openaivec 1.0.2__tar.gz → 1.0.4__tar.gz

{openaivec-1.0.2 → openaivec-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openaivec
-Version: 1.0.2
+Version: 1.0.4
 Summary: Generative mutation for tabular calculation
 Project-URL: Homepage, https://microsoft.github.io/openaivec/
 Project-URL: Repository, https://github.com/microsoft/openaivec
@@ -64,6 +64,20 @@ print(sentiment.tolist())
 
 **Try it live:** https://microsoft.github.io/openaivec/examples/pandas/
 
+## Benchmarks
+
+Simple task benchmark from [benchmark.ipynb](https://github.com/microsoft/openaivec/blob/main/docs/examples/benchmark.ipynb) (100 numeric strings → integer literals, `Series.aio.responses`, model `gpt-5.1`):
+
+| Mode                | Settings                                        | Time (s) |
+| ------------------- | ----------------------------------------------- | -------- |
+| Serial              | `batch_size=1`, `max_concurrency=1`             | ~141     |
+| Batching            | default `batch_size`, `max_concurrency=1`       | ~15      |
+| Concurrent batching | default `batch_size`, default `max_concurrency` | ~6       |
+
+Batching alone removes most HTTP overhead, and letting batching overlap with concurrency cuts total runtime to a few seconds while still yielding one output per input.
+
+<img alt="image" src="https://github.com/user-attachments/assets/8ace9bcd-bcae-4023-a37e-13082cd645e5" />
+
 ## Contents
 
 - [Why openaivec?](#why-openaivec)

{openaivec-1.0.2 → openaivec-1.0.4}/README.md

@@ -38,6 +38,20 @@ print(sentiment.tolist())
 
 **Try it live:** https://microsoft.github.io/openaivec/examples/pandas/
 
+## Benchmarks
+
+Simple task benchmark from [benchmark.ipynb](https://github.com/microsoft/openaivec/blob/main/docs/examples/benchmark.ipynb) (100 numeric strings → integer literals, `Series.aio.responses`, model `gpt-5.1`):
+
+| Mode                | Settings                                        | Time (s) |
+| ------------------- | ----------------------------------------------- | -------- |
+| Serial              | `batch_size=1`, `max_concurrency=1`             | ~141     |
+| Batching            | default `batch_size`, `max_concurrency=1`       | ~15      |
+| Concurrent batching | default `batch_size`, default `max_concurrency` | ~6       |
+
+Batching alone removes most HTTP overhead, and letting batching overlap with concurrency cuts total runtime to a few seconds while still yielding one output per input.
+
+<img alt="image" src="https://github.com/user-attachments/assets/8ace9bcd-bcae-4023-a37e-13082cd645e5" />
+
 ## Contents
 
 - [Why openaivec?](#why-openaivec)

{openaivec-1.0.2 → openaivec-1.0.4}/mkdocs.yml

@@ -63,6 +63,7 @@ nav:
       - Prompt Engineering: examples/prompt.ipynb
       - FAQ Generation: examples/generate_faq.ipynb
       - Token Count and Processing Time: examples/batch_size.ipynb
+      - Request Batching Benchmark: examples/benchmark.ipynb
   - API Reference:
       - Main Package: api/main.md
       - pandas_ext: api/pandas_ext.md
@@ -121,7 +122,7 @@ extra:
     - icon: fontawesome/brands/python
       link: https://pypi.org/project/openaivec/
     - icon: fontawesome/brands/discord
-      link: https://discord.gg/vbb83Pgn
+      link: https://discord.gg/hXCS9J6Qek
 
 plugins:
   - search: