SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 17:05:41 +01:00
Code Issues Projects Releases Packages Activity

Working refactor. Dependency clean-up pending.

Browse source
This commit is contained in:
imartinez 2024-02-28 18:45:54 +01:00
parent 12f3a39e8a
commit d0a7d991a2
20 changed files with 877 additions and 907 deletions
Download patch file Download diff file Expand all files Collapse all files

33
private_gpt/server/chat/chat_service.py
View file

@ -1,14 +1,15 @@
from dataclasses import dataclass
from injector import inject, singleton
from llama_index import ServiceContext, StorageContext, VectorStoreIndex
from llama_index.chat_engine import ContextChatEngine, SimpleChatEngine
from llama_index.chat_engine.types import (
from llama_index.core.chat_engine import ContextChatEngine, SimpleChatEngine
from llama_index.core.chat_engine.types import (
BaseChatEngine,
)
from llama_index.indices.postprocessor import MetadataReplacementPostProcessor
from llama_index.llms import ChatMessage, MessageRole
from llama_index.types import TokenGen
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.storage import StorageContext
from llama_index.core.types import TokenGen
from pydantic import BaseModel
from private_gpt.components.embedding.embedding_component import EmbeddingComponent
@ -75,20 +76,19 @@ class ChatService:
embedding_component: EmbeddingComponent,
node_store_component: NodeStoreComponent,
) -> None:
self.llm_service = llm_component
self.llm_component = llm_component
self.embedding_component = embedding_component
self.vector_store_component = vector_store_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.service_context = ServiceContext.from_defaults(
llm=llm_component.llm, embed_model=embedding_component.embedding_model
)
self.index = VectorStoreIndex.from_vector_store(
vector_store_component.vector_store,
storage_context=self.storage_context,
service_context=self.service_context,
llm=llm_component.llm,
embed_model=embedding_component.embedding_model,
show_progress=True,
)
@ -102,10 +102,17 @@ class ChatService:
vector_index_retriever = self.vector_store_component.get_retriever(
index=self.index, context_filter=context_filter
)
# TODO ContextChatEngine is still not migrated by LlamaIndex to accept
# llm directly, so we are passing legacy ServiceContext until it is fixed.
from llama_index.core import ServiceContext
return ContextChatEngine.from_defaults(
system_prompt=system_prompt,
retriever=vector_index_retriever,
service_context=self.service_context,
llm=self.llm_component.llm, # Takes no effect at the moment
service_context=ServiceContext.from_defaults(
llm=self.llm_component.llm,
embed_model=self.embedding_component.embedding_model,
),
node_postprocessors=[
MetadataReplacementPostProcessor(target_metadata_key="window"),
],
@ -113,7 +120,7 @@ class ChatService:
else:
return SimpleChatEngine.from_defaults(
system_prompt=system_prompt,
service_context=self.service_context,
llm=self.llm_component.llm,
)
def stream_chat(