Update README

chore(deps): update ghcr.io/astral-sh/uv docker tag to v0.9.12

CHANGELOG.md

@@ -1,3 +1,9 @@
+## v0.48.4 (2025-11-23)
+
+### Fix
+
+- Add rate limit retry logic to OpenAI provider
+
 ## v0.48.3 (2025-11-23)
 
 ### Fix

Dockerfile

@@ -1,6 +1,6 @@
 FROM docker.io/library/python:3.12-slim-trixie@sha256:b43ff04d5df04ad5cabb80890b7ef74e8410e3395b19af970dcd52d7a4bff921
 
-COPY --from=ghcr.io/astral-sh/uv:0.9.11@sha256:5aa820129de0a600924f166aec9cb51613b15b68f1dcd2a02f31a500d2ede568 /uv /uvx /bin/
+COPY --from=ghcr.io/astral-sh/uv:0.9.12@sha256:0eaa66c625730a3b13eb0b7bfbe085ed924b5dca6240b6f0632b4256cfb53f31 /uv /uvx /bin/
 
 # Install dependencies
 # 1. git (required for caldav dependency from git)

Dockerfile.smithery

@@ -17,7 +17,7 @@ FROM docker.io/library/python:3.12-slim-trixie@sha256:b43ff04d5df04ad5cabb80890b
 WORKDIR /app
 
 # Install uv for fast dependency management
-COPY --from=ghcr.io/astral-sh/uv:0.9.11@sha256:5aa820129de0a600924f166aec9cb51613b15b68f1dcd2a02f31a500d2ede568 /uv /uvx /bin/
+COPY --from=ghcr.io/astral-sh/uv:0.9.12@sha256:0eaa66c625730a3b13eb0b7bfbe085ed924b5dca6240b6f0632b4256cfb53f31 /uv /uvx /bin/
 
 # Install dependencies
 # 1. git (required for caldav dependency from git)

README.md

@@ -1,11 +1,12 @@
+```markdown
 <p align="center">
   <img src="astrolabe.svg" alt="Nextcloud MCP Server" width="128" height="128">
 </p>
 
 # Nextcloud MCP Server
 
-[![Docker Image](https://img.shields.io/badge/docker-ghcr.io/cbcoutinho/nextcloud--mcp--server-blue)](https://github.com/cbcoutinho/nextcloud-mcp-server/pkgs/container/nextcloud-mcp-server)
 [![smithery badge](https://smithery.ai/badge/@cbcoutinho/nextcloud-mcp-server)](https://smithery.ai/server/@cbcoutinho/nextcloud-mcp-server)
+[![Docker Image](https://img.shields.io/badge/docker-ghcr.io/cbcoutinho/nextcloud--mcp--server-blue)](https://github.com/cbcoutinho/nextcloud-mcp-server/pkgs/container/nextcloud-mcp-server)
 
 **A production-ready MCP server that connects AI assistants to your Nextcloud instance.**
 
@@ -223,3 +224,4 @@ This project is licensed under the AGPL-3.0 License. See [LICENSE](./LICENSE) fo
 - [Model Context Protocol](https://github.com/modelcontextprotocol)
 - [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)
 - [Nextcloud](https://nextcloud.com/)
+```

charts/nextcloud-mcp-server/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: nextcloud-mcp-server
 description: A Helm chart for Nextcloud MCP Server - enables AI assistants to interact with Nextcloud
 type: application
-version: 0.48.3
-appVersion: "0.48.3"
+version: 0.48.4
+appVersion: "0.48.4"
 keywords:
   - nextcloud
   - mcp

docker-compose.yml

@@ -21,7 +21,7 @@ services:
     restart: always
 
   app:
-    image: docker.io/library/nextcloud:32.0.2@sha256:ac08482d73ffd85d94069ba291bbd5fb39a70ff21502030a2e3e2d89a7246a48
+    image: docker.io/library/nextcloud:32.0.2@sha256:8cb1dc8c26944115469dd22f4965d2ed35bab9cf8c48d2bb052c8e9f83821ded
     restart: always
     ports:
       - 0.0.0.0:8080:80
@@ -245,7 +245,7 @@ services:
       - smithery
 
