Upgraded llama_index to 10.x version

private_gpt/components/embedding/custom/sagemaker.py

@@ -3,7 +3,7 @@
 from typing import Any
 
 import boto3
-from llama_index.embeddings.base import BaseEmbedding
+from llama_index.legacy.embeddings.base import BaseEmbedding
 from pydantic import Field, PrivateAttr
 
 

private_gpt/components/embedding/embedding_component.py

@@ -1,8 +1,8 @@
 import logging
 
 from injector import inject, singleton
-from llama_index import MockEmbedding
-from llama_index.embeddings.base import BaseEmbedding
+from llama_index.legacy import MockEmbedding
+from llama_index.legacy.embeddings.base import BaseEmbedding
 
 from private_gpt.paths import models_cache_path
 from private_gpt.settings.settings import Settings
@@ -20,7 +20,7 @@ def __init__(self, settings: Settings) -> None:
         logger.info("Initializing the embedding model in mode=%s", embedding_mode)
         match embedding_mode:
             case "local":
-                from llama_index.embeddings import HuggingFaceEmbedding
+                from llama_index.legacy.embeddings import HuggingFaceEmbedding
 
                 self.embedding_model = HuggingFaceEmbedding(
                     model_name=settings.local.embedding_hf_model_name,

private_gpt/components/ingest/ingest_component.py

@@ -8,16 +8,16 @@
 from pathlib import Path
 from typing import Any
 
-from llama_index import (
+from llama_index.legacy import (
     Document,
     ServiceContext,
     StorageContext,
     VectorStoreIndex,
     load_index_from_storage,
 )
-from llama_index.data_structs import IndexDict
-from llama_index.indices.base import BaseIndex
-from llama_index.ingestion import run_transformations
+from llama_index.legacy.data_structs import IndexDict
+from llama_index.legacy.indices.base import BaseIndex
+from llama_index.legacy.ingestion import run_transformations
 
 from private_gpt.components.ingest.ingest_helper import IngestionHelper
 from private_gpt.paths import local_data_path

private_gpt/components/ingest/ingest_helper.py

@@ -1,9 +1,9 @@
 import logging
 from pathlib import Path
 
-from llama_index import Document
-from llama_index.readers import JSONReader, StringIterableReader
-from llama_index.readers.file.base import DEFAULT_FILE_READER_CLS
+from llama_index.legacy import Document
+from llama_index.legacy.readers import JSONReader, StringIterableReader
+from llama_index.legacy.readers.file.base import DEFAULT_FILE_READER_CLS
 
 logger = logging.getLogger(__name__)
 

private_gpt/components/llm/custom/sagemaker.py

@@ -7,32 +7,32 @@
 from typing import TYPE_CHECKING, Any
 
 import boto3  # type: ignore
-from llama_index.bridge.pydantic import Field
-from llama_index.llms import (
+from llama_index.legacy.bridge.pydantic import Field
+from llama_index.legacy.llms import (
     CompletionResponse,
     CustomLLM,
     LLMMetadata,
 )
-from llama_index.llms.base import (
+from llama_index.legacy.llms.base import (
     llm_chat_callback,
     llm_completion_callback,
 )
-from llama_index.llms.generic_utils import (
+from llama_index.legacy.llms.generic_utils import (
     completion_response_to_chat_response,
     stream_completion_response_to_chat_response,
 )
-from llama_index.llms.llama_utils import (
+from llama_index.legacy.llms.llama_utils import (
     completion_to_prompt as generic_completion_to_prompt,
 )
-from llama_index.llms.llama_utils import (
+from llama_index.legacy.llms.llama_utils import (
     messages_to_prompt as generic_messages_to_prompt,
 )
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
 
-    from llama_index.callbacks import CallbackManager
-    from llama_index.llms import (
+    from llama_index.legacy.callbacks import CallbackManager
+    from llama_index.legacy.llms import (
         ChatMessage,
         ChatResponse,
         ChatResponseGen,

private_gpt/components/llm/llm_component.py

@@ -1,9 +1,9 @@
 import logging
 
 from injector import inject, singleton
-from llama_index import set_global_tokenizer
-from llama_index.llms import MockLLM
-from llama_index.llms.base import LLM
+from llama_index.legacy import set_global_tokenizer
+from llama_index.legacy.llms import MockLLM
+from llama_index.llms.openai.base import LLM
 from transformers import AutoTokenizer  # type: ignore
 
 from private_gpt.components.llm.prompt_helper import get_prompt_style
@@ -31,7 +31,7 @@ def __init__(self, settings: Settings) -> None:
         logger.info("Initializing the LLM in mode=%s", llm_mode)
         match settings.llm.mode:
             case "local":
-                from llama_index.llms import LlamaCPP
+                from llama_index.legacy.llms import LlamaCPP
 
                 prompt_style = get_prompt_style(settings.local.prompt_style)
 
