calesthio/OpenMontage · error · ValueError

rank_for_slot requires 'query_text'

Error message

rank_for_slot requires 'query_text'

What it means

Raised by _op_rank_for_slot in clip_search when inputs['query_text'] is missing, empty, or whitespace-only after .strip(). rank_for_slot is the text-embedding retrieval operation, so a query is mandatory before embed_texts is called.

Source

Thrown at tools/video/clip_search.py:286

        "per_kind": per_kind,
        "mean_motion_score": float(np.mean(motion_scores)) if motion_scores else 0.0,
        "mean_duration": float(np.mean(durations)) if durations else 0.0,
    }


def _op_rank_for_slot(corp, inputs: dict[str, Any]) -> dict[str, Any]:
    """Embed `query_text` and return top-k clips by fused similarity.

    This is the agent's main retrieval move. The returned list is
    ordered best-first and every entry carries a score so the agent
    can decide whether the match is strong enough (>= 0.25 is a rough
    "acceptable" threshold for CLIP ViT-B/32).
    """
    from lib.clip_embedder import embed_texts

    query_text = inputs.get("query_text", "").strip()
    if not query_text:
        raise ValueError("rank_for_slot requires 'query_text'")

    q_vec = embed_texts([query_text])[0]

    results = corp.rank_by_text(
        query_embedding=q_vec,
        k=int(inputs.get("k", 10)),
        tag_weight=float(inputs.get("tag_weight", 0.3)),
        motion_min=inputs.get("motion_min"),
        kind=inputs.get("kind"),
        exclude_ids=inputs.get("exclude_ids") or [],
    )
    return {
        "query_text": query_text,
        "results": [
            {"score": score, "record": asdict(rec)}
            for rec, score in results
        ],
    }

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Supply a non-empty query_text describing the desired footage (subject, motion, setting)
2. Strip/validate the query at your call site before invoking the tool
3. If the query comes from another step, fail fast there with a clear message rather than relying on this error

Example fix

# before
result = clip_search.run(inputs={'operation':'rank_for_slot','k':10})

# after
result = clip_search.run(inputs={'operation':'rank_for_slot','query_text':'slow motion ocean waves at dusk','k':10})

query = (inputs.get('query_text') or '').strip()
if not query:
    raise ValueError('query_text is required for rank_for_slot')
inputs['query_text'] = query

def valid_rank_query(inputs: dict) -> bool:
    return bool(isinstance(inputs.get('query_text'), str) and inputs['query_text'].strip())

try:
    result = clip_search.run(inputs=inputs)
except ValueError as e:
    if "rank_for_slot requires" in str(e):
        raise SystemExit('provide a text query describing the footage') from e
    raise

When it happens

Trigger: Calling the clip_search tool with operation='rank_for_slot' and no query_text; passing query_text='' or ' '; a caller building inputs dynamically where the query variable is None (inputs.get returns '' default only when key absent).

Common situations: An LLM agent omitting the query argument in a tool call; upstream text extraction returning empty (e.g. blank caption or failed transcription feeding the query); form/UI validation gap.

Related errors

• find_similar_set requires 'seed_clip_id'
• diversify requires 'candidate_ids'
• get requires 'clip_id'
• ${res.status} ${url}
• fetch failed ${r.status}: ${url}

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/3a0fb850f4853915. Report an issue: GitHub.