Ingest Podcast MP3

Ingest an MP3 podcast recording into Graphlit

Chat with a Podcast is another common use case, and a great source of knowledge.

With built-in audio transcription support, Graphlit automatically transcribes audio recordings (and video recordings with audio) to create a time-synchronized transcript.

Graphlit uses the power of Large Language Models (LLMs) to extract useful knowledge from these transcripts.

We can use this podcast recording about unstructured data, which we've placed on cloud storage as an example.

https://graphlitplatform.blob.core.windows.net/samples/Unstructured%20Data%20is%20Dark%20Data%20Podcast.mp3

Or if you have a URL to a cloud-hosted MP3 or AAC file, feel free to use that one.

Graphlit provides the ingestUri mutation to bring file-based content into the platform, and make it available to search, query and have a conversation about.

Assuming you're logged into the Graphlit Developer Portal, you can use the embedded API explorer to test this out. For more information, see the Projects page.

Now, try this yourself, and note, you can press the copy icon when you mouse-over the text boxes below.

Once you have your audio file ingested into Graphlit, you can explore the knowledge inside.

Mutation:

mutation IngestUri($uri: URL!) {
  ingestUri(uri: $uri) {
    id
    name
    state
    type
    fileType
    uri
  }
}

Variables:

{
  "uri": "https://graphlitplatform.blob.core.windows.net/samples/Unstructured%20Data%20is%20Dark%20Data%20Podcast.mp3"
}

Response:

{
  "type": "FILE",
  "fileType": "AUDIO",
  "uri": "https://graphlitplatform.blob.core.windows.net/samples/Unstructured%20Data%20is%20Dark%20Data%20Podcast.mp3",
  "id": "cc4f2a1f-b103-4cab-8a98-2b8cd84b691c",
  "name": "Unstructured Data is Dark Data Podcast.mp3",
  "state": "CREATED"
}