README.md
Serverless document and media processing with AI chat
. Upload documents, images, video, and audio — extract text with OCR or transcription — query using Amazon Bedrock.
Tools (3)
upload_documentUpload documents, images, video, or audio for processing.query_contentQuery processed content using Amazon Bedrock.extract_textPerform OCR or transcription on uploaded media files.Environment Variables
AWS_REGIONrequiredThe AWS region where Bedrock and Lambda are deployedAWS_ACCESS_KEY_IDrequiredAWS access key for authenticationAWS_SECRET_ACCESS_KEYrequiredAWS secret key for authenticationConfiguration
claude_desktop_config.json
{
"mcpServers": {
"ragstack-lambda": {
"command": "npx",
"args": ["-y", "@hatmanstack/ragstack-lambda"],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "<your-key>",
"AWS_SECRET_ACCESS_KEY": "<your-secret>"
}
}
}
}Try it
→Upload this PDF and summarize its main points using RAGStack.
→Transcribe this audio file and then ask Bedrock to identify the action items.
→Perform OCR on this image and search the text for any mentions of invoice numbers.
→Query my uploaded documents to find the project deadline mentioned in the meeting notes.