
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Marek Zebrowski Blog</title>
      <link>https://zebrowski.dev/blog</link>
      <description>Marek Zebrowski Blog &amp; Book resources</description>
      <language>en-us</language>
      <managingEditor>marek@zebrowski.com (Marek Zebrowski)</managingEditor>
      <webMaster>marek@zebrowski.com (Marek Zebrowski)</webMaster>
      <lastBuildDate>Fri, 05 Apr 2024 05:32:14 GMT</lastBuildDate>
      <atom:link href="https://zebrowski.dev/tags/python/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama-pref</guid>
    <title>Ollama Models via API to Production: Performance and Scaling</title>
    <link>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama-pref</link>
    <description>This follow-up post builds on the previous article about creating a FastAPI wrapper for Ollama models. It explores what’s needed to move from a dev-friendly API to a more production-grade service, including API authentication, rate limiting, request validation, load balancing, and monitoring. FastAPI performance a concern? Read on to find out more!</description>
    <pubDate>Fri, 05 Apr 2024 05:32:14 GMT</pubDate>
    <author>marek@zebrowski.com (Marek Zebrowski)</author>
    <category>blog</category><category>FastAPI</category><category>AI</category><category>Ollama</category><category>Python</category><category>Production</category>
  </item>

  <item>
    <guid>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama-series</guid>
    <title>Ollama Models via API to Production : Series Page</title>
    <link>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama-series</link>
    <description>This series of  follow-up posts builds on the orginal article about creating a FastAPI wrapper for Ollama models. These posts explore what’s needed to move from a dev-friendly API to a more production-grade service, including API authentication, rate limiting, request validation, load balancing, and monitoring. </description>
    <pubDate>Fri, 05 Apr 2024 01:32:14 GMT</pubDate>
    <author>marek@zebrowski.com (Marek Zebrowski)</author>
    <category>blog</category><category>FastAPI</category><category>AI</category><category>Ollama</category><category>Python</category><category>Production</category><category>Series</category>
  </item>

  <item>
    <guid>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama</guid>
    <title>Ollama Models via API</title>
    <link>https://zebrowski.dev/blog/fastapiOllama/fastapi-ollama</link>
    <description>This blog post explains how to use FastAPI to create an API for Ollama models, enabling wider application access and enhanced security. It provides code examples for using ollama.generate() and ollama.chat() and discusses best practices for deployment.</description>
    <pubDate>Tue, 19 Mar 2024 16:32:14 GMT</pubDate>
    <author>marek@zebrowski.com (Marek Zebrowski)</author>
    <category>blog</category><category>FastAPI</category><category>AI</category><category>Ollama</category><category>Python</category>
  </item>

    </channel>
  </rss>
