Build a research collection
A collection is a named group of videos in the server's library: the G-Wagon buyer videos, one course's lectures, a channel you follow. Once videos are in a collection, one id stands for all of them, in a context pack, a zip, an export or a search. This tutorial builds one from two G-Wagon buyer videos.
The steps chain: run step 1 and its collection id fills in every block below it. Until you run it, each block shows the response recorded when this tutorial was written.
1. Create the collection
POST /collections needs only a name. sources is optional: playlists, channels or feeds the collection follows, so that a refresh adds their new videos. Change the name if you like; the id is the name as a slug plus a random suffix, so two collections never collide.
/api/v1/collectionsCreate a collectionThe id is the name as a slug plus a random suffix. The blocks below use it once you run this one.
curl https://vid2context.com/api/v1/collections \
-H 'Content-Type: application/json' \
-d '{
"name": "G-Wagon research",
"description": "Buyer videos to compare model years"
}'const BASE = 'https://vid2context.com';
const body = {
name: 'G-Wagon research',
description: 'Buyer videos to compare model years',
};
const res = await fetch(`${BASE}/api/v1/collections`, {
headers: { 'Content-Type': 'application/json' },
method: 'POST',
body: JSON.stringify(body),
});
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
console.log(JSON.stringify(await res.json(), null, 2));import json
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
body = {
"name": "G-Wagon research",
"description": "Buyer videos to compare model years",
}
headers = {"Content-Type": "application/json"}
req = urllib.request.Request(f"{BASE}/api/v1/collections", data=json.dumps(body).encode(), headers=headers, method="POST")
try:
with urllib.request.urlopen(req, timeout=300) as res:
print(json.dumps(json.load(res), indent=2))
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}")npx -y vid2context collection create 'G-Wagon research' --description 'Buyer videos to compare model years'{
"name": "create_collection",
"arguments": {
"name": "G-Wagon research",
"description": "Buyer videos to compare model years"
}
}{
"id": "g-wagon-research-2c2983f1",
"name": "G-Wagon research",
"description": "Buyer videos to compare model years",
"sources": [],
"videoIds": [],
"createdAt": "2026-11-15T15:29:16.875Z",
"updatedAt": "2026-11-15T15:29:16.875Z"
}2. Add videos
POST /collections/{id}/items takes a list of inputs. Each video is read once (captions first, then speech-to-text) and saved in the library, so the steps below never contact YouTube again. A playlist in the list adds each of its videos.
With a jobs queue, the server answers 202 and a Job right away, and the block polls GET /jobs/{id} until it finishes. The finished job's result.summary lists the videos that were added and those that failed (with the reason), and counts the ones it skipped.
/api/v1/collections/{id}/itemsAdd videos to the collectionEach video is read once and saved in the library. With a jobs queue this answers 202 and a Job; the runner polls it.
curl https://vid2context.com/api/v1/collections/g-wagon-research-2c2983f1/items \
-H 'Content-Type: application/json' \
-d '{
"inputs": [
"https://www.youtube.com/watch?v=cCPsdFdlshc",
"https://www.youtube.com/watch?v=PzJL3aBRas8"
]
}'const BASE = 'https://vid2context.com';
const body = {
inputs: [
'https://www.youtube.com/watch?v=cCPsdFdlshc',
'https://www.youtube.com/watch?v=PzJL3aBRas8',
],
};
const res = await fetch(`${BASE}/api/v1/collections/g-wagon-research-2c2983f1/items`, {
headers: { 'Content-Type': 'application/json' },
method: 'POST',
body: JSON.stringify(body),
});
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
// With a jobs queue the server answers 202 and a Job; poll it until it finishes.
let job = res.status === 202 ? await res.json() : { status: "succeeded", result: await res.json() };
while (job.status === 'queued' || job.status === 'running') {
await new Promise((r) => setTimeout(r, 2000));
job = await (await fetch(`${BASE}/api/v1/jobs/${job.id}`)).json();
}
console.log(JSON.stringify(job.result ?? job.error, null, 2));import json
import time
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
body = {
"inputs": [
"https://www.youtube.com/watch?v=cCPsdFdlshc",
"https://www.youtube.com/watch?v=PzJL3aBRas8",
],
}
headers = {"Content-Type": "application/json"}
req = urllib.request.Request(f"{BASE}/api/v1/collections/g-wagon-research-2c2983f1/items", data=json.dumps(body).encode(), headers=headers, method="POST")
try:
with urllib.request.urlopen(req, timeout=300) as res:
status = res.status
answer = json.load(res)
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}")
