pyr0ball
e52bdb5128
Retrieval:
- Add _fetch_adjacent() to retriever: fetches page ± 1 chunks from DB
after ranking so mid-sentence EPUB chunk boundaries don't lose context
- Fix vec DB doc-filter: oversample to top_k*20 before Python filter
instead of post-filtering an already-small global pool (fixes wrong-book
results when searching within a single document)
- top_k default 5 → 10; context per chunk 500 → 1500 chars; citation
snippet 200 → 400 chars
Artifact cleaning:
- Add scripts/text_clean.py: strips ABC Amber LIT Converter watermarks,
processtext.com URLs, bare page numbers, piracy stamps from extracted text
- Wire clean_paragraph() into ingest_pdf.py and new ingest_epub.py
Startup validation:
- _check_vec_schema() at boot: detects embedding dimension mismatch,
deletes stale vec DB, and queues sequential re-embed in background thread
- Sequential _reembed_docs() prevents SQLite lock races on startup re-embed
cf-orch integration:
- Wire CF_ORCH_URL / CF_LICENSE_KEY into LLMRouter backend config so
allocate() fires and keeps the Ollama model warm between requests
Ingestion progress UI:
- GET /api/library/{doc_id}/status now returns vec_count from page_vecs_meta
- DocumentCard.vue polls status every 3 s while processing and shows
two-phase progress: indeterminate animation during extraction,
determinate "Embedding N/M pages" bar once vectors start landing
Other:
- Chat feedback endpoint + thumbs up/down UI (FeedbackButton.vue)
- EPUB ingest script (ingest_epub.py) with heading-based chunking
- migration 002: chat_feedback table
- README.md with setup and feature overview
88 lines
2.8 KiB
Python
88 lines
2.8 KiB
Python
"""Screenshot attachment endpoint for in-app feedback.
|
|
|
|
After the cf-core feedback router creates a Forgejo issue, the frontend
|
|
can call POST /feedback/attach to upload a screenshot as a comment on that issue.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
import os
|
|
|
|
import requests
|
|
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel, Field
|
|
|
|
router = APIRouter()
|
|
|
|
_FORGEJO_BASE = os.environ.get(
|
|
"FORGEJO_API_URL", "https://git.opensourcesolarpunk.com/api/v1"
|
|
)
|
|
_REPO = "Circuit-Forge/pagepiper"
|
|
_MAX_BYTES = 5 * 1024 * 1024
|
|
|
|
|
|
class AttachRequest(BaseModel):
|
|
issue_number: int
|
|
filename: str = Field(default="screenshot.png", max_length=80)
|
|
image_b64: str # data URI or raw base64
|
|
|
|
|
|
class AttachResponse(BaseModel):
|
|
comment_url: str
|
|
|
|
|
|
def _forgejo_headers() -> dict[str, str]:
|
|
token = os.environ.get("FORGEJO_API_TOKEN", "")
|
|
return {"Authorization": f"token {token}"}
|
|
|
|
|
|
def _decode_image(image_b64: str) -> tuple[bytes, str]:
|
|
if image_b64.startswith("data:"):
|
|
header, _, data = image_b64.partition(",")
|
|
mime = header.split(";")[0].split(":")[1] if ":" in header else "image/png"
|
|
else:
|
|
data = image_b64
|
|
mime = "image/png"
|
|
return base64.b64decode(data), mime
|
|
|
|
|
|
@router.post("/attach", response_model=AttachResponse)
|
|
def attach_screenshot(payload: AttachRequest) -> AttachResponse:
|
|
token = os.environ.get("FORGEJO_API_TOKEN", "")
|
|
if not token:
|
|
raise HTTPException(status_code=503, detail="Feedback not configured.")
|
|
|
|
raw_bytes, mime = _decode_image(payload.image_b64)
|
|
if len(raw_bytes) > _MAX_BYTES:
|
|
raise HTTPException(
|
|
status_code=413,
|
|
detail=f"Screenshot exceeds 5 MB limit ({len(raw_bytes) // 1024} KB received).",
|
|
)
|
|
|
|
asset_resp = requests.post(
|
|
f"{_FORGEJO_BASE}/repos/{_REPO}/issues/{payload.issue_number}/assets",
|
|
headers=_forgejo_headers(),
|
|
files={"attachment": (payload.filename, raw_bytes, mime)},
|
|
timeout=20,
|
|
)
|
|
if not asset_resp.ok:
|
|
raise HTTPException(
|
|
status_code=502,
|
|
detail=f"Forgejo asset upload failed: {asset_resp.text[:200]}",
|
|
)
|
|
|
|
asset_url = asset_resp.json().get("browser_download_url", "")
|
|
comment_body = f"**Screenshot attached by reporter:**\n\n"
|
|
comment_resp = requests.post(
|
|
f"{_FORGEJO_BASE}/repos/{_REPO}/issues/{payload.issue_number}/comments",
|
|
headers={**_forgejo_headers(), "Content-Type": "application/json"},
|
|
json={"body": comment_body},
|
|
timeout=15,
|
|
)
|
|
if not comment_resp.ok:
|
|
raise HTTPException(
|
|
status_code=502,
|
|
detail=f"Forgejo comment failed: {comment_resp.text[:200]}",
|
|
)
|
|
|
|
return AttachResponse(comment_url=comment_resp.json().get("html_url", ""))
|