FloTorch Version
v3.0.1
Bug Description
In the Cost Breakdown section of the experiment the Input Tokens and Output Tokens fields are always showing a value of 0, even after successful model inference and response generation.
Steps to Reproduce
Steps to Reproduce
Login to FloTorch.ai
Click on Get Started button
click on Create Project
Enter the Project Name, select the region
Navigate to the Knowledge Bases selection section.
Select an AWS Bedrock Knowledge Base for embedding.Click on Next
Select the N shot prompt and attach the N shot prompt file
Select the KNN value
Select the any of the inferencing models
Select the inferencing model temperature
Click on Next button
Select the Ragas evaluation, embedding model and Inferencing model
Click on Submit
Expected Behavior
Token counts should reflect the actual number of input and output tokens used during the model interaction for accurate cost reporting
Actual Behavior
Both Input Tokens and Output Tokens consistently display as 0, regardless of the length or content of the prompt and response.
Browser and Version
135.0.7049.115
Runtime Version
3.12
Error Messages
Additional Context
No response
FloTorch Version
v3.0.1
Bug Description
In the Cost Breakdown section of the experiment the Input Tokens and Output Tokens fields are always showing a value of 0, even after successful model inference and response generation.
Steps to Reproduce
Steps to Reproduce
Login to FloTorch.ai
Click on Get Started button
click on Create Project
Enter the Project Name, select the region
Navigate to the Knowledge Bases selection section.
Select an AWS Bedrock Knowledge Base for embedding.Click on Next
Select the N shot prompt and attach the N shot prompt file
Select the KNN value
Select the any of the inferencing models
Select the inferencing model temperature
Click on Next button
Select the Ragas evaluation, embedding model and Inferencing model
Click on Submit
Expected Behavior
Token counts should reflect the actual number of input and output tokens used during the model interaction for accurate cost reporting
Actual Behavior
Both Input Tokens and Output Tokens consistently display as 0, regardless of the length or content of the prompt and response.
Browser and Version
135.0.7049.115
Runtime Version
3.12
Error Messages
Additional Context
No response