# With a jobs queue the server answers 202 and a Job; poll it until it finishes.
job = answer if status == 202 else {"status": "succeeded", "result": answer}
while job["status"] in ("queued", "running"):
time.sleep(2)
poll = urllib.request.Request(f"{BASE}/api/v1/jobs/{job['id']}")
with urllib.request.urlopen(poll, timeout=60) as res:
job = json.load(res)
print(json.dumps(job.get("result") or job.get("error"), indent=2))npx -y vid2context collection add g-wagon-research-2c2983f1 'https://www.youtube.com/watch?v=cCPsdFdlshc' 'https://www.youtube.com/watch?v=PzJL3aBRas8'{
"name": "add_to_collection",
"arguments": {
"collection": "g-wagon-research-2c2983f1",
"urls": [
"https://www.youtube.com/watch?v=cCPsdFdlshc",
"https://www.youtube.com/watch?v=PzJL3aBRas8"
]
}
}{
"id": "job_cGwJKXxEL5ySzsETnHWCFg",
"kind": "ingest",
"status": "succeeded",
"createdAt": "2026-11-15T15:29:16.882Z",
"updatedAt": "2026-11-15T15:29:16.891Z",
"progress": {
"done": 2,
"total": 2,
"message": "Added Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550)"
},
"result": {
"collection": {
"id": "g-wagon-research-2c2983f1",
"name": "G-Wagon research",
"description": "Buyer videos to compare model years",
"sources": [],
"videoIds": [
"youtube:cCPsdFdlshc",
"youtube:PzJL3aBRas8"
],
"createdAt": "2026-11-15T15:29:16.875Z",
"updatedAt": "2026-11-15T15:29:16.890Z"
},
"summary": {
"collectionId": "g-wagon-research-2c2983f1",
"added": [
{
"id": "youtube:cCPsdFdlshc",
"ref": {
"input": "https://www.youtube.com/watch?v=cCPsdFdlshc",
"platform": "youtube",
"kind": "video",
"id": "youtube:cCPsdFdlshc",
"nativeId": "cCPsdFdlshc",
"url": "https://www.youtube.com/watch?v=cCPsdFdlshc"
},
"title": "Best & Worst G-Wagon Years: Reliability, Interiors & Engines Ranked!",
"channel": "Alliance Motorworks",
"durationSec": 1084,
"origin": "stt",
"language": "en",
"savedAt": "2026-11-14T17:39:41.214Z"
},
{
"id": "youtube:PzJL3aBRas8",
"ref": {
"input": "https://www.youtube.com/watch?v=PzJL3aBRas8",
"platform": "youtube",
"kind": "video",
"id": "youtube:PzJL3aBRas8",
"nativeId": "PzJL3aBRas8",
"url": "https://www.youtube.com/watch?v=PzJL3aBRas8"
},
"title": "Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550)",
"channel": "Alliance Motorworks",
"durationSec": 697,
"origin": "stt",
"language": "en",
"savedAt": "2026-11-14T17:37:21.797Z"
}
],
"skipped": 0,
"failed": [],
"remaining": 0,
"checkedAt": "2026-11-15T15:29:16.891Z"
}
}
}Try adding the playlist itself: put its URL on a line of its own and run the block again. Videos already in the collection are skipped and counted, not read twice.
3. Read it back
GET /collections/{id} returns the collection with a summary of each video: title, channel, duration, language, and origin, which says how its transcript was made.
/api/v1/collections/{id}Read the collectionIts videos (title, channel, duration, how the transcript was made), videos still pending, and the refresh schedule.
