knight/TLC-Search
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Disable vector search

Browse Source
This commit is contained in:
knight 2026-01-08 15:20:06 -05:00
parent 8e4c57a93a
commit 6a3d1ee491
6 changed files with 20 additions and 684 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
requirements.txt
View File

@ -4,4 +4,3 @@ youtube-transcript-api>=0.6
google-api-python-client>=2.0.0
python-dotenv>=0.19.0
requests>=2.31.0
sentence-transformers>=2.7.0

208
search_app.py
View File

@ -4,10 +4,8 @@ Flask application exposing search, graph, and transcript endpoints for TLC.
Routes:
GET / -> static HTML search page.
GET /graph -> static reference graph UI.
GET /vector-search -> experimental Qdrant vector search UI.
GET /api/channels -> channels aggregation.
GET /api/search -> Elasticsearch keyword search.
POST /api/vector-search -> Qdrant vector similarity query.
GET /api/graph -> reference graph API.
GET /api/transcript -> transcript JSON payload.
"""
@ -27,13 +25,6 @@ from datetime import datetime
from flask import Flask, jsonify, request, send_from_directory
import requests
try:
from sentence_transformers import SentenceTransformer # type: ignore
except ImportError: # pragma: no cover - optional dependency
SentenceTransformer = None
from .config import CONFIG, AppConfig
try:
@ -44,14 +35,11 @@ except ImportError: # pragma: no cover - dependency optional
BadRequestError = Exception # type: ignore
LOGGER = logging.getLogger(__name__)
_EMBED_MODEL = None
_EMBED_MODEL_NAME: Optional[str] = None
# Security constants
MAX_QUERY_SIZE = 100
MAX_OFFSET = 10000
ALLOWED_QDRANT_FILTER_FIELDS = {"channel_id", "date", "video_status", "external_reference"}
DEFAULT_ELASTIC_TIMEOUT = int(os.environ.get("ELASTIC_TIMEOUT_SECONDS", "30"))
def sanitize_query_string(query: str) -> str:
"""
@ -74,47 +62,6 @@ def sanitize_query_string(query: str) -> str:
return sanitized.strip() or "*"
def validate_qdrant_filter(filters: Any) -> Dict[str, Any]:
"""
Validate and sanitize Qdrant filter objects.
Only allows whitelisted fields to prevent filter injection.
"""
if not isinstance(filters, dict):
return {}
validated: Dict[str, Any] = {}
for key, value in filters.items():
if key in ALLOWED_QDRANT_FILTER_FIELDS:
validated[key] = value
return validated
def _ensure_embedder(model_name: str) -> "SentenceTransformer":
global _EMBED_MODEL, _EMBED_MODEL_NAME
if SentenceTransformer is None: # pragma: no cover - optional dependency
raise RuntimeError(
"sentence-transformers is required for vector search. Install via pip install sentence-transformers."