@@ -58,7 +58,7 @@ def __init__(self, settings: Settings) -> None:
                     context_window=settings.llm.context_window,
                 )
             case "openai":
-                from llama_index.llms import OpenAI
+                from llama_index.legacy.llms import OpenAI
 
                 openai_settings = settings.openai
                 self.llm = OpenAI(
@@ -67,7 +67,7 @@ def __init__(self, settings: Settings) -> None:
                     model=openai_settings.model,
                 )
             case "openailike":
-                from llama_index.llms import OpenAILike
+                from llama_index.legacy.llms import OpenAILike
 
                 openai_settings = settings.openai
                 self.llm = OpenAILike(
@@ -81,7 +81,7 @@ def __init__(self, settings: Settings) -> None:
             case "mock":
                 self.llm = MockLLM()
             case "ollama":
-                from llama_index.llms import Ollama
+                from llama_index.legacy.llms import Ollama
 
                 ollama_settings = settings.ollama
                 self.llm = Ollama(

private_gpt/components/llm/prompt_helper.py

@@ -3,8 +3,8 @@
 from collections.abc import Sequence
 from typing import Any, Literal
 
-from llama_index.llms import ChatMessage, MessageRole
-from llama_index.llms.llama_utils import (
+from llama_index.legacy.llms import ChatMessage, MessageRole
+from llama_index.legacy.llms.llama_utils import (
     completion_to_prompt,
     messages_to_prompt,
 )

private_gpt/components/node_store/node_store_component.py

@@ -1,9 +1,9 @@
 import logging
 
 from injector import inject, singleton
-from llama_index.storage.docstore import BaseDocumentStore, SimpleDocumentStore
-from llama_index.storage.index_store import SimpleIndexStore
-from llama_index.storage.index_store.types import BaseIndexStore
+from llama_index.legacy.storage.docstore import BaseDocumentStore, SimpleDocumentStore
+from llama_index.legacy.storage.index_store import SimpleIndexStore
+from llama_index.legacy.storage.index_store.types import BaseIndexStore
 
 from private_gpt.paths import local_data_path
 

private_gpt/components/vector_store/batched_chroma.py

@@ -1,9 +1,9 @@
 from typing import Any
 
-from llama_index.schema import BaseNode, MetadataMode
-from llama_index.vector_stores import ChromaVectorStore
-from llama_index.vector_stores.chroma import chunk_list
-from llama_index.vector_stores.utils import node_to_metadata_dict
+from llama_index.legacy.schema import BaseNode, MetadataMode
+from llama_index.legacy.vector_stores import ChromaVectorStore
+from llama_index.legacy.vector_stores.chroma import chunk_list
+from llama_index.legacy.vector_stores.utils import node_to_metadata_dict
 
 
 class BatchedChromaVectorStore(ChromaVectorStore):

private_gpt/components/vector_store/vector_store_component.py

@@ -2,9 +2,9 @@
 import typing
 
 from injector import inject, singleton
-from llama_index import VectorStoreIndex
-from llama_index.indices.vector_store import VectorIndexRetriever
-from llama_index.vector_stores.types import VectorStore
+from llama_index.legacy import VectorStoreIndex
+from llama_index.legacy.indices.vector_store import VectorIndexRetriever
+from llama_index.legacy.vector_stores.types import VectorStore
 
 from private_gpt.components.vector_store.batched_chroma import BatchedChromaVectorStore
 from private_gpt.open_ai.extensions.context_filter import ContextFilter
@@ -41,7 +41,7 @@ class VectorStoreComponent:
     def __init__(self, settings: Settings) -> None:
         match settings.vectorstore.database:
             case "pgvector":
-                from llama_index.vector_stores import PGVectorStore
+                from llama_index.legacy.vector_stores import PGVectorStore
 
                 if settings.pgvector is None:
                     raise ValueError(
@@ -85,7 +85,7 @@ def __init__(self, settings: Settings) -> None:
                 )
 
