Update README

chore(deps): update docker/metadata-action digest to c299e40

.github/workflows/docker-build-publish.yml

@@ -16,7 +16,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@318604b99e75e41977312d83839a89be02ca4893 # v5
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # v5
         with:
           # list of Docker images to use as base name for tags
           images: |

.github/workflows/rag-evaluation.yml

@@ -29,16 +29,17 @@ jobs:
       - name: Run docker compose with vector sync
         uses: hoverkraft-tech/compose-action@3846bcd61da338e9eaaf83e7ed0234a12b099b72 # v2.4.1
         with:
-          compose-file: "./docker-compose.yml"
+          compose-file: |
+            ./docker-compose.yml
+            ./docker-compose.ci.yml
           up-flags: "--build"
         env:
-          # Override MCP container environment for OpenAI + vector sync
-          VECTOR_SYNC_ENABLED: "true"
-          VECTOR_SYNC_SCAN_INTERVAL: "5"
+          # Environment variables passed to docker-compose.ci.yml
           OPENAI_API_KEY: ${{ secrets.GITHUB_TOKEN }}
           OPENAI_BASE_URL: "https://models.github.ai/inference"
           OPENAI_EMBEDDING_MODEL: ${{ inputs.embedding_model }}
           OPENAI_GENERATION_MODEL: ${{ inputs.generation_model }}
+          VECTOR_SYNC_SCAN_INTERVAL: "5"
 
       - name: Install the latest version of uv
         uses: astral-sh/setup-uv@1e862dfacbd1d6d858c55d9b792c756523627244 # v7.1.4
@@ -86,11 +87,17 @@ jobs:
           OPENAI_EMBEDDING_MODEL: ${{ inputs.embedding_model }}
           OPENAI_GENERATION_MODEL: ${{ inputs.generation_model }}
         run: |
-          uv run pytest tests/integration/test_rag_openai.py -v --log-cli-level=INFO --provider openai
+          uv run pytest tests/integration/test_rag.py -v --log-cli-level=INFO --provider openai
+
+      - name: Capture MCP container logs
+        if: always()
+        run: |
+          echo "=== MCP Container Logs ==="
+          docker compose logs mcp --tail=500
 
       - name: Upload test results
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: rag-evaluation-results
           path: |

.github/workflows/test.yml

@@ -35,7 +35,7 @@ jobs:
       ###### Required to build OIDC App ######
 
       - name: Set up php 8.4
-        uses: shivammathur/setup-php@bf6b4fbd49ca58e4608c9c89fba0b8d90bd2a39f # v2
+        uses: shivammathur/setup-php@44454db4f0199b8b9685a5d763dc37cbf79108e1 # v2
         with:
           php-version: 8.4
           coverage: none

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:0.9.13@sha256:f07d1bf7b1fb4b983eed2b31320e25a2a76625bdf83d5ff0208fe105d4d8d2f5 /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:0.9.13@sha256:f07d1bf7b1fb4b983eed2b31320e25a2a76625bdf83d5ff0208fe105d4d8d2f5 /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.lock

@@ -1,9 +1,9 @@
 dependencies:
 - name: qdrant
   repository: https://qdrant.github.io/qdrant-helm
-  version: 1.16.0
+  version: 1.16.1
 - name: ollama
   repository: https://otwld.github.io/ollama-helm
   version: 1.35.0
-digest: sha256:da8db198b12ce0252df220fabb297cfe69186edb8e67952c52e05de778189b92
-generated: "2025-11-21T11:09:07.997781541Z"
+digest: sha256:b6889ef1eb8d339cbc046db8b39b0fca5df14aa7db4f800b8486db82e1df9e13
+generated: "2025-11-26T17:04:46.314130537Z"

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
@@ -27,7 +27,7 @@ annotations:
   grafana_dashboard_folder: "Nextcloud MCP"
 dependencies:
   - name: qdrant
-    version: "1.16.0"
+    version: "1.16.1"
     repository: https://qdrant.github.io/qdrant-helm
     condition: qdrant.networkMode.deploySubchart
   - name: ollama

docker-compose.ci.yml

@@ -0,0 +1,25 @@
+# CI-specific overrides for RAG evaluation pipeline
+# This file is used by the rag-evaluation.yml workflow to configure the MCP
+# container with OpenAI/GitHub Models API for vector embeddings.
+#
+# Usage:
+#   docker compose -f docker-compose.yml -f docker-compose.ci.yml up
+#
+# Environment variables (set in CI workflow):
+#   OPENAI_API_KEY - API key for embeddings (GitHub Models uses GITHUB_TOKEN)
+#   OPENAI_BASE_URL - API endpoint (e.g., https://models.github.ai/inference)
+#   OPENAI_EMBEDDING_MODEL - Model name (e.g., openai/text-embedding-3-small)
+#   OPENAI_GENERATION_MODEL - Model name for generation (e.g., openai/gpt-4o-mini)
+
+services:
+  mcp:
+    environment:
+      # OpenAI provider configuration (required for CI vector sync)
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - OPENAI_BASE_URL=${OPENAI_BASE_URL:-https://models.github.ai/inference}
+      - OPENAI_EMBEDDING_MODEL=${OPENAI_EMBEDDING_MODEL:-openai/text-embedding-3-small}
+      - OPENAI_GENERATION_MODEL=${OPENAI_GENERATION_MODEL:-openai/gpt-4o-mini}
+      # Faster sync for CI
+      - VECTOR_SYNC_SCAN_INTERVAL=${VECTOR_SYNC_SCAN_INTERVAL:-5}
+      # Enable document processing for PDF parsing
+      - ENABLE_DOCUMENT_PROCESSING=true

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
@@ -34,7 +34,7 @@ services:
       - ./app-hooks:/docker-entrypoint-hooks.d:ro
       # Mount OIDC development directory outside /var/www/html to avoid rsync conflicts
       # The post-installation hook will register /opt/apps as an additional app directory
-      - ./third_party:/opt/apps:ro
+      #- ./third_party:/opt/apps:ro
     environment:
       - NEXTCLOUD_TRUSTED_DOMAINS=app
       - NEXTCLOUD_ADMIN_USER=admin
@@ -158,7 +158,7 @@ services:
       - oauth-tokens:/app/data
 
   keycloak:
-    image: quay.io/keycloak/keycloak:26.4.5@sha256:653852bfdea2be6e958b9e90a976eff1c6de34edd55f2f679bdc48ef16bc528e
+    image: quay.io/keycloak/keycloak:26.4.6@sha256:d0d4037f17521a7f06137afd5a0eecb1f977f4ade773ae7755f1ee82cad8a576
     command:
       - "start-dev"
       - "--import-realm"
@@ -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" },