)
if _EMBED_MODEL is None or _EMBED_MODEL_NAME != model_name:
LOGGER.info("Loading embedding model: %s", model_name)
_EMBED_MODEL = SentenceTransformer(model_name)
_EMBED_MODEL_NAME = model_name
return _EMBED_MODEL
def embed_query(text: str, *, model_name: str, expected_dim: int) -> List[float]:
embedder = _ensure_embedder(model_name)
vector = embedder.encode(
[f"query: {text}"],
show_progress_bar=False,
normalize_embeddings=True,
)[0].tolist()
if len(vector) != expected_dim:
raise RuntimeError(
f"Embedding dimension mismatch (expected {expected_dim}, got {len(vector)})"
)
return vector
def _ensure_client(config: AppConfig) -> "Elasticsearch":
if Elasticsearch is None:
raise RuntimeError(
@ -286,7 +233,7 @@ def elastic_metrics_payload(
"Elasticsearch metrics request: %s",
json.dumps({"index": index, "body": body}, indent=2),
)
response = client.search(index=index, body=body)
response = client.search(index=index, body=body, request_timeout=30)
break
except BadRequestError as exc:
last_error = exc
@ -857,7 +804,7 @@ def build_full_graph_payload(
scroll_id: Optional[str] = None
try:
body = {"query": query, "_source": source_fields, "sort": ["_doc"]}
response = client.search(index=index, body=body, size=batch_size, scroll="1m")
response = client.search(index=index, body=body, size=batch_size, scroll="1m", request_timeout=60)
scroll_id = response.get("_scroll_id")
stop_fetch = False
while not stop_fetch:
@ -957,11 +904,6 @@ def create_app(config: AppConfig = CONFIG) -> Flask:
client = _ensure_client(config)
index = config.elastic.index
qdrant_url = config.qdrant_url
qdrant_collection = config.qdrant_collection
qdrant_vector_name = config.qdrant_vector_name
qdrant_vector_size = config.qdrant_vector_size
qdrant_embed_model = config.qdrant_embed_model
@app.route("/")
def index_page():
@ -971,10 +913,6 @@ def create_app(config: AppConfig = CONFIG) -> Flask:
def graph_page():
return send_from_directory(app.static_folder, "graph.html")
@app.route("/vector-search")
def vector_search_page():
return send_from_directory(app.static_folder, "vector.html")
@app.route("/static/<path:filename>")
def static_files(filename: str):
return send_from_directory(app.static_folder, filename)
@ -1260,6 +1198,7 @@ def create_app(config: AppConfig = CONFIG) -> Flask:
from_=start,
size=size,
body=payload,
request_timeout=30,
)
if config.elastic.debug:
LOGGER.info(
@ -1550,145 +1489,6 @@ def create_app(config: AppConfig = CONFIG) -> Flask:
def frequency_page():
return send_from_directory(app.static_folder, "frequency.html")
@app.route("/api/vector-search", methods=["POST"])
def api_vector_search():
payload = request.get_json(silent=True) or {}
query_text = (payload.get("query") or "").strip()
filters = validate_qdrant_filter(payload.get("filters"))
limit = min(max(int(payload.get("size", 10)), 1), MAX_QUERY_SIZE)
offset = min(max(int(payload.get("offset", 0)), 0), MAX_OFFSET)
if not query_text:
return jsonify(
{"items": [], "totalResults": 0, "offset": offset, "error": "empty_query"}
)
try:
query_vector = embed_query(
query_text, model_name=qdrant_embed_model, expected_dim=qdrant_vector_size
)
except Exception as exc: # pragma: no cover - runtime dependency
LOGGER.error("Embedding failed: %s", exc, exc_info=config.elastic.debug)
return jsonify({"error": "embedding_unavailable"}), 500
qdrant_vector_payload: Any
if qdrant_vector_name:
qdrant_vector_payload = {qdrant_vector_name: query_vector}
else:
qdrant_vector_payload = query_vector
qdrant_body: Dict[str, Any] = {
"vector": qdrant_vector_payload,
"limit": limit,
"offset": offset,
"with_payload": True,
"with_vectors": False,
}
if filters:
qdrant_body["filter"] = filters
try:
response = requests.post(
f"{qdrant_url}/collections/{qdrant_collection}/points/search",
json=qdrant_body,
timeout=20,
)
response.raise_for_status()
data = response.json()
except Exception as exc:
LOGGER.error("Vector search failed: %s", exc, exc_info=config.elastic.debug)
return jsonify({"error": "vector_search_unavailable"}), 502
points = data.get("result", []) if isinstance(data, dict) else []
items: List[Dict[str, Any]] = []
missing_channel_ids: Set[str] = set()
for point in points:
payload = point.get("payload", {}) or {}
raw_highlights = payload.get("highlights") or []
highlight_entries: List[Dict[str, str]] = []
for entry in raw_highlights:
if isinstance(entry, dict):
html_value = entry.get("html") or entry.get("text")
else:
html_value = str(entry)
if not html_value:
continue
highlight_entries.append({"html": html_value, "source": "primary"})
