James Brunton and GitHub
5541dd666c
Flesh out RAG system ( #6197 )
...
# 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
```
2026-05-01 14:11:54 +01:00
Anthony Stirling and GitHub
5605062153
Add Dependabot groups for frontend npm + cargo deps ( #6287 )
2026-05-01 11:37:07 +01:00
86774d556e
Pdf comment agent ( #6196 )
...
Co-authored-by: James Brunton <[email protected]
2026-05-01 10:19:38 +01:00
2dc5276e8b
Fix French translations for various terms ( #6218 )
...
Co-authored-by: Copilot <[email protected]
2026-04-30 23:09:57 +01:00
c58deb6b55
build(deps): bump tauri-apps/tauri-action from 0.5.25 to 0.6.2 ( #6257 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-30 22:36:15 +01:00
Anthony Stirling and GitHub
324a7cd25e
decouple appimage ( #6281 )
2026-04-30 21:36:33 +01:00
Anthony Stirling and GitHub
d28ad89f64
gha cleanups ( #6275 )
...
# Description of Changes
Adds all pre commit PR checks under single file with job validator to
have a true "required" run step "all-checks-passed" check
Moves all GHAs into workflow helper function calls
Note if: always() overrides the default skip-on-needs-failure, "Needs"
is added to ensure the validation runs at end of all other tasks
---
## Checklist
### General
- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md )
- [ ] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md )
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md )
(if applicable)
- [ ] I have performed a self-review of my own code
- [ ] My changes generate no new warnings
### Documentation
- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/ )
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags )
(for new translation tags only)
### Translations (if applicable)
- [ ] I ran
[`scripts/counter_translation.py`](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/docs/counter_translation.md )
### UI Changes (if applicable)
- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)
### Testing (if applicable)
- [ ] I have run `task check` to verify linters, typechecks, and tests
pass
- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md#7-testing )
for more details.
2026-04-30 17:08:34 +01:00
Anthony Stirling and GitHub
d8c1ffa8ef
fix stubs playwright ( #6274 )
2026-04-30 12:37:15 +01:00
b552feaf28
Update Backend 3rd Party Licenses ( #6264 )
...
Co-authored-by: stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com>
2026-04-30 10:19:08 +01:00
Peter Dave Hello and GitHub
890cf16f74
Adjust zh-TW translation ignore list ( #6062 )
2026-04-29 10:55:51 +01:00
493757bf41
build(deps): bump com.google.guava:guava from 33.5.0-jre to 33.6.0-jre in /app/common ( #6260 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 21:42:20 +01:00
99b9b60f50
build(deps-dev): bump @stylistic/stylelint-plugin from 4.0.0 to 5.1.0 in /devTools ( #6177 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 21:42:02 +01:00
85aa722f37
build(deps): bump the npm_and_yarn group across 2 directories with 8 updates ( #6266 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 21:41:45 +01:00
1c42ce7087
build(deps): bump com.github.junrar:junrar from 7.5.8 to 7.5.10 in /app/common ( #6261 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 18:45:49 +01:00
5bd62eeb5c
build(deps): bump github/codeql-action from 4.32.6 to 4.35.2 ( #6256 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 18:45:38 +01:00
87e5b84324
build(deps): bump docker/setup-buildx-action from 3.12.0 to 4.0.0 ( #6254 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 18:45:24 +01:00
568c6da165
build(deps-dev): bump stylelint from 17.4.0 to 17.8.0 in /devTools ( #6253 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 18:45:09 +01:00
Anthony Stirling and GitHub
c818db1042
ci(tauri): skip Linux GPG signing when secret is missing ( #6263 )
2026-04-28 18:43:52 +01:00
cd3a59f077
build(deps): bump com.drewnoakes:metadata-extractor from 2.19.0 to 2.20.0 ( #6184 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Anthony Stirling <[email protected]
2026-04-28 17:40:22 +01:00
05e2ce45d4
build(deps): bump com.drewnoakes:metadata-extractor from 2.19.0 to 2.20.0 in /app/common ( #6193 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Anthony Stirling <[email protected]
2026-04-28 17:40:04 +01:00
94cf25b319
Update Backend 3rd Party Licenses ( #6243 )
...
Co-authored-by: stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com>
2026-04-28 17:38:00 +01:00
4149276b01
build(deps): bump actions/dependency-review-action from 4.8.2 to 4.9.0 ( #6230 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 17:37:43 +01:00
a26b15b1fe
Lazy load open cv ( #6236 )
...
Co-authored-by: EthanHealy01 <[email protected]
2026-04-28 17:36:34 +01:00
ConnorYoh and GitHub
4e4918b91e
fix(workflow): stop leaking peer share tokens from participant session API ( #6241 )
2026-04-28 17:36:20 +01:00
Anthony Stirling and GitHub
b966e771a4
add dependabot 7 day cooldown ( #6242 )
2026-04-28 17:36:09 +01:00
376e49a947
build(deps): bump peter-evans/create-pull-request from 8.1.0 to 8.1.1 ( #6229 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 17:35:56 +01:00
128697958b
build(deps): bump org.springframework.boot from 4.0.5 to 4.0.6 ( #6225 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 17:35:32 +01:00
60c39c6f6e
build(deps): bump actions/stale from 10.1.1 to 10.2.0 ( #6227 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 17:35:17 +01:00
c3c5b08ce6
build(deps): bump sigstore/cosign-installer from 4.0.0 to 4.1.1 ( #6226 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-28 17:35:04 +01:00
James Brunton and GitHub
49f24fa7a9
Have Task choose free ports for dev servers ( #6145 )
2026-04-28 17:26:04 +01:00
Anthony Stirling and GitHub
12a00fe9c5
bug fixes for some desktop tools ( #6246 )
2026-04-28 17:24:56 +01:00
James Brunton and GitHub
3c09b7f736
Guard PR commenting on pull requests ( #6250 )
...
# Description of Changes
Attempt 2 at #6249
2026-04-28 15:17:42 +01:00
James Brunton and GitHub
5116e6ec43
Set CI to run the same in the merge queue as it does in CI ( #6249 )
2026-04-28 14:13:55 +01:00
Anthony Stirling and GitHub
8daee7303d
playwright ( #6025 )
2026-04-27 11:35:50 +01:00
Philip H. and GitHub
688c3e1e58
Update: AUR PKGBUILDs desktop and server ( #6220 )
2026-04-25 22:20:05 +01:00
albanobattistella and GitHub
df5d0a9aa8
Fix translation ( #6224 )
2026-04-25 22:19:53 +01:00
James Brunton and GitHub
1e3da14081
Change frontend .env files to be committed and have .env.*.local overrides ( #6207 )
2026-04-25 13:09:59 +01:00
Anthony Stirling and GitHub
276bbd635c
release notes fix for engine ( #6219 )
2026-04-25 13:09:48 +01:00
Ludy and GitHub
8cd6377131
build: Add Sync app version to AUR PKGBUILD files ( #6222 )
2026-04-25 13:09:25 +01:00
Ludy and GitHub
9890d6a7de
fix: skip translation key extraction for files without i18n usage ( #6221 )
2026-04-25 13:08:24 +01:00
5cfb77314f
Update Backend 3rd Party Licenses ( #5932 )
...
Co-authored-by: stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com>
Co-authored-by: Ludy <[email protected]
2026-04-24 21:34:58 +01:00
6ebd85defb
🌐 Sync Translations + Update README Progress Table ( #5716 )
...
Co-authored-by: stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com>
2026-04-24 21:30:37 +01:00
c16dc1782d
build(deps): bump dorny/test-reporter from 2.5.0 to 3.0.0 ( #5973 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Anthony Stirling <[email protected]
2026-04-24 21:24:21 +01:00
87464aca53
build(deps): bump com.github.jk1.dependency-license-report from 3.1.1 to 3.1.2 ( #6188 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 21:23:30 +01:00
2ade011106
build(deps): bump com.bucket4j:bucket4j_jdk17-core from 8.17.0 to 8.18.0 ( #6189 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 21:21:02 +01:00
ac0ef7056e
build(deps): bump astral-sh/setup-uv from 4.2.0 to 8.1.0 ( #6181 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 19:26:23 +01:00
7cb0f928bc
build(deps): bump docker/login-action from 3.7.0 to 4.1.0 ( #6072 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 19:26:02 +01:00
42978b9ad6
build(deps): bump docker/setup-qemu-action from 3.7.0 to 4.0.0 ( #6021 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 19:25:41 +01:00
c5cdde0b58
build(deps): bump docker/build-push-action from 6.18.0 to 7.1.0 ( #6192 )
...
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-04-24 19:25:21 +01:00
Anthony Stirling and GitHub
9f6d7750f2
translation additions ( #6208 )
2026-04-24 14:02:13 +01:00
James BruntonandGitHub
Anthony StirlingandGitHub
Peter Dave HelloandGitHub
Philip H.andGitHub
albanobattistellaandGitHub
LudyandGitHub