feat:core:#95

[louis030195]

Description

Core step towards

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .search(question, max_token=3000, ratio=[.7, .1, .1, .1])
)

Related Issue

#95

Type of Change

• 📚 Examples / docs / tutorials / dependencies update
• 🔧 Bug fix (non-breaking change which fixes an issue)
• 🥂 Improvement (non-breaking change which improves an existing feature)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to change)
• 🔐 Security fix

Checklist

• I've read the CODE_OF_CONDUCT.md document.
• I've read the CONTRIBUTING.md guide.

• I've written tests for all new methods and classes that I created.
• I've written the docstring in Google format for all the methods and classes that I used.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
embedbase	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 15, 2023 2:51pm
embedbase-docs	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 15, 2023 2:51pm

[louis030195]

@hotkartoffel happy to receive feedback on how to best handle duplicate in this

example use case in tests:

Should we filter duplicate now or in a later version? (i.e. when the same data is present across multiple datasets of the same user)

[louis030195]

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .search(question, max_token=3000, ratio=[.7, .1, .1, .1])
)

or

results = (
  await embedbase
  .dataset(recipe_id)
  .dataset(farm_id)
  .dataset(user_id)
  .dataset(locaton_id)
  .search(question)
  .limit(max_token=3000)
  .ratio([.7, .1, .1, .1])
)

or

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .search(question)
  .limit(max_token=3000)
  .ratio([.7, .1, .1, .1])
)

or

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .search(question)
  .limit(max_token=3000, ratio=[.7, .1, .1, .1])
)

or

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .create_context(question, max_token=3000, ratio=[.7, .1, .1, .1])
)

or

results = (
  await embedbase
  .dataset(recipe_id, farm_id, user_id, locaton_id)
  .search(question, max_token=3000, ratio=[.7, .1, .1, .1])
  .get()
)

or something else? (ask same for TS)

[louis030195]

imho should optimise UX for:

• least amount of string
• functional approach
• while maintaining all degrees of freedom (the right abstraction)

[ccomkhj]

Looking forward to this update! @louis030195