S3 bucket objects
Feed type: Site / S3Blob
Bucket objects under a prefix
PDFs, images, audio, and video
Documents and uploaded files
Path filters and read limits
Setup fields
Bucket Name *Object PrefixCustom EndpointAllowed PathsMaximum Objects
Ingest
What gets ingested
Graphlit reads the selected Amazon S3 surfaces, converts the source material into searchable content, and keeps enough source metadata for grounded answers, retrieval, and downstream agent workflows.
AmazonS3
Prepare
What Graphlit prepares
The integration is not just a connector. Graphlit turns Amazon S3 into content that can be searched, cited, summarized, enriched with observations, and supplied to agents through the Graphlit API and MCP.
{
"source": "Amazon S3",
"content": "S3 bucket objects",
"extracted": [
"entities",
"observations",
"facts",
"summaries"
],
"citations": [
"Amazon S3 source references"
],
"agentContext": {
"searchable": true,
"groundedAnswers": true,
"deliveryEnabled": false
}
}Use cases
What you can build with Amazon S3
01
Build a Amazon S3 knowledge base from bucket objects under a prefix and pDFs, images, audio, and video and search it alongside the rest of your Graphlit content.
02
Ask grounded questions over Amazon S3 context without forcing users to leave the tools where the work originally happened.
03
Extract people, organizations, projects, events, facts, and decisions from Amazon S3 content so agents can reason over durable context.
04
Combine Amazon S3 with Slack, Website, and GitHub to build cross-tool RAG, research, and operational intelligence workflows.
Need a code sample? Ask our AI assistant
SDK:
Try:or
FAQ
Common questions
Related
Commonly paired integrations
Start building
Start building with Amazon S3 and Graphlit
Create a free Graphlit project, connect Amazon S3, and turn real operational context into retrieval, knowledge graphs, and MCP-native agent workflows.