channel_label = (
payload.get("channel_name")
or payload.get("channel_title")
or payload.get("channel_id")
)
items.append(
{
"video_id": payload.get("video_id"),
"channel_id": payload.get("channel_id"),
"channel_name": channel_label,
"title": payload.get("title"),
"titleHtml": payload.get("title"),
"description": payload.get("description"),
"descriptionHtml": payload.get("description"),
"date": payload.get("date"),
"url": payload.get("url"),
"chunkText": payload.get("text")
or payload.get("chunk_text")
or payload.get("chunk")
or payload.get("content"),
"chunkTimestamp": payload.get("timestamp")
or payload.get("start_seconds")
or payload.get("start"),
"toHighlight": highlight_entries,
"highlightSource": {
"primary": bool(highlight_entries),
"secondary": False,
},
"distance": point.get("score"),
"internal_references_count": payload.get("internal_references_count", 0),
"internal_references": payload.get("internal_references", []),
"referenced_by_count": payload.get("referenced_by_count", 0),
"referenced_by": payload.get("referenced_by", []),
"video_status": payload.get("video_status"),
"duration": payload.get("duration"),
}
)
if (not channel_label) and payload.get("channel_id"):
missing_channel_ids.add(str(payload.get("channel_id")))
if missing_channel_ids:
try:
es_lookup = client.search(
index=index,
body={
"size": len(missing_channel_ids) * 2,
"_source": ["channel_id", "channel_name"],
"query": {"terms": {"channel_id.keyword": list(missing_channel_ids)}},
},
)
hits = es_lookup.get("hits", {}).get("hits", [])
channel_lookup = {}
for hit in hits:
src = hit.get("_source", {}) or {}
cid = src.get("channel_id")
cname = src.get("channel_name")
if cid and cname and cid not in channel_lookup:
channel_lookup[cid] = cname
for item in items:
if not item.get("channel_name"):
cid = item.get("channel_id")
if cid and cid in channel_lookup:
item["channel_name"] = channel_lookup[cid]
except Exception as exc:
LOGGER.debug("Vector channel lookup failed: %s", exc)
return jsonify(
{
"items": items,
"totalResults": len(items),
"offset": offset,
}
)
@app.route("/api/transcript")
def transcript():
video_id = request.args.get("video_id", type=str)

14
static/app.js
View File

@ -1340,10 +1340,12 @@ async function updateFrequencyChart(term, channels, year, queryMode, toggles = {
}
const el = document.createElement("div");
el.className = "item";
const rawTitle = item.title || "Untitled";
const rawDescription = item.description || "";
const titleHtml =
item.titleHtml || escapeHtml(item.title || "Untitled");
item.titleHtml || escapeHtml(rawTitle);
const descriptionHtml =
item.descriptionHtml || escapeHtml(item.description || "");
item.descriptionHtml || escapeHtml(rawDescription);
const header = document.createElement("div");
header.className = "result-header";
@ -1395,7 +1397,11 @@ async function updateFrequencyChart(term, channels, year, queryMode, toggles = {
}
const titleEl = document.createElement("strong");
if (item.titleHtml) {
titleEl.innerHTML = titleHtml;
} else {
titleEl.textContent = rawTitle;
}
headerMain.appendChild(titleEl);
const metaLine = document.createElement("div");
@ -1519,7 +1525,11 @@ async function updateFrequencyChart(term, channels, year, queryMode, toggles = {
if (descriptionHtml) {
const desc = document.createElement("div");
desc.className = "muted description-block";
if (item.descriptionHtml) {
desc.innerHTML = descriptionHtml;
} else {
desc.textContent = rawDescription;
}
el.appendChild(desc);
}

8
static/index.html
View File

@ -5,9 +5,9 @@
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>TLC Search</title>
<link rel="icon" href="/static/favicon.png" type="image/png" />
<link rel="stylesheet" href="https://unpkg.com/xp.css" />
<link rel="stylesheet" href="https://unpkg.com/xp.css" integrity="sha384-isKk8ZXKlU28/m3uIrnyTfuPaamQIF4ONLeGSfsWGEe3qBvaeLU5wkS4J7cTIwxI" crossorigin="anonymous" />
<link rel="stylesheet" href="/static/style.css" />
<script src="https://cdn.jsdelivr.net/npm/d3@7/dist/d3.min.js"></script>
<script src="https://cdn.jsdelivr.net/npm/d3@7/dist/d3.min.js" integrity="sha384-CjloA8y00+1SDAUkjs099PVfnY2KmDC2BZnws9kh8D/lX1s46w6EPhpXdqMfjK6i" crossorigin="anonymous"></script>
</head>
<body>
<div class="window" style="max-width: 1200px; margin: 20px auto;">
@ -22,10 +22,6 @@
</div>
<div class="window-body">
<p>Enter a phrase to query title, description, and transcript text.</p>
<p style="font-size: 11px;">
Looking for semantic matches? Try the
<a href="/vector-search">vector search beta</a>.