curl https://vid2context.com/api/v1/collections/g-wagon-research-2c2983f1const BASE = 'https://vid2context.com';
const res = await fetch(`${BASE}/api/v1/collections/g-wagon-research-2c2983f1`);
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
console.log(JSON.stringify(await res.json(), null, 2));import json
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
headers = {}
req = urllib.request.Request(f"{BASE}/api/v1/collections/g-wagon-research-2c2983f1", headers=headers)
try:
with urllib.request.urlopen(req, timeout=300) as res:
print(json.dumps(json.load(res), indent=2))
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}")npx -y vid2context collection show g-wagon-research-2c2983f1{
"name": "get_collection",
"arguments": {
"collection": "g-wagon-research-2c2983f1"
}
}{
"id": "g-wagon-research-2c2983f1",
"name": "G-Wagon research",
"description": "Buyer videos to compare model years",
"sources": [],
"videoIds": [
"youtube:cCPsdFdlshc",
"youtube:PzJL3aBRas8"
],
"createdAt": "2026-11-15T15:29:16.875Z",
"updatedAt": "2026-11-15T15:29:16.890Z",
"videos": [
{
"id": "youtube:cCPsdFdlshc",
"ref": {
"input": "https://www.youtube.com/watch?v=cCPsdFdlshc",
"platform": "youtube",
"kind": "video",
"id": "youtube:cCPsdFdlshc",
"nativeId": "cCPsdFdlshc",
"url": "https://www.youtube.com/watch?v=cCPsdFdlshc"
},
"title": "Best & Worst G-Wagon Years: Reliability, Interiors & Engines Ranked!",
"channel": "Alliance Motorworks",
"durationSec": 1084,
"origin": "stt",
"language": "en",
"savedAt": "2026-11-14T17:39:41.214Z"
},
{
"id": "youtube:PzJL3aBRas8",
"ref": {
"input": "https://www.youtube.com/watch?v=PzJL3aBRas8",
"platform": "youtube",
"kind": "video",
"id": "youtube:PzJL3aBRas8",
"nativeId": "PzJL3aBRas8",
"url": "https://www.youtube.com/watch?v=PzJL3aBRas8"
},
"title": "Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550)",
"channel": "Alliance Motorworks",
"durationSec": 697,
"origin": "stt",
"language": "en",
"savedAt": "2026-11-14T17:37:21.797Z"
}
],
"pending": [],
"watch": null
}4. One pack for the whole collection
POST /pack with collectionId instead of inputs builds one Markdown document from every video in the collection, sized by maxTokens. Paste it into any chat model, or have an agent read it: the citation rule at the top tells the model to cite each claim as a timestamp link.
/api/v1/packOne context pack for the collectionThe same pack as for a list of inputs, built from every video in the collection.
curl https://vid2context.com/api/v1/pack \
-H 'Content-Type: application/json' \
-d '{
"collectionId": "g-wagon-research-2c2983f1",
"maxTokens": 2500
}'const BASE = 'https://vid2context.com';
const body = {
collectionId: 'g-wagon-research-2c2983f1',
maxTokens: 2500,
};
const res = await fetch(`${BASE}/api/v1/pack`, {
headers: { 'Content-Type': 'application/json' },
method: 'POST',
body: JSON.stringify(body),
});
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
console.log(await res.text());import json
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
body = {
"collectionId": "g-wagon-research-2c2983f1",
"maxTokens": 2500,
}
headers = {"Content-Type": "application/json"}
req = urllib.request.Request(f"{BASE}/api/v1/pack", data=json.dumps(body).encode(), headers=headers, method="POST")
try:
with urllib.request.urlopen(req, timeout=300) as res:
print(res.read().decode())
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}"){
"name": "export_context_pack",
"arguments": {
"collectionId": "g-wagon-research-2c2983f1",
"maxTokens": 2500
}
}# Video context pack
This document holds the transcripts and metadata of 2 videos (29:41 in total), prepared by vid2context for an AI model to read. Each transcript paragraph starts with the time it begins in the video, in brackets; linked times open the video at that moment.
Citation rule: when you use something from a video, cite it as [Title @ m:ss](link), using the time and link of the paragraph you drew on (or [Title @ m:ss] when the video has no link).
Some content was left out to fit a budget of 2500 tokens. Each cut is marked where it happened.
## Contents
1. [Best & Worst G-Wagon Years: Reliability, Interiors & Engines Ranked!](#video-1-best--worst-g-wagon-years-reliability-interiors--engines-ranked) (18:04)
2. [Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550)](#video-2-why-im-selling-my-dream-g-wagon-custom-build-2015-mercedes-g550) (11:37)
