saksham
1a4c80958f
FastAPI + Celery + Next.js + Postgres/Redis app with company monitoring, source collection, LLM-based change analysis, enrichment, and account security (Turnstile, escalating lockout, email verification).
52 lines
1.9 KiB
Python
52 lines
1.9 KiB
Python
"""Task A: document relevance. Decides whether a collected document is
|
|
actually about the target company and matches the user's stated focus,
|
|
before it's used as evidence for anything else."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from app.analysis.llm.base import LLMProvider
|
|
from app.prompts.base import build_user_prompt
|
|
|
|
SYSTEM_PROMPT = (
|
|
"You are a competitive intelligence analyst. Given a single document and a company "
|
|
"profile, judge only whether the document is genuinely about that company and whether "
|
|
"it relates to the user's stated monitoring focus. Do not summarize the document's "
|
|
"content here - a later task does that. Be conservative: if the document could be about "
|
|
"a different company with a similar name, say so."
|
|
)
|
|
|
|
|
|
class RelevanceAssessment(BaseModel):
|
|
is_relevant: bool = Field(description="Is this document genuinely about the target company?")
|
|
matches_focus: bool = Field(description="Does it relate to the user's stated monitoring focus?")
|
|
topic_categories: list[str] = Field(default_factory=list)
|
|
source_reliability: float = Field(ge=0.0, le=1.0)
|
|
reasoning: str
|
|
|
|
|
|
async def assess_relevance(
|
|
llm: LLMProvider,
|
|
*,
|
|
company_name: str,
|
|
company_aliases: list[str],
|
|
monitoring_focus: str | None,
|
|
document_title: str | None,
|
|
document_text: str,
|
|
document_url: str,
|
|
) -> RelevanceAssessment:
|
|
evidence = {
|
|
"company_name": company_name,
|
|
"company_aliases": company_aliases,
|
|
"monitoring_focus": monitoring_focus,
|
|
"document_title": document_title,
|
|
"document_url": document_url,
|
|
"document_text": document_text[:4000],
|
|
}
|
|
user_prompt = build_user_prompt(
|
|
"Assess whether this document is about the target company and matches its monitoring focus.",
|
|
evidence,
|
|
)
|
|
return await llm.generate_structured(SYSTEM_PROMPT, user_prompt, RelevanceAssessment)
|