</p>
<fieldset>
<legend>Search</legend>

46
static/vector.html
View File

@ -1,46 +0,0 @@
<!doctype html>
<html>
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>TLC Vector Search</title>
<link rel="icon" href="/static/favicon.png" type="image/png" />
<link rel="stylesheet" href="https://unpkg.com/xp.css" />
<link rel="stylesheet" href="/static/style.css" />
</head>
<body>
<div class="window" style="max-width: 1200px; margin: 20px auto;">
<div class="title-bar">
<div class="title-bar-text">Vector Search (Experimental)</div>
<div class="title-bar-controls">
<a class="title-bar-link" href="/">⬅ Back to Search</a>
</div>
</div>
<div class="window-body">
<p>Enter a natural language prompt; results come from the Qdrant vector index.</p>
<fieldset>
<legend>Vector Query</legend>
<div class="field-row" style="margin-bottom: 8px;">
<label for="vectorQuery" style="width: 60px;">Query:</label>
<input id="vectorQuery" type="text" placeholder="Describe what you are looking for" style="flex: 1;" />
<button id="vectorSearchBtn">Search</button>
</div>
</fieldset>
<div id="vectorMeta" style="margin-top: 12px; font-size: 11px;"></div>
<fieldset style="margin-top: 16px;">
<legend>Results</legend>
<div id="vectorResults"></div>
</fieldset>
</div>
<div class="status-bar">
<p class="status-bar-field">Experimental mode • Qdrant</p>
</div>
</div>
<script src="/static/vector.js"></script>
</body>
</html>

423
static/vector.js
View File

@ -1,423 +0,0 @@
(() => {
const queryInput = document.getElementById("vectorQuery");
const searchBtn = document.getElementById("vectorSearchBtn");
const resultsDiv = document.getElementById("vectorResults");
const metaDiv = document.getElementById("vectorMeta");
const transcriptCache = new Map();
if (!queryInput || !searchBtn || !resultsDiv || !metaDiv) {
console.error("Vector search elements missing");
return;
}
/** Utility helpers **/
const escapeHtml = (str) =>
(str || "").replace(/[&<>"']/g, (ch) => {
switch (ch) {
case "&":
return "&amp;";
case "<":
return "&lt;";
case ">":
return "&gt;";
case '"':
return "&quot;";
case "'":
return "&#39;";
default:
return ch;
}
});
const fmtDate = (value) => {
try {
return (value || "").split("T")[0];
} catch {
return value;
}
};
const fmtSimilarity = (score) => {
if (typeof score !== "number" || Number.isNaN(score)) return "";
return score.toFixed(3);
};
const getVideoStatus = (item) =>
(item && item.video_status ? String(item.video_status).toLowerCase() : "");
const isLikelyDeleted = (item) => getVideoStatus(item) === "deleted";
const formatTimestamp = (seconds) => {
if (!seconds && seconds !== 0) return "00:00";
const hours = Math.floor(seconds / 3600);
const mins = Math.floor((seconds % 3600) / 60);
const secs = Math.floor(seconds % 60);
if (hours > 0) {
return `${hours}:${mins.toString().padStart(2, "0")}:${secs
.toString()
.padStart(2, "0")}`;
}
return `${mins}:${secs.toString().padStart(2, "0")}`;
};
const formatSegmentTimestamp = (segment) => {
if (!segment) return "";
if (segment.timestamp) return segment.timestamp;
const fields = [
segment.start_seconds,
segment.start,
segment.offset,
segment.time,
];
for (const value of fields) {
if (value == null) continue;
const num = parseFloat(value);
if (!Number.isNaN(num)) {
return formatTimestamp(num);
}
}
return "";
};
const serializeTranscriptSection = (label, parts, fullText) => {
let content = "";
if (typeof fullText === "string" && fullText.trim()) {
content = fullText.trim();
} else if (Array.isArray(parts) && parts.length) {
