Update poetry lock (#1209)

* Update the version of llama_index used to fix transient openai errors

* Update poetry.lock file

* Make `local` mode the default mode by default

private_gpt/components/vector_store/batched_chroma.py

@@ -44,12 +44,12 @@ def __init__(
         )
         self.chroma_client = chroma_client
 
-    def add(self, nodes: list[BaseNode]) -> list[str]:
+    def add(self, nodes: list[BaseNode], **add_kwargs: Any) -> list[str]:
         """Add nodes to index, batching the insertion to avoid issues.
 
         Args:
             nodes: List[BaseNode]: list of nodes with embeddings
-
+            add_kwargs: _
         """
         if not self.chroma_client:
             raise ValueError("Client not initialized")

private_gpt/components/vector_store/vector_store_component.py

@@ -46,8 +46,11 @@ def __init__(self) -> None:
             "make_this_parameterizable_per_api_call"
         )  # TODO
 
-        self.vector_store = BatchedChromaVectorStore(
-            chroma_client=chroma_client, chroma_collection=chroma_collection
+        self.vector_store = typing.cast(
+            VectorStore,
+            BatchedChromaVectorStore(
+                chroma_client=chroma_client, chroma_collection=chroma_collection
+            ),
         )
 
     @staticmethod

private_gpt/open_ai/openai_models.py

@@ -1,6 +1,7 @@
 import time
 import uuid
 from collections.abc import Iterator
+from typing import Literal
 
 from llama_index.llms import ChatResponse, CompletionResponse
 from pydantic import BaseModel, Field
@@ -21,7 +22,7 @@ class OpenAIMessage(BaseModel):
     (providing a default response, not AI generated).
     """
 
-    role: str = Field(default="user", enum=["assistant", "system", "user"])
+    role: Literal["assistant", "system", "user"] = Field(default="user")
     content: str | None
 
 
@@ -46,9 +47,9 @@ class OpenAICompletion(BaseModel):
     """
 
     id: str
-    object: str = Field("completion", enum=["completion", "completion.chunk"])
+    object: Literal["completion", "completion.chunk"] = Field(default="completion")
     created: int = Field(..., examples=[1623340000])
-    model: str = Field(enum=["private-gpt"])
+    model: Literal["private-gpt"]
     choices: list[OpenAIChoice]
 
     @classmethod

private_gpt/server/chunks/chunks_router.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from fastapi import APIRouter
 from pydantic import BaseModel, Field
 
@@ -16,8 +18,8 @@ class ChunksBody(BaseModel):
 
 
 class ChunksResponse(BaseModel):
-    object: str = Field(enum=["list"])
-    model: str = Field(enum=["private-gpt"])
+    object: Literal["list"]
+    model: Literal["private-gpt"]
     data: list[Chunk]
 
 

private_gpt/server/chunks/chunks_service.py

@@ -1,4 +1,4 @@
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Literal
 
 from injector import inject, singleton
 from llama_index import ServiceContext, StorageContext, VectorStoreIndex
@@ -19,7 +19,7 @@
 
 
 class Chunk(BaseModel):
-    object: str = Field(enum=["context.chunk"])
+    object: Literal["context.chunk"]
     score: float = Field(examples=[0.023])
     document: IngestedDoc
     text: str = Field(examples=["Outbound sales increased 20%, driven by new leads."])

private_gpt/server/embeddings/embeddings_router.py

@@ -1,5 +1,7 @@
+from typing import Literal
+
 from fastapi import APIRouter
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 
 from private_gpt.di import root_injector
 from private_gpt.server.embeddings.embeddings_service import (
@@ -15,8 +17,8 @@ class EmbeddingsBody(BaseModel):
 
 
 class EmbeddingsResponse(BaseModel):
-    object: str = Field(enum=["list"])
-    model: str = Field(enum=["private-gpt"])
+    object: Literal["list"]
+    model: Literal["private-gpt"]
     data: list[Embedding]
 
 

private_gpt/server/embeddings/embeddings_service.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from injector import inject, singleton
 from pydantic import BaseModel, Field
 
@@ -6,7 +8,7 @@
 
 class Embedding(BaseModel):
     index: int
-    object: str = Field(enum=["embedding"])
+    object: Literal["embedding"]
     embedding: list[float] = Field(examples=[[0.0023064255, -0.009327292]])
 
 

private_gpt/server/health/health_router.py

@@ -1,11 +1,13 @@
+from typing import Literal
+
 from fastapi import APIRouter
 from pydantic import BaseModel, Field
 
 health_router = APIRouter()
 
 
 class HealthResponse(BaseModel):
-    status: str = Field(enum=["ok"])
+    status: Literal["ok"] = Field(default="ok")
 
 
 @health_router.get("/health", tags=["Health"])

private_gpt/server/ingest/ingest_router.py

@@ -1,5 +1,7 @@
+from typing import Literal
+
 from fastapi import APIRouter, HTTPException, UploadFile
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 
 from private_gpt.di import root_injector
 from private_gpt.server.ingest.ingest_service import IngestedDoc, IngestService
@@ -8,8 +10,8 @@
 
 
 class IngestResponse(BaseModel):
-    object: str = Field(enum=["list"])
-    model: str = Field(enum=["private-gpt"])
+    object: Literal["list"]
+    model: Literal["private-gpt"]
     data: list[IngestedDoc]
 
 

private_gpt/server/ingest/ingest_service.py

@@ -1,7 +1,7 @@
 import logging
 import tempfile
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, AnyStr
+from typing import TYPE_CHECKING, Any, AnyStr, Literal
 
 from injector import inject, singleton
 from llama_index import (
@@ -40,7 +40,7 @@
 
 
 class IngestedDoc(BaseModel):
-    object: str = Field(enum=["ingest.document"])
+    object: Literal["ingest.document"]
     doc_id: str = Field(examples=["c202d5e6-7b69-4869-81cc-dd574ee8ee11"])
     doc_metadata: dict[str, Any] | None = Field(
         examples=[

private_gpt/settings/settings.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from pydantic import BaseModel, Field
 
 from private_gpt.settings.settings_loader import load_active_profiles
@@ -57,7 +59,7 @@ class DataSettings(BaseModel):
 
 
 class LLMSettings(BaseModel):
-    mode: str = Field(enum=["local", "open_ai", "sagemaker", "mock"])
+    mode: Literal["local", "open_ai", "sagemaker", "mock"]
 
 
 class LocalSettings(BaseModel):

pyproject.toml

@@ -12,7 +12,7 @@ injector = "^0.21.0"
 pyyaml = "^6.0.1"
 python-multipart = "^0.0.6"
 pypdf = "^3.16.2"
-llama-index = "0.8.47"
+llama-index = "0.8.67"
 chromadb = "^0.4.13"
 watchdog = "^3.0.0"
 
@@ -138,4 +138,4 @@ asyncio_mode = "auto"
 testpaths = ["tests"]
 addopts = [
     "--import-mode=importlib",
-]
+]

settings.yaml

@@ -15,7 +15,7 @@ ui:
   path: /
 
 llm:
-  mode: mock
+  mode: local
 
 local:
   llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.1-GGUF