             case "qdrant":
-                from llama_index.vector_stores.qdrant import QdrantVectorStore
+                from llama_index.legacy.vector_stores.qdrant import QdrantVectorStore
                 from qdrant_client import QdrantClient
 
                 if settings.qdrant is None:

private_gpt/main.py

@@ -6,6 +6,6 @@
 from private_gpt.launcher import create_app
 
 # Add LlamaIndex simple observability
-llama_index.set_global_handler("simple")
+llama_index.legacy.set_global_handler("simple")
 
 app = create_app(global_injector)

private_gpt/open_ai/openai_models.py

@@ -3,7 +3,7 @@
 from collections.abc import Iterator
 from typing import Literal
 
-from llama_index.llms import ChatResponse, CompletionResponse
+from llama_index.legacy.llms import ChatResponse, CompletionResponse
 from pydantic import BaseModel, Field
 
 from private_gpt.server.chunks.chunks_service import Chunk

private_gpt/server/chat/chat_router.py

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

private_gpt/server/chat/chat_service.py

@@ -1,14 +1,14 @@
 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.legacy import ServiceContext, StorageContext, VectorStoreIndex
+from llama_index.legacy.chat_engine import ContextChatEngine, SimpleChatEngine
+from llama_index.legacy.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.legacy.indices.postprocessor import MetadataReplacementPostProcessor
+from llama_index.legacy.llms import ChatMessage, MessageRole
+from llama_index.legacy.types import TokenGen
 from pydantic import BaseModel
 
 from private_gpt.components.embedding.embedding_component import EmbeddingComponent

private_gpt/server/chunks/chunks_service.py

@@ -1,8 +1,8 @@
 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.legacy import ServiceContext, StorageContext, VectorStoreIndex
+from llama_index.legacy.schema import NodeWithScore
 from pydantic import BaseModel, Field
 
 from private_gpt.components.embedding.embedding_component import EmbeddingComponent
@@ -15,7 +15,7 @@
 from private_gpt.server.ingest.model import IngestedDoc
 
 if TYPE_CHECKING:
-    from llama_index.schema import RelatedNodeInfo
+    from llama_index.legacy.schema import RelatedNodeInfo
 
 
 class Chunk(BaseModel):

private_gpt/server/ingest/ingest_service.py

@@ -4,11 +4,11 @@
 from typing import AnyStr, BinaryIO
 
 from injector import inject, singleton
-from llama_index import (
+from llama_index.legacy import (
     ServiceContext,
     StorageContext,
 )
-from llama_index.node_parser import SentenceWindowNodeParser
+from llama_index.legacy.node_parser import SentenceWindowNodeParser
 
 from private_gpt.components.embedding.embedding_component import EmbeddingComponent
 from private_gpt.components.ingest.ingest_component import get_ingestion_component

private_gpt/server/ingest/model.py

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

private_gpt/ui/ui.py

@@ -10,7 +10,7 @@
 from fastapi import FastAPI
 from gradio.themes.utils.colors import slate  # type: ignore
 from injector import inject, singleton
-from llama_index.llms import ChatMessage, ChatResponse, MessageRole
+from llama_index.legacy.llms import ChatMessage, ChatResponse, MessageRole
 from pydantic import BaseModel
 
 from private_gpt.constants import PROJECT_ROOT_PATH

pyproject.toml

@@ -11,10 +11,10 @@ boto3 = "^1.28.56"
 injector = "^0.21.0"
 pyyaml = "^6.0.1"
 python-multipart = "^0.0.6"
-pypdf = "^3.16.2"
-llama-index = { extras = ["local_models"], version = "0.9.3" }
+pypdf = "^4.0.1"
+llama-index = "^0.10.12"
 watchdog = "^3.0.0"
-qdrant-client = "^1.6.9"
+qdrant-client = "^1.7.3"
 chromadb = {version = "^0.4.13", optional = true}
 asyncpg = {version = "^0.29.0", optional = true}
 pgvector = {version = "^0.2.5", optional = true}

tests/test_prompt_helper.py

@@ -1,5 +1,5 @@
 import pytest
-from llama_index.llms import ChatMessage, MessageRole
+from llama_index.legacy.llms import ChatMessage, MessageRole
 
 from private_gpt.components.llm.prompt_helper import (
     ChatMLPromptStyle,