github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-09-13 13:50:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Upgrade to LlamaIndex to 0.10 (#1663)

Browse Source 
* 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
This commit is contained in:
Iván Martínez
2024-03-06 17:51:30 +01:00
committed by GitHub
parent 12f3a39e8a
commit 45f05711eb
43 changed files with 1474 additions and 1396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
private_gpt/server/chat/chat_router.py
View File

@@ -1,5 +1,5 @@
from fastapi import APIRouter, Depends, Request
from llama_index.llms import ChatMessage, MessageRole
from llama_index.core.llms import ChatMessage, MessageRole
from pydantic import BaseModel
from starlette.responses import StreamingResponse

26
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,
)
@@ -105,7 +105,7 @@ class ChatService:
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
node_postprocessors=[
MetadataReplacementPostProcessor(target_metadata_key="window"),
],
@@ -113,7 +113,7 @@ class ChatService:
else:
return SimpleChatEngine.from_defaults(
system_prompt=system_prompt,
service_context=self.service_context,
llm=self.llm_component.llm,
)
def stream_chat(