feat(parsing): LaTeX, Nougat, GROBID parsers with chunking

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Tarik Moussa
2026-06-04 23:30:58 +02:00
parent b52a6a7412
commit c6a428d335
8 changed files with 672 additions and 1 deletions

View File

@@ -9,7 +9,7 @@ from __future__ import annotations
from functools import lru_cache
from pydantic import Field
from pydantic import AliasChoices, Field
from pydantic_settings import BaseSettings, SettingsConfigDict
@@ -42,6 +42,12 @@ class Settings(BaseSettings):
description="Base URL of the GROBID HTTP API (containerised).",
)
nougat_url: str = Field(
default="http://localhost:8080",
validation_alias=AliasChoices("NOUGAT_URL", "nougat_url"),
description="Base URL of the Nougat OCR HTTP API (containerised).",
)
ollama_base_url: str = Field(
default="http://localhost:11434",
description="Base URL of the local Ollama endpoint (optional Q&A layer).",