Browse Bot Version 2.0 #18
Open
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
- Migrate to the Vercel AI SDK for streaming responses. - Implement tool calling with user confirmation. - Update message handling to support string or array content. - Improve error handling and message persistence.
- Add build step with npm to bundle the project using Vercel AI SDK - Document technologies used: Vercel AI SDK and Zod - Update import path to the bundled file `browse-bot.uc.js`
- Add detailed debug logs for LLM interactions, including system prompt, history, model details, tool calls, stream chunks, and errors. - Improve visibility into LLM behavior for debugging and troubleshooting.
- Refactor sendMessage to handle streaming and citations separately - Add citation support via generateObject with schema validation - Update UI to display citations and handle historical messages
- Add chokidar-cli for file watching during development - Update build script to include a `dev` script for watching file changes and rebuild
- Implemented streaming message responses from the LLM, improving UI responsiveness. - Added a "Stop Generation" button to allow users to abort ongoing streaming requests. - Refactored message sending to handle both streaming and non-streaming modes with a unified try/catch/finally structure. - Added abort signal to LLM sendMessage calls.
- Move Gemini and Mistral providers to a single "providers.js" file - Remove individual provider files for better organization
- Update available models for Mistral and Gemini providers - Add new Mistral and Gemini models with their labels
- Adds OpenAI, Claude, Grok, Perplexity, and Ollama providers - Updates preferences and provider handling
- Remove redundant getters/setters in PREFS - Use PREFS.getPref/setPref in LLM provider files
- Use provider prototype to share logic - Apply prototype to each provider object
- Update Ollama model list and add descriptive labels for each model.
- Refactors findbar-ai.uc.js to use `export const` for `browseBotFindbar` - Updates references to `browserBotfindbar` to use `browseBotFindbar` throughout the project
- Add Claude, Grok, and Perplexity AI as LLM providers - Update model options for Gemini and Mistral - Add API key settings for Claude, Grok and Perplexity
…y time i change branches)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Todos:
generateObjectfor citation (less chance of error due to schema validation).Bugs: