openaivec 1.0.6__tar.gz → 1.0.8__tar.gz

{openaivec-1.0.6 → openaivec-1.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openaivec
-Version: 1.0.6
+Version: 1.0.8
 Summary: Generative mutation for tabular calculation
 Project-URL: Homepage, https://microsoft.github.io/openaivec/
 Project-URL: Repository, https://github.com/microsoft/openaivec
@@ -26,7 +26,7 @@ Description-Content-Type: text/markdown
 
 # openaivec
 
-Transform pandas and Spark workflows with AI-powered text processing—batching, caching, and guardrails included.
+Transform pandas and Spark workflows with AI-powered text processing—batching, caching, and guardrails included. Built for OpenAI batch pipelines so you can group prompts, cut API overhead, and keep outputs aligned with your data.
 
 [Contributor guidelines](AGENTS.md)
 
@@ -92,6 +92,7 @@ Batching alone removes most HTTP overhead, and letting batching overlap with con
 ## Why openaivec?
 
 - Drop-in `.ai` and `.aio` accessors keep pandas analysts in familiar tooling.
+- OpenAI batch-optimized: `BatchingMapProxy`/`AsyncBatchingMapProxy` coalesce requests, dedupe prompts, and keep column order stable.
 - Smart batching (`BatchingMapProxy`/`AsyncBatchingMapProxy`) dedupes prompts, preserves order, and releases waiters on failure.
 - Reasoning support mirrors the OpenAI SDK; structured outputs accept Pydantic `response_format`.
 - Built-in caches and retries remove boilerplate; helpers reuse caches across pandas, Spark, and async flows.
@@ -100,7 +101,7 @@ Batching alone removes most HTTP overhead, and letting batching overlap with con
 
 # Overview
 
-Vectorized OpenAI access so you process many inputs per call instead of one-by-one. Batching proxies dedupe inputs, enforce ordered outputs, and unblock waiters even on upstream errors. Cache helpers (`responses_with_cache`, Spark UDF builders) plug into the same layer so expensive prompts are reused across pandas, Spark, and async flows. Reasoning models honor SDK semantics. Requires Python 3.10+.
+Vectorized OpenAI batch processing so you handle many inputs per call instead of one-by-one. Batching proxies dedupe inputs, enforce ordered outputs, and unblock waiters even on upstream errors. Cache helpers (`responses_with_cache`, Spark UDF builders) plug into the same layer so expensive prompts are reused across pandas, Spark, and async flows. Reasoning models honor SDK semantics. Requires Python 3.10+.
 
 ## Core Workflows
 

{openaivec-1.0.6 → openaivec-1.0.8}/README.md

@@ -1,6 +1,6 @@
 # openaivec
 
-Transform pandas and Spark workflows with AI-powered text processing—batching, caching, and guardrails included.
+Transform pandas and Spark workflows with AI-powered text processing—batching, caching, and guardrails included. Built for OpenAI batch pipelines so you can group prompts, cut API overhead, and keep outputs aligned with your data.
 
 [Contributor guidelines](AGENTS.md)
 
@@ -66,6 +66,7 @@ Batching alone removes most HTTP overhead, and letting batching overlap with con
 ## Why openaivec?
 
 - Drop-in `.ai` and `.aio` accessors keep pandas analysts in familiar tooling.
+- OpenAI batch-optimized: `BatchingMapProxy`/`AsyncBatchingMapProxy` coalesce requests, dedupe prompts, and keep column order stable.
 - Smart batching (`BatchingMapProxy`/`AsyncBatchingMapProxy`) dedupes prompts, preserves order, and releases waiters on failure.
 - Reasoning support mirrors the OpenAI SDK; structured outputs accept Pydantic `response_format`.
 - Built-in caches and retries remove boilerplate; helpers reuse caches across pandas, Spark, and async flows.
@@ -74,7 +75,7 @@ Batching alone removes most HTTP overhead, and letting batching overlap with con
 
 # Overview
 
-Vectorized OpenAI access so you process many inputs per call instead of one-by-one. Batching proxies dedupe inputs, enforce ordered outputs, and unblock waiters even on upstream errors. Cache helpers (`responses_with_cache`, Spark UDF builders) plug into the same layer so expensive prompts are reused across pandas, Spark, and async flows. Reasoning models honor SDK semantics. Requires Python 3.10+.
+Vectorized OpenAI batch processing so you handle many inputs per call instead of one-by-one. Batching proxies dedupe inputs, enforce ordered outputs, and unblock waiters even on upstream errors. Cache helpers (`responses_with_cache`, Spark UDF builders) plug into the same layer so expensive prompts are reused across pandas, Spark, and async flows. Reasoning models honor SDK semantics. Requires Python 3.10+.
 
 ## Core Workflows
 

{openaivec-1.0.6 → openaivec-1.0.8}/docs/index.md

@@ -1,6 +1,10 @@
-# AI-Powered Data Processing for Pandas & Spark
+---
+title: OpenAI Batch Processing for Pandas & Spark
+---
 
-Welcome to **openaivec** - Transform your data analysis with OpenAI's language models! This library enables seamless integration of AI text processing, sentiment analysis, NLP tasks, and embeddings into your [**Pandas**](https://pandas.pydata.org/) DataFrames and [**Apache Spark**](https://spark.apache.org/) workflows for scalable data insights.
+# OpenAI Batch Processing for Pandas & Spark
+
+Welcome to **openaivec** - Transform your data analysis with OpenAI's language models and batch-first pipelines! This library enables seamless integration of AI text processing, sentiment analysis, NLP tasks, and embeddings into your [**Pandas**](https://pandas.pydata.org/) DataFrames and [**Apache Spark**](https://spark.apache.org/) workflows for scalable data insights, while automatically handling OpenAI batch orchestration.
 
 ## 🚀 Quick Start Example
 
@@ -41,6 +45,7 @@ Perfect for **data scientists**, **analysts**, and **ML engineers** who want to
 
 - **🚀 Vectorized Processing**: Handle thousands of records in minutes, not hours
 - **⚡ Asynchronous Interface**: `.aio` accessor with `batch_size` and `max_concurrency` control
+- **📦 OpenAI Batch Friendly**: `BatchingMapProxy` groups prompts, dedupes inputs, and keeps outputs aligned for pandas and Spark
 - **💰 Cost Efficient**: Automatic deduplication significantly reduces API costs
 - **🔗 Seamless Integration**: Works within existing pandas/Spark workflows
 - **📈 Enterprise Scale**: From 100s to millions of records

openaivec-1.0.8/docs/overrides/main.html

@@ -0,0 +1,10 @@
+{% extends "base.html" %}
+
+{% block extrahead %}
+  {{ super() }}
+  {%- set site_meta = config.extra.get("meta", []) -%}
+  {%- set page_meta = page.meta.get("meta", []) if page and page.meta else [] -%}
+  {%- for meta in site_meta + page_meta %}
+    <meta{% for attr, value in meta.items() %} {{ attr }}="{{ value }}"{% endfor %}>
+  {%- endfor %}
+{% endblock %}

{openaivec-1.0.6 → openaivec-1.0.8}/mkdocs.yml

@@ -8,6 +8,7 @@ edit_uri: edit/main/docs/
 theme:
   name: material
   language: en
+  custom_dir: docs/overrides
   palette:
     # Palette toggle for light mode
     - media: "(prefers-color-scheme: light)"
@@ -116,6 +117,9 @@ extra:
   analytics:
     provider: google
     property: G-ZZ7FDHLKYS
+  meta:
+    - name: google-site-verification
+      content: UZhByQkwHoP8ke9kNHhrVrXNM_nnHFGd6ycOKKcBRcs
   social:
     - icon: fontawesome/brands/github
       link: https://github.com/microsoft/openaivec