Small and Mighty Conversational Agent Framework
This is an experimental project to develop next generation of conversational agents that can connect the world of unconstrained generation of Large Language Models (LLM) to the world of structured data sources. Our goal is to build a modular and configurable framework to seamlessly integrate language agents with data sources to build conversational experiences for next generation of digital systems.
THIS PROJECT IS IN ACTIVE DEVELOPMENT. PROCEED WITH CAUTION!
The Big Idea about Small Things
To achieve our goals, we are pursuing two fundamental ideas:
- Sequence to structure: Convert sequence to sequence models to sequence to structure extraction ones. This is about extracting the structure of information required to properly fulfill a user request from her natural language utterances.
- Structure Informed Generation: Generate responses that combine both unstructured and structured information.
Copyright © 2023 Weavers @ Eternal Loom. All rights reserved.
1 maintainer
Release files for smighty 0.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| smighty-0.0.3.tar.gz | 18.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| smighty-0.0.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size:50.9 kB
Release files / smighty-0.0.3.tar.gz
| Download URL | smighty-0.0.3.tar.gz |
|---|---|
| Size | 18.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f7eb422668a0b7519dc746f775351e03f96b48dab5236393c69cc0660b8eae88
|
|
BLAKE2b-256 checksum How to use checksums |
b0b0e9052005d94dd8d80a06c488fde7bc35447f304ae1131fabe919aedf8639
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.10.9 Darwin/23.1.0
|
Release files / smighty-0.0.3-py3-none-any.whl
| Download URL | smighty-0.0.3-py3-none-any.whl |
|---|---|
| Size | 32.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
75c3db60095ae71f1073ed2f70ae6cac4f571459af3a17181ee71c9e3e492657
|
|
BLAKE2b-256 checksum How to use checksums |
3ec7d444c5cbaf602b2a6b1e6426f80e960f0dcc60bb1f7f23fbf6d5c04f57a2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.10.9 Darwin/23.1.0
|
