Commit Graph

6 Commits

Author SHA1 Message Date
Huu Le 087c96164d feat: [server] Add Human in the Loop example with FastAPI integration (#630) 2025-06-02 17:47:04 +07:00
Thuc Pham eee3230e99 feat: support custom layout (#641) 2025-05-23 14:18:22 +07:00
Huu Le 0bc5a0d882 feat: Add config for suggest next question (#640)
* Enhance LlamaIndexServer with next question suggestion feature

- Added `suggest_next_questions` parameter to the LlamaIndexServer for suggesting follow-up questions after the assistant's response.
- Updated README.md to document the new configuration option.
- Introduced `SUGGEST_NEXT_QUESTION_PROMPT` in prompts.py for customizable question suggestions.
- Bumped version to 0.1.16 in uv.lock to reflect the new feature.

* Implement next question suggestion feature in LlamaIndexServer

- Added `suggestNextQuestions` option to LlamaIndexServer for suggesting follow-up questions after the assistant's response.
- Updated README.md to include the new configuration option.
- Modified example workflow to utilize the new feature.
- Enhanced chat handler to conditionally send suggested questions based on the new option.

* add changeset

* remove log

* bundle ui instead of download

* check test

* check test

check test

check test

check test

check test

check test

check test

check test

check test

check test

* fix tests

* Update artifact path in workflow and clarify README.md text

- Changed the artifact path in the GitHub Actions workflow from `python/llama-index-server/dist/` to `dist/`.
- Revised README.md to clarify the default prompt used for the `suggest_next_questions` configuration option.

* support changeset for python

* refactor: update llama-index-server structure and workflows

* fix workflows

* fix workflows

* fix workflows

* add changeset

* fix cannot release python

* Update packages/server/README.md

Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>

* Update starter questions in LlamaIndex App and add TODO for suggestion feature in chat API

---------

Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2025-05-23 12:48:45 +07:00
Huu Le 58362542c0 chore: add workflow contract for server (#623) 2025-05-16 14:26:24 +07:00
Huu Le f072308d03 feat: Add dev mode (#610)
* Add UI components and static assets for chat interface

* feat: Add simple chat app example with FastAPI integration

* fix: update default workflow file path and improve error handling

* update doc

* change to file_path

* include changes from #614

* fix mypy

* support devmode for backend ts server

* Revert "support devmode for backend ts server"

This reverts commit bd943fd8c1.

* fix: polling should work when server not yet started

* bump chat-ui to fix syntax highlight issue

* fix: missing language for code editor

* enhance UI with shadow overlay

* enhance doc

* fix minor UI bugs

* enhance doc

* remove unessesary debug log

* fix wrong check

* increase delay time before trigger polling

* feat: support dev mode for backend ts server (#616)

* feat: support dev mode for backend ts server

* update message

* validate typescript file

* fix: format

* use temp file to avoid server restart

* fix format

* use npx tsc

* remove typescript deps

---------

Co-authored-by: thucpn <thucsh2@gmail.com>
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2025-05-15 14:56:08 +07:00
Thuc Pham 3960618454 chore: create-llama monorepo (#581)
* chore: create-llama monorepo

* add root package.json and pnpm workspace

* keep e2e inside create-llama

* update root package.json

* move scripts and dev dependencies of create-llama to root

* update e2e test for create-llama package

* update lint workflow

* update release llama-index-server workflow

* update path for test_llama_index_server workflow

* remove local lock file

* keep lint and format in create-llama

* fix: format

* update pre-commit

* move playwright back to create-llama

* disable pnpm for installing generated frontend

* use npm for type check

* update gitignore

* try --ignore-workspace option

* Move llama-index-server from packages/python-server to python directory

* update CI for python server

* Create plenty-spies-tickle.md
2025-04-25 18:38:02 +07:00