Product Advisor and selection matching components for AI-Parrot
Project description
AI-Parrot Advisors
Async-first Product Advisor and selection matching components for AI-Parrot.
Features
- ProductCatalog: Hybrid search (semantic + structured) for product matching.
- ProductAdvisorMixin: Easily add recommendation capabilities to any Agent.
- QuestionGenerator: Automatically generate discriminant questions to narrow down selections.
- SelectionStateManager: Managed selection state with Redis persistence and Undo/Redo support.
Installation
pip install ai-parrot-advisors
Usage
Inherit from ProductAdvisorMixin to give your agent advisor powers:
from parrot.advisors import ProductAdvisorMixin
from parrot.bots import Agent
class ShoppingAgent(ProductAdvisorMixin, Agent):
async def configure(self):
await super().configure()
await self.configure_advisor()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ai_parrot_advisors-0.1.0.tar.gz
(66.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ai_parrot_advisors-0.1.0.tar.gz.
File metadata
- Download URL: ai_parrot_advisors-0.1.0.tar.gz
- Upload date:
- Size: 66.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e0ace17470b4328541eb1ffbea436fc2be43fc6af84511e67782cd0b762d5433
|
|
| MD5 |
dad1c37ffac0023f8eecb039657db921
|
|
| BLAKE2b-256 |
8b7a7815e0ec3afc08213e725fa872f4904ebbe19e4a68eaf10b830dd68e047e
|
File details
Details for the file ai_parrot_advisors-0.1.0-py3-none-any.whl.
File metadata
- Download URL: ai_parrot_advisors-0.1.0-py3-none-any.whl
- Upload date:
- Size: 77.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
54056219a3da06a1409f9865683f1a2336d81d8d3d8d0d78eb9ca6f64d3f189f
|
|
| MD5 |
0cbfbbf82879b12e927c4e6760b9bd97
|
|
| BLAKE2b-256 |
443164b4dc8b56e4f3372cde7dcee613b2735dc6dca0bd679bd6635af95a564d
|