You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have noticed that in the code, the project restricts the use of OpenAI parallel tool calls. Specifically, when using the OpenAI function calling, the agent can only make one function call at a time. Could you please provide some insight into the reason behind this restriction?
Thank you for your time and assistance.
The text was updated successfully, but these errors were encountered:
Thank you for your question. In fact, the function calling feature was in the end not used in the AutoCodeRover default workflow (the stratified search mode). Instead, when we want the model to make context retrieval API call(s), we made it respond with natural language and then extract the structured API calls in another prompt. We found that in this way the model can make better selection on the context retrieval APIs, compared to using the function calling feature.
Hello,
I have noticed that in the code, the project restricts the use of OpenAI parallel tool calls. Specifically, when using the OpenAI function calling, the agent can only make one function call at a time. Could you please provide some insight into the reason behind this restriction?
Thank you for your time and assistance.
The text was updated successfully, but these errors were encountered: