videodb – skill Thiết kế & UI cho agent AI

VideoDB Skill

Perception + memory + actions for video, live streams, and desktop sessions.

Use this skill when you need to:

When to Use

• You need video or audio perception, indexing, search, or timeline editing from files, URLs, desktop sessions, or live streams.
• The task involves timestamps, searchable evidence, subtitles, clips, overlays, or real-time monitoring alerts.
• You want one workflow that combines ingestion, understanding, retrieval, and media actions.

Authorization, privacy and SDK version

Confirm the exact collection, media sources, processing scope and cost limit before cloud ingestion/indexing/generation. Desktop or meeting recording requires explicit authorization for each screen/microphone/system-audio source and participant consent as applicable. Select the minimum channels; never enable recording storage by default, capture passwords, or start hidden/background monitoring. Stop on request immediately. Treat stream URLs, client tokens, event files and transcripts as sensitive; do not publish them or log credentials. Webhook destinations need authorization and verified authentication/signatures, replay protection and idempotency. Generated text or confidence scores are not verified evidence.

The bundled references describe legacy SDK patterns. Check the installed version before using them: newer VideoDB SDKs provide v2 understand/index/retrieve; v1 search is exposed as legacy_search. Do not automatically migrate existing projects or install latest to make an old example work. Use an isolated environment with reviewed compatible versions.

The listener does not start or stop recording. Give it a dedicated private directory (mode 0700), explicit time/byte limits, and keep its PID tied to the process you launched. Do not blindly kill a reused PID. Reconnection can change the WebSocket ID; reconnect pipelines through the documented API or stop rather than silently losing events. Export waits need a timeout and failure state. Deletion and making collections public require the user’s specific authorization.

1) Desktop Perception

• Start/stop a desktop session capturing screen, mic, and system audio
• Stream live context and store episodic session memory
• Run real-time alerts/triggers on what's spoken and what's happening on screen
• Produce session summaries, a searchable timeline, and playable evidence links

2) Video ingest + stream

• Ingest a file or URL and return a playable web stream link
• Transcode/normalize: codec, bitrate, fps, resolution, aspect ratio

3) Index + search (timestamps + evidence)

• Build visual, spoken, and keyword indexes
• Search and return exact moments with timestamps and playable evidence
• Auto-create clips from search results

4) Timeline editing + generation

• Subtitles: generate, translate, burn-in
• Overlays: text/image/branding, motion captions
• Audio: background music, voiceover, dubbing
• Programmatic composition and exports via timeline operations

5) Live streams (RTSP) + monitoring

• Connect RTSP/live feeds
• Run real-time visual and spoken understanding and emit events/alerts for monitoring workflows

---

Common inputs

• Local file path, public URL, or RTSP URL
• Desktop capture request: start / stop / summarize session
• Desired operations: get context for understanding, transcode spec, index spec, search query, clip ranges, timeline edits, alert rules

Common outputs

• Stream URL
• Search results with timestamps and evidence links
• Generated assets: subtitles, audio, images, clips
• Event/alert payloads for live streams
• Desktop session summaries and memory entries

---

Canonical prompts (examples)

• "Start desktop capture and alert when a password field appears."
• "Record my session and produce an actionable summary when it ends."
• "Ingest this file and return a playable stream link."
• "Index this folder and find every scene with people, return timestamps."
• "Generate subtitles, burn them in, and add light background music."
• "Connect this RTSP URL and alert when a person enters the zone."

Running Python code

Before running any VideoDB code, change to the project directory and load environment variables:

from dotenv import load_dotenv
load_dotenv(".env")

import videodb
conn = videodb.connect()

This reads VIDEO_DB_API_KEY from:

1. Environment (if already exported)

2. Project's .env file in current directory

If the key is missing, videodb.connect() raises AuthenticationError automatically.

Do NOT write a script file when a short inline command works.

