from watchdog.observers import Observer
@@ -20,11 +19,11 @@ class IngestWatcher:
         self.on_file_changed = on_file_changed
 
         class Handler(FileSystemEventHandler):
-            def on_modified(self, event: DirModifiedEvent | FileModifiedEvent) -> None:
+            def on_modified(self, event: FileSystemEvent) -> None:
                 if isinstance(event, FileModifiedEvent):
                     on_file_changed(Path(event.src_path))
 
-            def on_created(self, event: DirCreatedEvent | FileCreatedEvent) -> None:
+            def on_created(self, event: FileSystemEvent) -> None:
                 if isinstance(event, FileCreatedEvent):
                     on_file_changed(Path(event.src_path))
 

private_gpt/server/ingest/model.py

@@ -1,6 +1,6 @@
 from typing import Any, Literal
 
-from llama_index import Document
+from llama_index.core.schema import Document
 from pydantic import BaseModel, Field