   qdrant:
-    image: qdrant/qdrant:v1.16.0@sha256:1005201498cf927d835383d0f918b17d8c9da7db58550f169f694455e42d78f4
+    image: qdrant/qdrant:v1.16.1@sha256:db1c735496dfa982ef27576a17b624e48e6b46a140bcdc2ac34e39d186204ef5
     restart: always
     ports:
       - 127.0.0.1:6333:6333  # REST API

nextcloud_mcp_server/providers/openai.py

@@ -7,13 +7,48 @@ Supports:
 """
 
 import logging
+from functools import wraps
 
-from openai import AsyncOpenAI
+import anyio
+from openai import AsyncOpenAI, RateLimitError
 
 from .base import Provider
 
 logger = logging.getLogger(__name__)
 
+# Rate limit retry configuration
+MAX_RETRIES = 5
+INITIAL_RETRY_DELAY = 2.0  # seconds
+MAX_RETRY_DELAY = 60.0  # seconds
+
+
+def retry_on_rate_limit(func):
+    """Decorator to retry on OpenAI rate limit errors with exponential backoff."""
+
+    @wraps(func)
+    async def wrapper(*args, **kwargs):
+        retry_delay = INITIAL_RETRY_DELAY
+        last_error: Exception | None = None
+
+        for attempt in range(1, MAX_RETRIES + 1):
+            try:
+                return await func(*args, **kwargs)
+            except RateLimitError as e:
+                last_error = e
+                if attempt < MAX_RETRIES:
+                    logger.warning(
+                        f"Rate limit hit (attempt {attempt}/{MAX_RETRIES}), "
+                        f"retrying in {retry_delay:.1f}s..."
+                    )
+                    await anyio.sleep(retry_delay)
+                    retry_delay = min(retry_delay * 2, MAX_RETRY_DELAY)
+
+        logger.error(f"Rate limit exceeded after {MAX_RETRIES} attempts")
+        raise last_error  # type: ignore[misc]
+
+    return wrapper
+
+
 # Well-known embedding dimensions for OpenAI models
 OPENAI_EMBEDDING_DIMENSIONS: dict[str, int] = {
     "text-embedding-3-small": 1536,
@@ -86,6 +121,7 @@ class OpenAIProvider(Provider):
         """Whether this provider supports text generation."""
         return self.generation_model is not None
 
+    @retry_on_rate_limit
     async def embed(self, text: str) -> list[float]:
         """
         Generate embedding vector for text.
@@ -151,14 +187,8 @@ class OpenAIProvider(Provider):
         for i in range(0, len(texts), batch_size):
             batch = texts[i : i + batch_size]
 
-            response = await self.client.embeddings.create(
-                input=batch,
-                model=self.embedding_model,
-            )
-
-            # Sort by index to maintain order
-            sorted_data = sorted(response.data, key=lambda x: x.index)
-            batch_embeddings = [item.embedding for item in sorted_data]
+            # Use helper method with retry logic for each batch
+            batch_embeddings = await self._embed_batch_request(batch)
             all_embeddings.extend(batch_embeddings)
 
             # Update dimension if not set
@@ -171,6 +201,17 @@ class OpenAIProvider(Provider):
 
         return all_embeddings
 
+    @retry_on_rate_limit
+    async def _embed_batch_request(self, batch: list[str]) -> list[list[float]]:
+        """Make a single batch embedding request with retry logic."""
+        response = await self.client.embeddings.create(
+            input=batch,
+            model=self.embedding_model,
+        )
+        # Sort by index to maintain order
+        sorted_data = sorted(response.data, key=lambda x: x.index)
+        return [item.embedding for item in sorted_data]
+
     def get_dimension(self) -> int:
         """
         Get embedding dimension.
@@ -194,6 +235,7 @@ class OpenAIProvider(Provider):
             )
         return self._dimension
 
+    @retry_on_rate_limit
     async def generate(self, prompt: str, max_tokens: int = 500) -> str:
         """
         Generate text from a prompt.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nextcloud-mcp-server"
-version = "0.48.3"
+version = "0.48.4"
 description = "Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data"
 authors = [
     {name = "Chris Coutinho", email = "chris@coutinho.io"}

uv.lock

@@ -1936,7 +1936,7 @@ wheels = [
 
 [[package]]
 name = "nextcloud-mcp-server"
-version = "0.48.3"
+version = "0.48.4"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },