feat: file attachment #6766
Open
feat: file attachment #6766
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit introduces a new field, `is_embedding`, to the `SessionInfo` structure to clearly mark sessions running dedicated embedding models. Key changes: - Adds `is_embedding` to the `SessionInfo` interface in `AIEngine.ts` and the Rust backend. - Updates the `loadLlamaModel` command signatures to pass this new flag. - Modifies the llama.cpp extension's **auto-unload logic** to explicitly **filter out** and **not unload** any currently loaded embedding models when a new text generation model is loaded. This is a critical performance fix to prevent the embedding model (e.g., used for RAG) from being repeatedly reloaded. Also includes minor code style cleanup/reformatting in `jan-provider-web/provider.ts` for improved readability.
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a comprehensive file attachment feature for document retrieval-augmented generation (RAG) in the Jan application. It provides capabilities for uploading, indexing, and semantically searching documents (PDFs, text files, Office docs, etc.) during chat conversations.
- Implements a complete RAG pipeline with vector storage, semantic search, and document parsing
- Adds settings UI for configuring attachment behavior (file size limits, chunk sizes, search modes)
- Introduces new extension architecture for RAG and vector database operations
Reviewed Changes
Copilot reviewed 92 out of 95 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| web-app/src/types/attachment.ts | Defines unified attachment types for images and documents |
| web-app/src/services/uploads/default.ts | Implements document ingestion service with RAG extension integration |
| web-app/src/routes/settings/attachments.tsx | Provides settings UI for attachment configuration |
| web-app/src/hooks/useAttachments.ts | Manages attachment settings state and persistence |
| web-app/src/containers/ChatInput.tsx | Extends chat input with document and image attachment capabilities |
| src-tauri/plugins/tauri-plugin-vector-db | New Tauri plugin for vector database operations with sqlite-vec support |
| extensions/rag-extension | RAG extension providing document retrieval tools and orchestration |
| core/src/browser/extensions/vector-db.ts | Core vector database extension interface |
Comments suppressed due to low confidence (2)
web-app/src/locales/en/common.json:1
- Removed trailing empty line at end of file.
{
src-tauri/plugins/tauri-plugin-vector-db/src/db.rs:1
- [nitpick] Missing space after closing brace. Consider formatting:
if mag_a == 0.0 || mag_b == 0.0 { return Ok(0.0) }
use crate::VectorDBError;
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Co-authored-by: Copilot <[email protected]>
dinhlongviolin1
requested review from
Copilot,
louis-menlo,
qnixsynapse and
urmauur
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 92 out of 95 changed files in this pull request and generated 3 comments.
Comments suppressed due to low confidence (2)
web-app/src/hooks/useThreadScrolling.tsx:1
- Dependencies in useCallback should only include values that actually affect the callback. Remove
setIsAtBottomandsetHasScrollbarfrom dependencies as they are stable setState functions.
import { useCallback, useEffect, useMemo, useRef, useState } from 'react'
src-tauri/plugins/tauri-plugin-vector-db/src/db.rs:1
- [nitpick] Format the early return with proper spacing and line breaks for better readability.
use crate::VectorDBError;
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Co-authored-by: Copilot <[email protected]>
- Added shallow equality guard for `connectedServers` state to prevent redundant updates when the fetched server list hasn't changed. - Updated error handling for server fetch to only clear the state when it actually contains data. - Introduced `newHasActiveModels` variable and conditional updater for `hasActiveModels` to avoid unnecessary state changes. - Adjusted error handling for active model fetch to only set `hasActiveModels` to `false` when the current state differs. These changes reduce needless re‑renders and improve component performance.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe Your Changes
Overview: File Attachment Feature
What Files Are Supported
Document Formats:
How It Works
Architecture:
Key Components:
Settings (extensions/rag-extension/settings.json):
Internal Tools Exposed:
Ingestion Flow:
Notable Features:
Fixes Issues
Self Checklist