mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-05 10:13:39 +00:00
arc53-machine
5578039c19
Review follow-up. The per-group secret validators normalised a hand-picked list of API keys, which left other optional credentials and overrides (OPEN_ROUTER_API_KEY, S3 and Daytona keys, ELASTIC_PASSWORD, the OIDC trio, connector client ids, MICROSOFT_AUTHORITY, MCP_OAUTH_REDIRECT_URI) holding the literal "None" or "" a .env file spells "unset" with, so truthiness checks and fallbacks downstream saw a value. One rule on the group base replaces those lists: every Optional[str] field maps "", "None" and whitespace to None and strips real values. Plain str fields are left alone. The OIDC required-settings check therefore also rejects those spellings. EMBEDDINGS_POOLING is Literal["cls", "mean"] with case-insensitive parsing; its consumer silently ignored anything else. Bounds added where the consumer rejects or misbehaves on the value: SCHEDULE_RUN_OUTPUT_RETENTION_DAYS and MESSAGE_EVENTS_RETENTION_DAYS (the cleanup repositories raise on <= 0), EMBEDDINGS_DELEGATE_TIMEOUT, the remote-device idle/pairing/invocation TTLs and CELERY_VISIBILITY_TIMEOUT (> 0), REMOTE_DEVICE_CMD_QUEUE_TTL_SECONDS (> 605, the documented drain deadline), GRAPHRAG_MAX_CHUNKS_FOR_EXTRACTION (>= 0; negative would slice the pending list from the end). The generated reference now renders generic type arguments (dict[str, int] rather than dict).
39 lines
1.5 KiB
Python
39 lines
1.5 KiB
Python
"""Retrieval strategy and GraphRAG."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Literal, Optional
|
|
|
|
from pydantic import Field, field_validator
|
|
|
|
from docsgpt.core.settings._shared import SettingsGroup, normalize_choice
|
|
|
|
|
|
class RetrievalSettings(SettingsGroup):
|
|
"""Which vector store answers searches and how retrieval fans out across sources."""
|
|
|
|
VECTOR_STORE: Literal["faiss", "elasticsearch", "mongodb", "qdrant", "milvus", "pgvector"] = Field(
|
|
default="faiss", description="Vector store backend."
|
|
)
|
|
RETRIEVAL_MAX_PARALLEL_SOURCES: int = Field(
|
|
default=4,
|
|
ge=1,
|
|
description="Concurrent per-source searches in one retrieval; the query is embedded once and shared.",
|
|
)
|
|
PER_SOURCE_RETRIEVAL_ENABLED: bool = Field(
|
|
default=True,
|
|
description="Kill-switch for per-source retrieval dispatch; False collapses to a single retriever.",
|
|
)
|
|
GRAPHRAG_ENABLED: bool = Field(default=False, description="Gates graph-aware ingestion and retrieval.")
|
|
GRAPHRAG_EXTRACTION_MODEL: Optional[str] = Field(
|
|
default=None, description="Model for ingest-time graph extraction; unset reuses LLM_PROVIDER/LLM_NAME."
|
|
)
|
|
GRAPHRAG_MAX_CHUNKS_FOR_EXTRACTION: int = Field(
|
|
default=2000, ge=0, description="Hard cap on chunks extracted per source (cost control); 0 extracts nothing."
|
|
)
|
|
|
|
@field_validator("VECTOR_STORE", mode="before")
|
|
@classmethod
|
|
def _normalize_vector_store(cls, v):
|
|
return normalize_choice(v)
|