content = parts
.map((segment) => {
const ts = formatSegmentTimestamp(segment);
const text = segment && segment.text ? segment.text : "";
return ts ? `[${ts}] ${text}` : text;
})
.join("\n")
.trim();
}
if (!content) return "";
return `${label}\n${content}\n`;
};
const fetchTranscriptData = async (videoId) => {
if (!videoId) return null;
if (transcriptCache.has(videoId)) {
return transcriptCache.get(videoId);
}
const res = await fetch(`/api/transcript?video_id=${encodeURIComponent(videoId)}`);
if (!res.ok) {
throw new Error(`Transcript fetch failed (${res.status})`);
}
const data = await res.json();
transcriptCache.set(videoId, data);
return data;
};
const buildTranscriptDownloadText = (item, transcriptData) => {
const lines = [];
lines.push(`Title: ${item.title || "Untitled"}`);
if (item.channel_name) lines.push(`Channel: ${item.channel_name}`);
if (item.date) lines.push(`Published: ${item.date}`);
if (item.url) lines.push(`URL: ${item.url}`);
lines.push("");
const primaryText = serializeTranscriptSection(
"Primary Transcript",
transcriptData.transcript_parts,
transcriptData.transcript_full
);
const secondaryText = serializeTranscriptSection(
"Secondary Transcript",
transcriptData.transcript_secondary_parts,
transcriptData.transcript_secondary_full
);
if (primaryText) lines.push(primaryText);
if (secondaryText) lines.push(secondaryText);
if (!primaryText && !secondaryText) {
lines.push("No transcript available.");
}
return lines.join("\n").trim() + "\n";
};
const flashButtonMessage = (button, message, duration = 1800) => {
if (!button) return;
const original = button.dataset.originalLabel || button.textContent;
button.dataset.originalLabel = original;
button.textContent = message;
setTimeout(() => {
button.textContent = button.dataset.originalLabel || original;
}, duration);
};
const handleTranscriptDownload = async (item, button) => {
if (!item.video_id) return;
button.disabled = true;
try {
const transcriptData = await fetchTranscriptData(item.video_id);
if (!transcriptData) throw new Error("Transcript unavailable");
const text = buildTranscriptDownloadText(item, transcriptData);
const blob = new Blob([text], { type: "text/plain" });
const url = URL.createObjectURL(blob);
const link = document.createElement("a");
link.href = url;
link.download = `${item.video_id}.txt`;
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
URL.revokeObjectURL(url);
flashButtonMessage(button, "Downloaded");
} catch (err) {
console.error("Download failed", err);
alert("Unable to download transcript right now.");
} finally {
button.disabled = false;
}
};
const formatMlaDate = (value) => {
if (!value) return "n.d.";
const parsed = new Date(value);
if (Number.isNaN(parsed.valueOf())) return value;
const months = [
"Jan.", "Feb.", "Mar.", "Apr.", "May", "June",
"July", "Aug.", "Sept.", "Oct.", "Nov.", "Dec.",
];
return `${parsed.getDate()} ${months[parsed.getMonth()]} ${parsed.getFullYear()}`;
};
const buildMlaCitation = (item) => {
const channel = (item.channel_name || item.channel_id || "Unknown").trim();
const title = (item.title || "Untitled").trim();
const url = item.url || "";
const publishDate = formatMlaDate(item.date);
const today = formatMlaDate(new Date().toISOString().split("T")[0]);
return `${channel}. "${title}." YouTube, uploaded by ${channel}, ${publishDate}, ${url}. Accessed ${today}.`;
};
const handleCopyCitation = async (item, button) => {
const citation = buildMlaCitation(item);
try {