## Video 1: Best & Worst G-Wagon Years: Reliability, Interiors & Engines Ranked!
- Channel: [Alliance Motorworks](https://www.youtube.com/channel/UCdEjP_BjQ5audhxLKKzZl2A)
- Published: 2025-03-09
- Duration: 18:04
- Source: https://www.youtube.com/watch?v=cCPsdFdlshc
- Language: en
- Transcript: speech-to-text by stt/cloudflare/@cf/openai/whisper-large-v3-turbo
### Description
> Watch this side-by-side comparison of G-Wagons from 2000 - 2018 to rank the best and worst for interiors, engines, and reliability. This is part 1 of a multi-video series for buying and building your
_Description shortened to 199 of 799 characters._
### Chapters
- [0:00](https://www.youtube.com/watch?v=cCPsdFdlshc&t=0s) G wagon buying guide
- [1:05](https://www.youtube.com/watch?v=cCPsdFdlshc&t=65s) G500 m113 engine overview
- [2:04](https://www.youtube.com/watch?v=cCPsdFdlshc&t=124s) G500 interior and features
- [4:12](https://www.youtube.com/watch?v=cCPsdFdlshc&t=252s) G55 AMG specs and history
- [5:50](https://www.youtube.com/watch?v=cCPsdFdlshc&t=350s) G55 interior and technology
- [8:25](https://www.youtube.com/watch?v=cCPsdFdlshc&t=505s) Best G-Wagon for your budget
- [9:39](https://www.youtube.com/watch?v=cCPsdFdlshc&t=579s) G550 technological leap
- [12:27](https://www.youtube.com/watch?v=cCPsdFdlshc&t=747s) 2016-2018 G-Wagon updates
- [14:01](https://www.youtube.com/watch?v=cCPsdFdlshc&t=841s) Final recommendations
### Transcript
#### G wagon buying guide (0:00)
[0:00](https://www.youtube.com/watch?v=cCPsdFdlshc&t=0s) So you're going to buy a G-Wagon. Which year is best for you? Well, in this video, we're going to do a year-by-year breakdown of the legendary W463 platform, so you can check out the model year ranges, the engine options, and the interior, because if you buy the wrong one, I don't want you getting buyer's remorse or ending up with a bad specimen. My name's Adam. Welcome to the G-Wheel and YouTube channel. I do everything here for the love of G. I'm joined by Joe from Alliance Auto Care. He is the G-Wagon specialist and helped me produce not only these videos, but also the ultimate build and buyer's guide for the G-Wagon. So if you're in the market, click the link in the description right now. Joe, thanks for being here, man.
[0:39] All right. Let's get into it. Let's rock and roll. Let's introduce each one of these three trucks. We're going to hit the year range, the engine options, and give you an interior tour. Let's rock and roll. Cool. We have three trucks here. Starting with our first one, we have a 2000 G500. The second one is a 2012 G55 AMG. The third one is a 2015 G550. We're going to walk through and look at some of the engine options real quick. On the first one, the 2000 G500. Now, there's a couple of models prior to this one, but this is kind of the one everyone gravitates to.
#### G500 m113 engine overview (1:05)
[1:09] This one has what we know the legendary M113 V8. This was Mercedes' big hurrah into the V8s, and this is arguably one of their most reliable V8s out there. Some call it the Land Cruiser Killer. Yeah, it is known as the Land Cruiser Killer. I really like this motor. It's all aluminum. It's super light, and it is as reliable as it gets. Now, some of the key things. It's a single overhead cam motor. It's timing chains. It's two spark plugs per cylinder, and it makes 300 horsepower and 300 foot-pounds of torque. Nice round numbers.
[1:41](https://www.youtube.com/watch?v=cCPsdFdlshc&t=101s) Yeah. It looks simple. It's neat. It's clean. Most importantly, it's easy to work on. Parts are cheap, and parts are available almost everywhere. This is what we call a global motor. Yeah. Sweet. Sweet. It means if you're in Dubai, if you're in India, if you're in Japan, wherever, you can always get parts for it. Or if you're in Arkansas. Let's hop into the inside. Yeah.
> The rest, 2:04 to 18:02, is omitted for length. Fetch it with the get_section tool or the full transcript.
## Video 2: Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550)
- Channel: [Alliance Motorworks](https://www.youtube.com/channel/UCdEjP_BjQ5audhxLKKzZl2A)
- Published: 2026-04-11
- Duration: 11:37
- Source: https://www.youtube.com/watch?v=PzJL3aBRas8
- Language: en
- Transcript: speech-to-text by stt/cloudflare/@cf/openai/whisper-large-v3-turbo
### Description
> Here's how I found it, how I built it, and why I'm selling it. The real story of my 2015 Mercedes G550. For Sale Here:
_Description shortened to 118 of 384 characters._
### Chapters
- [0:00](https://www.youtube.com/watch?v=PzJL3aBRas8&t=0s) Intro
- [0:30](https://www.youtube.com/watch?v=PzJL3aBRas8&t=30s) Background
- [2:45](https://www.youtube.com/watch?v=PzJL3aBRas8&t=165s) The Build
- [4:45](https://www.youtube.com/watch?v=PzJL3aBRas8&t=285s) Ownership
- [6:50](https://www.youtube.com/watch?v=PzJL3aBRas8&t=410s) Why Im Selling
- [8:10](https://www.youtube.com/watch?v=PzJL3aBRas8&t=490s) New Vehicle
14 more lines not shown. Run it to see the whole response.
