SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 10:45:42 +01:00
Code Issues Projects Releases Packages Activity

Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity

Browse source
This commit is contained in:
imartinez 2024-02-29 16:40:11 +01:00
parent 85276893a3
commit c3fe36e070
21 changed files with 186 additions and 106 deletions
Download patch file Download diff file Expand all files Collapse all files

18
private_gpt/settings/settings.py
View file

@ -81,7 +81,7 @@ class DataSettings(BaseModel):
class LLMSettings(BaseModel):
mode: Literal["local", "openai", "openailike", "sagemaker", "mock", "ollama"]
mode: Literal["llamacpp", "openai", "openailike", "sagemaker", "mock", "ollama"]
max_new_tokens: int = Field(
256,
description="The maximum number of token that the LLM is authorized to generate in one completion.",
@ -104,12 +104,9 @@ class VectorstoreSettings(BaseModel):
database: Literal["chroma", "qdrant", "pgvector"]
class LocalSettings(BaseModel):
class LlamaCPPSettings(BaseModel):
llm_hf_repo_id: str
llm_hf_model_file: str
embedding_hf_model_name: str = Field(
description="Name of the HuggingFace model to use for embeddings"
)
prompt_style: Literal["default", "llama2", "tag", "mistral", "chatml"] = Field(
"llama2",
description=(
@ -123,8 +120,14 @@ class LocalSettings(BaseModel):
)
class HuggingFaceSettings(BaseModel):
embedding_hf_model_name: str = Field(
description="Name of the HuggingFace model to use for embeddings"
)
class EmbeddingSettings(BaseModel):
mode: Literal["local", "openai", "sagemaker", "mock"]
mode: Literal["huggingface", "openai", "sagemaker", "mock"]
ingest_mode: Literal["simple", "batch", "parallel"] = Field(
"simple",
description=(
@ -292,7 +295,8 @@ class Settings(BaseModel):
ui: UISettings
llm: LLMSettings
embedding: EmbeddingSettings
local: LocalSettings
llamacpp: LlamaCPPSettings
huggingface: HuggingFaceSettings
sagemaker: SagemakerSettings
openai: OpenAISettings
ollama: OllamaSettings