* feat: support human in the loop for TS
* add example for custom workflow
* fix: need to request humanResponseEvent to save missing step to snapshot
* refactor: human response data should be any
* refactor runWorkflow function to support resume stream
* refactor: hitl
* fix: workflow
* add summary event
* send tool event
* use requestId from Vercel
* update chat route.ts
* fix copy utils/*
* refactor: workflow and stream
* Create eight-moons-perform.md
* update typo
* make schema simple
* fix typo
* use messages in startAgentEvent
* save to snapshots folder
* fix lint
* feat: workflowBaseEvent
* include response event in input event
* simplify type
* update readme
* update document
* fix typecheck
* bump: "@llamaindex/workflow": "~1.1.8"
* remove any
* use fixed tsx version to fix e2e
* fix wrong copy
* add cli hitl examples as a use case for both Python and TS
* update changeset to release create-llama also
* fix e2e
* fix e2e
* hitl frontend chat
* try disable hitl test
* feat: show document artifact after generating report
* keep chat message content as it is
* use artifactEvent from server
* add deep research example
* bump chat-ui for new editor
* import editor css
* hide warning for workflowEvent<{}>() in eject mode
* fix format
* use CL for better testing
* generate artifact after streaming report in Python
* bump chat-ui to support citations
* use isinstance to check stream
* fix document editor spacing
* Create tame-wolves-obey.md
* add sources to document artifact
* add sources to document artifact in python
* type cast
* no need score
* fix lint
* move handle stream logic to server
* refactor: use chunk.text and chunk.raw
* bump chat-ui 0.5.6 to fix citations
* update changset
* fix lock
* init private support for python BE
* feat: Add private file handling and upload support in FastAPI
- Introduced `main.py` to set up the FastAPI application with file upload capabilities.
- Created `workflow.py` to manage file reading and tool creation for uploaded files.
- Updated `server.py` to include upload API configuration.
- Modified chat router to handle file uploads and return server file metadata.
- Refactored chat models to support new file handling structure.
- Enhanced file service to manage private file storage and retrieval.
* add process base64 and update examples
* add readme example
* fix test
* feat: Add file upload support to LlamaIndexServer TS
* add get_file to fileservice
* refactor: Simplify file storage logic in helpers.ts
* update example
* attach file to user message
* fix example, improve model
* feat: Add file upload support and enhance chat workflow in LlamaIndexServer
* remove redundant change
* support agent workflow for ts
* Enhance README and add file upload examples for LlamaIndex Server. Updated instructions for running examples and added new workflows for handling uploaded files. Included detailed notes on using file attachments in workflows.
* update doc
* update example
* Enhance README with detailed instructions for file upload in chat UI. Update custom workflow to handle file attachments and modify chat router to remove unused attachment handling. Refactor create_workflow to pass attachments from chat request.
* Refactor file handling in workflows by updating the create_file_tool function to accept file attachments directly. Introduce a new ServerFileResponse model for better file response handling. Update chat router to utilize the new FileUpload model for file uploads. Clean up imports and ensure consistent file attachment processing across workflows.
* Enhance file handling in workflows by updating README and example files. Introduce a new `workflowFactory` structure to support file attachments, and improve the `extractFileAttachments` function for better clarity and usability. Update descriptions in tools to reflect changes in file ID handling.
* fix unstoppable
* chore: fix issues
* add changeset
* bump chat-ui
* bump chat-ui for eject project
---------
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
* 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>
github-actions[bot]