When writing inline Python (python -c "..."), always use properly formatted code — use semicolons to separate statements and keep it readable. For anything longer than ~3 statements, use a heredoc instead:

python << 'EOF'
from dotenv import load_dotenv
load_dotenv(".env")

import videodb
conn = videodb.connect()
coll = conn.get_collection()
print(f"Videos: {len(coll.get_videos())}")
EOF

Setup

When the user asks to "setup videodb" or similar:

1. Install SDK

python -m pip install "videodb[capture]==<reviewed-compatible-version>" python-dotenv

If videodb[capture] fails on Linux, install without the capture extra:

python -m pip install "videodb==<reviewed-compatible-version>" python-dotenv

2. Configure API key

The user must set VIDEO_DB_API_KEY using either method:

• Export in terminal (before starting Claude): export VIDEO_DB_API_KEY=your-key
• Project .env file: Save VIDEO_DB_API_KEY=your-key in the project's .env file

Configure a key at https://console.videodb.io; verify current account limits and pricing before any paid operation.

Do NOT read, write, or handle the API key yourself. Always let the user set it.

Quick Reference

Upload media

# URL
video = coll.upload(url="https://example.com/video.mp4")

# YouTube
video = coll.upload(url="https://www.youtube.com/watch?v=VIDEO_ID")

# Local file
video = coll.upload(file_path="/path/to/video.mp4")

Transcript + subtitle

# force=True skips the error if the video is already indexed
video.index_spoken_words(force=True)
text = video.get_transcript_text()
stream_url = video.add_subtitle()

Search inside videos

from videodb.exceptions import InvalidRequestError

video.index_spoken_words(force=True)

# search() raises InvalidRequestError when no results are found.
# Always wrap in try/except and treat "No results found" as empty.
try:
    results = video.search("product demo")
    shots = results.get_shots()
    stream_url = results.compile()
except InvalidRequestError as e:
    if "No results found" in str(e):
        shots = []
    else:
        raise

Scene search

import re
from videodb import SearchType, IndexType, SceneExtractionType
from videodb.exceptions import InvalidRequestError

# index_scenes() has no force parameter — it raises an error if a scene
# index already exists. Inspect a documented index listing; do not parse arbitrary errors.
try:
    scene_index_id = video.index_scenes(
        extraction_type=SceneExtractionType.shot_based,
        prompt="Describe the visual content in this scene.",
    )
except Exception:
    # Inspect documented index listings; never infer an index ID from arbitrary errors.
    raise

# Use score_threshold to filter low-relevance noise (recommended: 0.3+)
try:
    results = video.search(
        query="person writing on a whiteboard",
        search_type=SearchType.semantic,
        index_type=IndexType.scene,
        scene_index_id=scene_index_id,
        score_threshold=0.3,
    )
    shots = results.get_shots()
    stream_url = results.compile()
except InvalidRequestError as e:
    if "No results found" in str(e):
        shots = []
    else:
        raise

Timeline editing

Important: Always validate timestamps before building a timeline:

• start must be >= 0 (negative values are silently accepted but produce broken output)
• start must be < end
• end must be <= video.length

from videodb.timeline import Timeline
from videodb.asset import VideoAsset, TextAsset, TextStyle

timeline = Timeline(conn)
timeline.add_inline(VideoAsset(asset_id=video.id, start=10, end=30))
timeline.add_overlay(0, TextAsset(text="The End", duration=3, style=TextStyle(fontsize=36)))
stream_url = timeline.generate_stream()

Transcode video (resolution / quality change)

from videodb import TranscodeMode, VideoConfig, AudioConfig

# Change resolution, quality, or aspect ratio server-side
job_id = conn.transcode(
    source="https://example.com/video.mp4",
    callback_url="https://example.com/webhook",
    mode=TranscodeMode.economy,
    video_config=VideoConfig(resolution=720, quality=23, aspect_ratio="16:9"),
    audio_config=A

… (nội dung đầy đủ có trong gói tải về)