if (navigator.clipboard && window.isSecureContext) {
await navigator.clipboard.writeText(citation);
} else {
const textarea = document.createElement("textarea");
textarea.value = citation;
textarea.style.position = "fixed";
textarea.style.opacity = "0";
document.body.appendChild(textarea);
textarea.select();
document.execCommand("copy");
document.body.removeChild(textarea);
}
flashButtonMessage(button, "Copied!");
} catch (err) {
console.error("Citation copy failed", err);
alert(citation);
}
};
/** Rendering helpers **/
const createHighlightRows = (entries) => {
if (!Array.isArray(entries) || !entries.length) return null;
const container = document.createElement("div");
container.className = "transcript highlight-list";
entries.forEach((entry) => {
if (!entry) return;
const row = document.createElement("div");
row.className = "highlight-row";
const textBlock = document.createElement("div");
textBlock.className = "highlight-text";
const html = entry.html || entry.text || entry;
textBlock.innerHTML = html || "";
row.appendChild(textBlock);
const indicator = document.createElement("span");
indicator.className = "highlight-source-indicator highlight-source-indicator--primary";
indicator.title = "Vector highlight";
row.appendChild(indicator);
container.appendChild(row);
});
return container;
};
const createActions = (item) => {
const actions = document.createElement("div");
actions.className = "result-actions";
const downloadBtn = document.createElement("button");
downloadBtn.type = "button";
downloadBtn.className = "result-action-btn";
downloadBtn.textContent = "Download transcript";
downloadBtn.addEventListener("click", () => handleTranscriptDownload(item, downloadBtn));
actions.appendChild(downloadBtn);
const citationBtn = document.createElement("button");
citationBtn.type = "button";
citationBtn.className = "result-action-btn";
citationBtn.textContent = "Copy citation";
citationBtn.addEventListener("click", () => handleCopyCitation(item, citationBtn));
actions.appendChild(citationBtn);
const graphBtn = document.createElement("button");
graphBtn.type = "button";
graphBtn.className = "result-action-btn graph-launch-btn";
graphBtn.textContent = "Graph";
graphBtn.disabled = !item.video_id;
graphBtn.addEventListener("click", () => {
if (!item.video_id) return;
const target = `/graph?video_id=${encodeURIComponent(item.video_id)}`;
window.open(target, "_blank", "noopener");
});
actions.appendChild(graphBtn);
return actions;
};
const renderVectorResults = (payload) => {
resultsDiv.innerHTML = "";
const items = payload.items || [];
if (!items.length) {
metaDiv.textContent = "No vector matches for this prompt.";
return;
}
metaDiv.textContent = `Matches: ${items.length} (vector mode)`;
items.forEach((item) => {
const el = document.createElement("div");
el.className = "item";
const header = document.createElement("div");
header.className = "result-header";
const headerMain = document.createElement("div");
headerMain.className = "result-header-main";
const titleEl = document.createElement("strong");
titleEl.innerHTML = item.titleHtml || escapeHtml(item.title || "Untitled");
headerMain.appendChild(titleEl);
const metaLine = document.createElement("div");
metaLine.className = "muted result-meta";
const channelLabel = item.channel_name || item.channel_id || "Unknown";
const dateLabel = fmtDate(item.date);
let durationSeconds = null;
if (typeof item.duration === "number") {
durationSeconds = item.duration;
} else if (typeof item.duration === "string" && item.duration.trim()) {