POST /bundle takes the same collectionId for a zip with every format, and GET /search?collectionId=<id> searches only this collection's transcripts.
5. Notes for Obsidian
POST /exports/obsidian turns videos into Markdown notes with frontmatter, chapter headings and timestamp links, plus an index note. The server writes nothing: the answer holds the files, for you or your agent to save into a vault. The MCP tool export_obsidian writes them into a vault path for you.
The block exports one video. Paste your collection id from step 1 into Collection id to export every video in the collection as well.
/api/v1/exports/obsidianExport notes for ObsidianOne Markdown note per video with frontmatter, chapters and timestamp links, and an index note. The server writes nothing: you get the files.
curl https://vid2context.com/api/v1/exports/obsidian \
-H 'Content-Type: application/json' \
-d '{
"inputs": [
"https://www.youtube.com/watch?v=PzJL3aBRas8"
]
}'const BASE = 'https://vid2context.com';
const body = {
inputs: [
'https://www.youtube.com/watch?v=PzJL3aBRas8',
],
};
const res = await fetch(`${BASE}/api/v1/exports/obsidian`, {
headers: { 'Content-Type': 'application/json' },
method: 'POST',
body: JSON.stringify(body),
});
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
console.log(JSON.stringify(await res.json(), null, 2));import json
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
body = {
"inputs": [
"https://www.youtube.com/watch?v=PzJL3aBRas8",
],
}
headers = {"Content-Type": "application/json"}
req = urllib.request.Request(f"{BASE}/api/v1/exports/obsidian", data=json.dumps(body).encode(), headers=headers, method="POST")
try:
with urllib.request.urlopen(req, timeout=300) as res:
print(json.dumps(json.load(res), indent=2))
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}"){
"files": [
{
"path": "vid2context/Why I'm Selling My DREAM G-Wagon (Custom Build 2015 Mercedes G550).md",5 more lines not shown. Run it to see the whole response.
6. Share the definition
GET /collections/{id}/export returns a small, portable definition: the name, the sources, the video URLs and the refresh schedule. Send it to another vid2context server with POST /collections/import (add ?refresh=1 to read the videos right away) and that server rebuilds the same collection from the platforms.
/api/v1/collections/{id}/exportExport the collection definitionName, sources, video ids and schedule: everything another server needs to rebuild the collection with POST /collections/import.
curl https://vid2context.com/api/v1/collections/g-wagon-research-2c2983f1/exportconst BASE = 'https://vid2context.com';
const res = await fetch(`${BASE}/api/v1/collections/g-wagon-research-2c2983f1/export`);
if (!res.ok) {
const { error } = await res.json();
throw new Error(`${error.code}: ${error.message} ${error.hint ?? ''}`);
}
console.log(JSON.stringify(await res.json(), null, 2));import json
import urllib.error
import urllib.request
BASE = "https://vid2context.com"
headers = {}
req = urllib.request.Request(f"{BASE}/api/v1/collections/g-wagon-research-2c2983f1/export", headers=headers)
try:
with urllib.request.urlopen(req, timeout=300) as res:
print(json.dumps(json.load(res), indent=2))
except urllib.error.HTTPError as err:
error = json.load(err)["error"]
raise SystemExit(f"{error['code']}: {error['message']} {error.get('hint', '')}"){
"format": "vid2context.collection",
"version": 1,
"name": "G-Wagon research",
"description": "Buyer videos to compare model years",
"sources": [],
"videos": [
"https://www.youtube.com/watch?v=cCPsdFdlshc",
"https://www.youtube.com/watch?v=PzJL3aBRas8"
]
}Keep it up to date
A collection with sources can refresh itself. PATCH /collections/{id} with a watch schedule (for example {"every": "daily", "at": "06:00"}, in UTC) checks the sources on that schedule and adds new videos, and a webhook can tell you when it did. The collections guide covers schedules, webhooks and limits.
Next
- Cited answers and briefs: ask questions across the videos you just collected.
- Collections and library examples: every request on one page, plus the library itself.