NuklearRabbit
b511ba2dbc
KnowledgeProvider protocol with a deterministic TF-IDF-weighted extractive demo provider (never generative, always cites real excerpts) and a RAGcore HTTP adapter that degrades cleanly to unavailable. Knowledge nav + chat-style Q&A UI with source cards and honest grounded/insufficient/unavailable states. 57 backend tests passing, ruff clean. Fixed a real relevance bug (generic terms like "vehicle" crowding out distinctive matches) via IDF weighting, found by testing the actual S6 scenario. Verified end-to-end in the browser: grounded damage question cites both expected procedures; unrelated question honestly returns insufficient evidence with no fabrication.
99 lines
3.7 KiB
Python
99 lines
3.7 KiB
Python
from __future__ import annotations
|
|
|
|
import httpx
|
|
|
|
from app.core.config import get_settings
|
|
from app.services.knowledge import GroundedAnswer, KnowledgeHealth, SourceCard
|
|
|
|
|
|
class RAGcoreKnowledgeProvider:
|
|
"""Adapter for the central RAGcore service.
|
|
|
|
RAGcore is built and owned separately (see contracts/ragcore-contract-assumptions.md).
|
|
No live RAGcore instance was reachable during this build, so the exact request/response
|
|
shape below is a best-effort guess at a REST contract; any failure (connection, timeout,
|
|
malformed response) degrades to `unavailable` rather than raising, per the architecture's
|
|
reliability boundary: RAGcore failure disables knowledge answers only, never the rest of
|
|
the app, and never fabricates an answer.
|
|
"""
|
|
|
|
name = "ragcore"
|
|
|
|
def __init__(self) -> None:
|
|
self._settings = get_settings()
|
|
|
|
def _client(self) -> httpx.Client:
|
|
headers = {}
|
|
if self._settings.ragcore_api_token:
|
|
headers["Authorization"] = f"Bearer {self._settings.ragcore_api_token}"
|
|
return httpx.Client(
|
|
base_url=self._settings.ragcore_base_url,
|
|
headers=headers,
|
|
timeout=self._settings.ragcore_http_timeout_seconds,
|
|
)
|
|
|
|
def health(self) -> KnowledgeHealth:
|
|
try:
|
|
with self._client() as client:
|
|
response = client.get("/health")
|
|
response.raise_for_status()
|
|
available = True
|
|
detail = "RAGcore reachable."
|
|
except httpx.HTTPError as exc:
|
|
available = False
|
|
detail = f"RAGcore unavailable: {type(exc).__name__}: {exc}"
|
|
return KnowledgeHealth(
|
|
provider=self.name,
|
|
available=available,
|
|
detail=detail,
|
|
tenant=self._settings.ragcore_tenant,
|
|
workspace=self._settings.ragcore_workspace,
|
|
collection=self._settings.ragcore_collection,
|
|
document_count=0,
|
|
)
|
|
|
|
def ask(self, question: str, correlation_id: str) -> GroundedAnswer:
|
|
try:
|
|
with self._client() as client:
|
|
response = client.post(
|
|
"/api/v1/ask",
|
|
json={
|
|
"tenant": self._settings.ragcore_tenant,
|
|
"workspace": self._settings.ragcore_workspace,
|
|
"collection": self._settings.ragcore_collection,
|
|
"question": question,
|
|
"correlation_id": correlation_id,
|
|
},
|
|
)
|
|
response.raise_for_status()
|
|
body = response.json()
|
|
except (httpx.HTTPError, ValueError):
|
|
return GroundedAnswer(
|
|
answer="",
|
|
evidence_state="unavailable",
|
|
sources=[],
|
|
provider=self.name,
|
|
correlation_id=correlation_id,
|
|
)
|
|
|
|
try:
|
|
sources = [SourceCard(**s) for s in body.get("sources", [])]
|
|
evidence_state = body.get("evidence_state", "insufficient")
|
|
if evidence_state not in ("grounded", "insufficient", "unavailable"):
|
|
evidence_state = "insufficient"
|
|
return GroundedAnswer(
|
|
answer=body.get("answer", ""),
|
|
evidence_state=evidence_state,
|
|
sources=sources,
|
|
provider=self.name,
|
|
correlation_id=correlation_id,
|
|
)
|
|
except (TypeError, ValueError):
|
|
return GroundedAnswer(
|
|
answer="",
|
|
evidence_state="unavailable",
|
|
sources=[],
|
|
provider=self.name,
|
|
correlation_id=correlation_id,
|
|
)
|