const parsed = parseFloat(item.duration);
if (!Number.isNaN(parsed)) {
durationSeconds = parsed;
}
}
const durationLabel = durationSeconds != null ? ` • ${formatTimestamp(durationSeconds)}` : "";
metaLine.textContent = channelLabel ? `${channelLabel} • ${dateLabel}${durationLabel}` : `${dateLabel}${durationLabel}`;
if (isLikelyDeleted(item)) {
metaLine.appendChild(document.createTextNode(" "));
const statusEl = document.createElement("span");
statusEl.className = "result-status result-status--deleted";
statusEl.textContent = "Likely deleted";
metaLine.appendChild(statusEl);
}
headerMain.appendChild(metaLine);
if (item.url) {
const linkLine = document.createElement("div");
linkLine.className = "muted";
const anchor = document.createElement("a");
anchor.href = item.url;
anchor.target = "_blank";
anchor.rel = "noopener";
anchor.textContent = "Open on YouTube";
linkLine.appendChild(anchor);
headerMain.appendChild(linkLine);
}
if (typeof item.distance === "number") {
const scoreLine = document.createElement("div");
scoreLine.className = "muted";
scoreLine.textContent = `Similarity score: ${fmtSimilarity(item.distance)}`;
headerMain.appendChild(scoreLine);
}
header.appendChild(headerMain);
header.appendChild(createActions(item));
el.appendChild(header);
if (item.descriptionHtml || item.description) {
const desc = document.createElement("div");
desc.className = "muted description-block";
desc.innerHTML = item.descriptionHtml || escapeHtml(item.description);
el.appendChild(desc);
}
if (item.chunkText) {
const chunkBlock = document.createElement("div");
chunkBlock.className = "vector-chunk";
if (item.chunkTimestamp && item.url) {
const tsObj =
typeof item.chunkTimestamp === "object"
? item.chunkTimestamp
: { timestamp: item.chunkTimestamp };
const ts = formatSegmentTimestamp(tsObj);
const tsLink = document.createElement("a");
const paramValue =
typeof item.chunkTimestamp === "number"
? Math.floor(item.chunkTimestamp)
: item.chunkTimestamp;
tsLink.href = `${item.url}${item.url.includes("?") ? "&" : "?"}t=${encodeURIComponent(
paramValue
)}`;
tsLink.target = "_blank";
tsLink.rel = "noopener";
tsLink.textContent = ts ? `[${ts}]` : "[timestamp]";
chunkBlock.appendChild(tsLink);
chunkBlock.appendChild(document.createTextNode(" "));
}
const chunkTextSpan = document.createElement("span");
chunkTextSpan.textContent = item.chunkText;
chunkBlock.appendChild(chunkTextSpan);
el.appendChild(chunkBlock);
}
const highlights = createHighlightRows(item.toHighlight);
if (highlights) {
el.appendChild(highlights);
}
resultsDiv.appendChild(el);
});
};
/** Search handler **/
const runVectorSearch = async () => {
const query = queryInput.value.trim();
if (!query) {
alert("Please enter a query.");
return;
}
metaDiv.textContent = "Searching vector index…";
resultsDiv.innerHTML = "";
searchBtn.disabled = true;
try {
const res = await fetch("/api/vector-search", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ query }),
});
if (!res.ok) {
throw new Error(`Vector search failed (${res.status})`);
}
const data = await res.json();
if (data.error) {
metaDiv.textContent = "Vector search unavailable.";
return;
}
renderVectorResults(data);
} catch (err) {
console.error(err);
metaDiv.textContent = "Vector search unavailable.";
} finally {
searchBtn.disabled = false;
}
};
searchBtn.addEventListener("click", runVectorSearch);
queryInput.addEventListener("keypress", (event) => {
if (event.key === "Enter") {
runVectorSearch();
}
});
})();