Sign InShare Feedback and Report Bugs
Broker Experience Feedback
Please share your experience and suggestions about:
- Broker connections
- Data synchronization
- Order placement
Please include the broker name and details of what you're experiencing.
HappyHappyHappy
HappyHappyHappy
John
Feedbacktesttesttest
testtesttesttest
JohnFeedbackMemory system
Either approach could work, but from an automation perspective, the simplest would probably be passing a list of files directly with the chat request, and having those files automatically appended to the prompt (similar to how it works in the Venice Chat web app). That avoids extra steps like separate upload calls and managing file_ids, which would be harder to automate when working with dynamic content.Right now I use placeholders in my prompts (like %%filename%%) and have my script load the file content and insert it before sending the API request. Having to manage file_ids would add extra complexity compared to this flow — just passing a list of files with the request would cleanly replace what I’m doing today.Possible approaches I can see: File Upload API — a separate upload call returning file_ids (though a bit more complex for automation). Automatic file embedding — files passed directly with chat request and auto-appended behind the scenes. Tool-based — where a file reader tool could be invoked during conversation.For my use case (batch automation and dynamic workflows), the simplest would be letting me pass a list of files along with the chat request and having those embedded automatically.
JohnFeedbackReconsider new models
Similar to how Open ai have their memory with ChatGPT, where you can store data that the AI can remember across different chats, and also it can reinforce memory of a current chat.
JohnFeedbackTitle of Post
Description of Post, please descibe the detail info
JohnFeedback
