Update README

CHANGELOG.md

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

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: 0.48.4
-appVersion: "0.48.4"
+version: 0.48.3
+appVersion: "0.48.3"
 keywords:
   - nextcloud
   - mcp

docker-compose.yml

@@ -21,7 +21,7 @@ services:
     restart: always
 
   app:
-    image: docker.io/library/nextcloud:32.0.2@sha256:8cb1dc8c26944115469dd22f4965d2ed35bab9cf8c48d2bb052c8e9f83821ded
+    image: docker.io/library/nextcloud:32.0.2@sha256:ac08482d73ffd85d94069ba291bbd5fb39a70ff21502030a2e3e2d89a7246a48
     restart: always
     ports:
       - 0.0.0.0:8080:80

nextcloud_mcp_server/providers/openai.py

@@ -7,48 +7,13 @@ Supports:
 """
 
 import logging
-from functools import wraps
 
-import anyio
-from openai import AsyncOpenAI, RateLimitError
+from openai import AsyncOpenAI
 
 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,
@@ -121,7 +86,6 @@ 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.
@@ -187,8 +151,14 @@ class OpenAIProvider(Provider):
         for i in range(0, len(texts), batch_size):
             batch = texts[i : i + batch_size]
 
-            # Use helper method with retry logic for each batch
-            batch_embeddings = await self._embed_batch_request(batch)
+            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]
             all_embeddings.extend(batch_embeddings)
 
             # Update dimension if not set
@@ -201,17 +171,6 @@ 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.
@@ -235,7 +194,6 @@ 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 = "0.48.4"
+version = "0.48.3"
 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 = "0.48.4"
+version = "0.48.3"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },