Build, evaluate and optimize your LLM pipelines to increase accuracy and reduce cost.
pip install superpipe-py
Github
Build multistep pipelines and experiment with parameters like models, prompts, and number of RAG results.
from superpipe import grid_search
params_grid = {
short_description_step.name: {
'model': [models.gpt35, models.gpt4],
},
embedding_search_step.name: {
'k': [3, 5, 7],
},
categorize_step.name: {
'prompt': [simple_prompt, advanced_prompt],
},
}
search_embeddings = grid_search.GridSearch(categorizer, params_grid)
search_embeddings.run(df)
Dataset management
Build golden sets with easy ground-truth labeling tools
Experimentation
Compare experiments across cost, speed, and accuracy
Observability
Observe pipelines and deep dive into logs
Tag and categorize data from product taxonomies to social comments
Backed by
Does this replace my BPO team?
It's possible! You may still want manual review if you need 100% accuracy.
Does Superpipe require engineering recources?
We'll build you a custom tool that and help you deploy it on your own infrastructure, no engineering required.
What if my data is private?
We can deploy Superpipe on your infrastructure. We'll never see or have access to your data.
© Stelo Labs, Inc. 2024
Privacy
Terms