Update README

2025-11-23 04:46:16 +00:00
8 changed files with 21 additions and 101 deletions
@@ -29,17 +29,16 @@ jobs:
      - name: Run docker compose with vector sync
        uses: hoverkraft-tech/compose-action@3846bcd61da338e9eaaf83e7ed0234a12b099b72 # v2.4.1
        with:
-          compose-file: |
-            ./docker-compose.yml
-            ./docker-compose.ci.yml
+          compose-file: "./docker-compose.yml"
          up-flags: "--build"
        env:
-          # Environment variables passed to docker-compose.ci.yml
+          # Override MCP container environment for OpenAI + vector sync
+          VECTOR_SYNC_ENABLED: "true"
+          VECTOR_SYNC_SCAN_INTERVAL: "5"
          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
@@ -87,17 +86,11 @@ jobs:
          OPENAI_EMBEDDING_MODEL: ${{ inputs.embedding_model }}
          OPENAI_GENERATION_MODEL: ${{ inputs.generation_model }}
        run: |
-          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
+          uv run pytest tests/integration/test_rag_openai.py -v --log-cli-level=INFO --provider openai

      - name: Upload test results
        if: always()
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
+        uses: actions/upload-artifact@v4
        with:
          name: rag-evaluation-results
          path: |
@@ -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
@@ -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
@@ -1,25 +0,0 @@
-# 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
@@ -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
@@ -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
@@ -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.
@@ -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"}
@@ -1936,7 +1936,7 @@ wheels = [

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