mirror of
https://github.com/Frooodle/Stirling-PDF.git
synced 2026-05-01 23:16:31 +02:00
5541dd666c
# Description of Changes
Flesh out the RAG system and connect it to the PDF Question Agent so it
can respond to questions about PDFs of an extremely large size.
I'd expect lots more work will need to be done to finish off the RAG
system to really be what we need, but this should be a reasonable start
which will let us connect it to tools and have the ingestion mostly
handled automatically. I'm leaving file deletion and proper file ID
management to be done in a future PR. We also need to consider whether
all tools should retrieve content exclusively via RAG, or whether it's
beneficial to have tools sometimes fetch the direct content and other
times fetch it from RAG.
A diagram of the expected interaction is as follows:
```mermaid
sequenceDiagram
autonumber
actor U as User
participant FE as Frontend<br/>(ChatPanel)
participant J as Java<br/>(AiWorkflowService)
participant O as Engine:<br/>OrchestratorAgent
participant QA as Engine:<br/>PdfQuestionAgent
participant RAG as Engine:<br/>RagService + SqliteVecStore
participant V as VoyageAI<br/>(embeddings)
participant L as LLM<br/>(Claude / etc.)
U->>FE: types "Summarise this PDF"<br/>(PDF already uploaded)
FE->>J: POST /api/v1/ai/orchestrate/stream<br/>multipart: fileInputs[], userMessage
Note over J: ByteHashFileIdStrategy<br/>id = sha256(bytes)[:16]
J->>O: POST /api/v1/orchestrator<br/>{ files:[{id,name}], userMessage }
O->>L: route via fast model
L-->>O: delegate_pdf_question
O->>QA: PdfQuestionRequest
loop for each file
QA->>RAG: has_collection(file.id)
RAG-->>QA: false
end
QA-->>O: NeedIngestResponse(files_to_ingest)
O-->>J: { outcome:"need_ingest", filesToIngest:[...] }
Note over J: onNeedIngest
loop per file
J->>J: PDFBox: extract page text
J->>O: POST /api/v1/rag/documents<br/>(long-running timeout)
O->>RAG: chunk + stage documents
O->>V: embed_documents (batches of 256)
V-->>O: embeddings
O->>RAG: add_documents
O-->>J: { chunks_indexed: N }
end
Note over J: retry with resumeWith=pdf_question
J->>O: POST /api/v1/orchestrator
Note over O: fast-path to PdfQuestionAgent
O->>QA: PdfQuestionRequest
Note over QA: build RagCapability<br/>pinned to file IDs
QA->>L: run(prompt) with search_knowledge tool
loop up to max_searches
L->>QA: search_knowledge(query)
QA->>V: embed_query
V-->>QA: query vector
QA->>RAG: search(vector, collections=[file.id])
RAG-->>QA: top-k chunks
QA-->>L: formatted chunks
end
Note over QA: once budget spent,<br/>prepare() hides the tool
L-->>QA: PdfQuestionAnswerResponse
QA-->>O: answer
O-->>J: { outcome:"answer", answer, evidence }
J-->>FE: SSE "result"
FE->>U: assistant bubble
```
Stirling PDF - The Open-Source PDF Platform
Stirling PDF is a powerful, open-source PDF editing platform. Run it as a personal desktop app, in the browser, or deploy it on your own servers with a private API. Edit, sign, redact, convert, and automate PDFs without sending documents to external services.
Key Capabilities
- Everywhere you work - Desktop client, browser UI, and self-hosted server with a private API.
- 50+ PDF tools - Edit, merge, split, sign, redact, convert, OCR, compress, and more.
- Automation & workflows - No-code pipelines direct in UI with APIs to process millions of PDFs.
- Enterprise‑grade - SSO, auditing, and flexible on‑prem deployments.
- Developer platform - REST APIs available for nearly all tools to integrate into your existing systems.
- Global UI - Interface available in 40+ languages.
For a full feature list, see the docs: https://docs.stirlingpdf.com
Quick Start
docker run -p 8080:8080 docker.stirlingpdf.com/stirlingtools/stirling-pdf
Then open: http://localhost:8080
For full installation options (including desktop and Kubernetes), see our Documentation Guide.
Resources
Support
- Community Discord
- Bug Reports: Github issues
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
This project uses Task as a unified command runner for all build, dev, and test commands. Run task install to get started, or see the Developer Guide for full details.
For adding translations, see the Translation Guide.
License
Stirling PDF is open-core. See LICENSE for details.