Delta stream makes structured streaming easy and efficient. The primary use case in mind is handling the streaming of structured outputs of LLMs.
Project description
Delta Stream
Structured streaming made efficient – built for real-time structured LLM output with smart deltas and validation.
✨ Features
- Efficiency – Only triggers an update when new information is added.
- Delta Mode – Dramatically reduces bandwidth by sending only diffs.
- Validation – Powered by Pydantic for safe and structured data integrity.
- Convenience – Define stream-defaults without impacting LLM accuracy.
⚠️ Current Limitations
-
❌ No custom
default_factorysupport
Nested Union models cannot currently define custom default factories. -
⚠️ Delta mode & non-empty string defaults
Avoid setting non-empty string defaults when using delta mode, as this may lead to false "deltas."
📋 Requirements
- Python 3.10+
- pydantic >= 2.0
📄 License
MIT License.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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 delta_stream-0.1.0.tar.gz.
File metadata
- Download URL: delta_stream-0.1.0.tar.gz
- Upload date:
- Size: 17.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.2 CPython/3.12.9 Linux/5.15.167.4-microsoft-standard-WSL2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c9051a85da7db25c37402ebdd437306f9bc19eb3f9c597ff38542c24906a7dd9
|
|
| MD5 |
5feee005e847f04b8442c149eaaa75a0
|
|
| BLAKE2b-256 |
1d058dee22bf98350c2e84c772c23dd803cea27e20422f08b84564b6ee11b494
|
File details
Details for the file delta_stream-0.1.0-py3-none-any.whl.
File metadata
- Download URL: delta_stream-0.1.0-py3-none-any.whl
- Upload date:
- Size: 20.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.2 CPython/3.12.9 Linux/5.15.167.4-microsoft-standard-WSL2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f75b85d1a6f6a869672c78c163811c1cbf6207de179b514b27ddcbe1a705c963
|
|
| MD5 |
9fc8091f6d4eacef45fdf5b24784624e
|
|
| BLAKE2b-256 |
c8c92f4f5f342abc77343fa4e76dd243c660655d17866dcd8e1dbe5502dc2800
|