Hermes Pipeline
78 lines
3.3 KiB
Markdown
78 lines
3.3 KiB
Markdown
---
|
|
name: literature-review-with-traceable-ai-evidence
|
|
version: 1.0.0
|
|
description: Enable researchers to ingest documents, asynchronously index them, and
|
|
interact with multi-agent AI to answer questions with verifiable citations to original
|
|
text.
|
|
inputs:
|
|
- Documents in PDF, Office, image, or text formats
|
|
- Research questions or topics of interest
|
|
- 'Optional: user model configuration via .env or settings'
|
|
steps:
|
|
- Upload documents to a project (via desktop app or web UI)
|
|
- System asynchronously converts Office docs to PDF if needed, runs OCR to extract
|
|
text with coordinates, chunks and embeds into vector store
|
|
- User starts a main research session or creates exploration branches without waiting
|
|
for indexing to finish
|
|
- Leader agent receives query and delegates subtasks to researcher, reviewer, writer
|
|
subagents
|
|
- Subagents perform hybrid retrieval and rerank to find relevant chunks with source
|
|
coordinates
|
|
- Agents synthesize answers and return evidence with clickable citations that highlight
|
|
original pages
|
|
- User verifies conclusions by navigating to cited source locations and can save notes
|
|
to research memory or mind map
|
|
outputs:
|
|
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
|
- Research session history with branches
|
|
- Indexed document library for future queries
|
|
- Mind maps or structured notes
|
|
- Persistent run events for resuming sessions
|
|
tags: []
|
|
metadata:
|
|
source_repo: https://github.com/0verL1nk/PaperSage.git
|
|
extracted_at: ''
|
|
confidence: 0.85
|
|
---
|
|
|
|
# literature-review-with-traceable-ai-evidence
|
|
|
|
Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.
|
|
|
|
## Steps
|
|
|
|
1. Upload documents to a project (via desktop app or web UI)
|
|
2. System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store
|
|
3. User starts a main research session or creates exploration branches without waiting for indexing to finish
|
|
4. Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents
|
|
5. Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates
|
|
6. Agents synthesize answers and return evidence with clickable citations that highlight original pages
|
|
7. User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map
|
|
|
|
## Inputs
|
|
|
|
- Documents in PDF, Office, image, or text formats
|
|
- Research questions or topics of interest
|
|
- Optional: user model configuration via .env or settings
|
|
|
|
## Outputs
|
|
|
|
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
|
- Research session history with branches
|
|
- Indexed document library for future queries
|
|
- Mind maps or structured notes
|
|
- Persistent run events for resuming sessions
|
|
|
|
## Failure Modes
|
|
|
|
- Missing local Office/LibreOffice converter causes document conversion failure
|
|
- First-time model download may be slow or require network
|
|
- OCR may have low confidence on poor quality scans
|
|
- Retrieval might miss context if chunking splits semantics
|
|
- Multi-agent coordination could produce conflicting intermediate results
|
|
|
|
## Source
|
|
|
|
Extracted from: [https://github.com/0verL1nk/PaperSage.git](https://github.com/0verL1nk/PaperSage.git)
|
|
Confidence: 0.85
|