mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 20:12:55 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
65 lines
1.6 KiB
Python
65 lines
1.6 KiB
Python
"""Base schema for data structures."""
|
|
from abc import abstractmethod
|
|
from dataclasses import dataclass
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from dataclasses_json import DataClassJsonMixin
|
|
|
|
|
|
@dataclass
|
|
class BaseDocument(DataClassJsonMixin):
|
|
"""Base document.
|
|
|
|
Generic abstract interfaces that captures both index structs
|
|
as well as documents.
|
|
|
|
"""
|
|
|
|
# TODO: consolidate fields from Document/IndexStruct into base class
|
|
text: Optional[str] = None
|
|
doc_id: Optional[str] = None
|
|
embedding: Optional[List[float]] = None
|
|
|
|
# extra fields
|
|
extra_info: Optional[Dict[str, Any]] = None
|
|
|
|
@classmethod
|
|
@abstractmethod
|
|
def get_type(cls) -> str:
|
|
"""Get Document type."""
|
|
|
|
def get_text(self) -> str:
|
|
"""Get text."""
|
|
if self.text is None:
|
|
raise ValueError("text field not set.")
|
|
return self.text
|
|
|
|
def get_doc_id(self) -> str:
|
|
"""Get doc_id."""
|
|
if self.doc_id is None:
|
|
raise ValueError("doc_id not set.")
|
|
return self.doc_id
|
|
|
|
@property
|
|
def is_doc_id_none(self) -> bool:
|
|
"""Check if doc_id is None."""
|
|
return self.doc_id is None
|
|
|
|
def get_embedding(self) -> List[float]:
|
|
"""Get embedding.
|
|
|
|
Errors if embedding is None.
|
|
|
|
"""
|
|
if self.embedding is None:
|
|
raise ValueError("embedding not set.")
|
|
return self.embedding
|
|
|
|
@property
|
|
def extra_info_str(self) -> Optional[str]:
|
|
"""Extra info string."""
|
|
if self.extra_info is None:
|
|
return None
|
|
|
|
return "\n".join([f"{k}: {str(v)}" for k, v in self.extra_info.items()])
|