Merge branch 'main' into dev

# Conflicts:
#	docker-compose.yaml
#	poetry.lock
#	pyproject.toml
#	settings.yaml

private_gpt/server/chat/chat_service.py

@@ -8,6 +8,10 @@ from llama_index.core.chat_engine.types import (
 from llama_index.core.indices import VectorStoreIndex
 from llama_index.core.indices.postprocessor import MetadataReplacementPostProcessor
 from llama_index.core.llms import ChatMessage, MessageRole
+from llama_index.core.postprocessor import (
+    SentenceTransformerRerank,
+    SimilarityPostprocessor,
+)
 from llama_index.core.storage import StorageContext
 from llama_index.core.types import TokenGen
 from pydantic import BaseModel
@@ -20,6 +24,7 @@ from private_gpt.components.vector_store.vector_store_component import (
 )
 from private_gpt.open_ai.extensions.context_filter import ContextFilter
 from private_gpt.server.chunks.chunks_service import Chunk
+from private_gpt.settings.settings import Settings
 
 
 class Completion(BaseModel):
@@ -68,14 +73,18 @@ class ChatEngineInput:
 
 @singleton
 class ChatService:
+    settings: Settings
+
     @inject
     def __init__(
         self,
+        settings: Settings,
         llm_component: LLMComponent,
         vector_store_component: VectorStoreComponent,
         embedding_component: EmbeddingComponent,
         node_store_component: NodeStoreComponent,
     ) -> None:
+        self.settings = settings
         self.llm_component = llm_component
         self.embedding_component = embedding_component
         self.vector_store_component = vector_store_component
@@ -98,17 +107,31 @@ class ChatService:
         use_context: bool = False,
         context_filter: ContextFilter | None = None,
     ) -> BaseChatEngine:
+        settings = self.settings
         if use_context:
             vector_index_retriever = self.vector_store_component.get_retriever(
-                index=self.index, context_filter=context_filter
+                index=self.index,
+                context_filter=context_filter,
+                similarity_top_k=self.settings.rag.similarity_top_k,
             )
+            node_postprocessors = [
+                MetadataReplacementPostProcessor(target_metadata_key="window"),
+                SimilarityPostprocessor(
+                    similarity_cutoff=settings.rag.similarity_value
+                ),
+            ]
+
+            if settings.rag.rerank.enabled:
+                rerank_postprocessor = SentenceTransformerRerank(
+                    model=settings.rag.rerank.model, top_n=settings.rag.rerank.top_n
+                )
+                node_postprocessors.append(rerank_postprocessor)
+
             return ContextChatEngine.from_defaults(
                 system_prompt=system_prompt,
                 retriever=vector_index_retriever,
                 llm=self.llm_component.llm,  # Takes no effect at the moment
-                node_postprocessors=[
-                    MetadataReplacementPostProcessor(target_metadata_key="window"),
-                ],
+                node_postprocessors=node_postprocessors,
             )
         else:
             return SimpleChatEngine.from_defaults(

private_gpt/server/ingest/ingest_service.py

@@ -1,7 +1,7 @@
 import logging
 import tempfile
 from pathlib import Path
-from typing import AnyStr, BinaryIO
+from typing import TYPE_CHECKING, AnyStr, BinaryIO
 
 from injector import inject, singleton
 from llama_index.core.node_parser import SentenceWindowNodeParser
@@ -17,6 +17,9 @@ from private_gpt.components.vector_store.vector_store_component import (
 from private_gpt.server.ingest.model import IngestedDoc
 from private_gpt.settings.settings import settings
 
+if TYPE_CHECKING:
+    from llama_index.core.storage.docstore.types import RefDocInfo
+
 logger = logging.getLogger(__name__)
 
 
@@ -86,17 +89,15 @@ class IngestService:
         return [IngestedDoc.from_document(document) for document in documents]
 
     def list_ingested(self) -> list[IngestedDoc]:
-        ingested_docs = []
+        ingested_docs: list[IngestedDoc] = []
         try:
             docstore = self.storage_context.docstore
-            ingested_docs_ids: set[str] = set()
+            ref_docs: dict[str, RefDocInfo] | None = docstore.get_all_ref_doc_info()
 
-            for node in docstore.docs.values():
-                if node.ref_doc_id is not None:
-                    ingested_docs_ids.add(node.ref_doc_id)
+            if not ref_docs:
+                return ingested_docs
 
-            for doc_id in ingested_docs_ids:
-                ref_doc_info = docstore.get_ref_doc_info(ref_doc_id=doc_id)
+            for doc_id, ref_doc_info in ref_docs.items():
                 doc_metadata = None
                 if ref_doc_info is not None and ref_doc_info.metadata is not None:
                     doc_metadata = IngestedDoc.curate_metadata(ref_doc_info.metadata)