> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pureframe.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Examples

> End-to-end walkthroughs combining multiple Pureframe AI features.

These examples combine calls documented individually elsewhere into complete, runnable flows.

## Build a searchable clip library

Using the [Python SDK](/sdks/python-sdk) to index a folder of recordings and search them.

```python theme={null}
from pureframe import Pureframe
import glob, time

client = Pureframe(token="pf_...")

# 1. Create a collection
collection = client.collections.create_collection(name="Sales calls")

# 2. Upload every recording in a folder
job_ids = []
for path in glob.glob("recordings/*.mp4"):
    job = client.upload.upload_video(collection_id=collection.data.id, file=open(path, "rb"))
    job_ids.append(job.data.job_id)

# 3. Wait for every job to finish
for job_id in job_ids:
    while True:
        status = client.jobs.get_job(job_id)
        if status.data.status in ("done", "failed"):
            break
        time.sleep(5)

# 4. Search across the whole collection
results = client.search.search(query="customer mentions renewal", collection_id=collection.data.id)
for video in results.data:
    for seg in video.segments:
        print(f"{video.filename} @ {seg.timestamp_start:.1f}s — {seg.score:.2f}")
```

## Give an agent video search via MCP

Configure Claude Code to search your library directly, using the setup from [Connect an Agent](/agents/connect-an-agent):

```bash theme={null}
claude mcp add pureframe -- npx -y @pureframeai/mcp
```

Set `PUREFRAME_API_KEY` to a `read_only` key (see [API Keys](/get-started/api-keys)) so the agent can search but never upload or delete. Then, in conversation:

> "Search our onboarding call recordings for anywhere a customer asks about SSO, and tell me what was said."

Claude calls `search_videos`, receives clips with `thumbnail_base64` and transcribed speech, and can answer directly from what it sees and reads — no manual video scrubbing.

## Reverse image search for brand mentions

Find every moment a specific product or logo appears on screen, using a reference image instead of a text description:

```bash theme={null}
curl -X POST https://api.pureframe.ai/v1/search \
  -H "Authorization: Bearer pf_..." \
  -F "image=@logo-reference.jpg" \
  -F "modes=video"
```

This restricts to `modes=video` since a static reference image has no transcript to match. Combine with `collection_id` to scope the scan to a specific library — see [Image Search](/search/image) for the full parameter reference.