Files
nextcloud-mcp-server/tests/rag_evaluation/llm_providers.py
T
Chris Coutinho 5b484c9226 feat: add unified provider architecture with Amazon Bedrock support
Refactored LLM provider infrastructure to support sustainable additions of new providers with both embedding and text generation capabilities.

## Major Changes

### Unified Provider Architecture (ADR-015)
- Created `nextcloud_mcp_server/providers/` with unified Provider ABC
- Providers now support optional capabilities (embeddings and/or generation)
- Auto-detection registry with priority: Bedrock → Ollama → Simple
- Backward compatible - existing code continues to work

### New Providers
- **BedrockProvider**: Full Amazon Bedrock integration
  - Embeddings: Titan Embed, Cohere Embed models
  - Generation: Claude, Llama, Titan Text, Mistral models
  - Model-specific request/response handling
  - AWS credential chain integration
- **OllamaProvider**: Migrated with both capabilities support
- **AnthropicProvider**: Moved from test code to production providers
- **SimpleProvider**: Migrated in-memory fallback provider

### Breaking Changes
None - full backward compatibility maintained:
- `embedding.get_embedding_service()` still works
- RAG evaluation tests updated to use unified providers
- All existing tests pass (127 unit tests)

### Testing
- Added 9 comprehensive Bedrock unit tests with mocked boto3
- All existing unit tests pass
- Type checking (ty) and linting (ruff) pass
- Verified backward compatibility

### Documentation
- `docs/ADR-015-unified-provider-architecture.md`: Comprehensive ADR
- `docs/bedrock-setup.md`: AWS setup guide with IAM permissions
- `CLAUDE.md`: Updated with provider architecture section

### Dependencies
- Added `boto3>=1.35.0` to dev dependencies (optional)

## Environment Variables

### Bedrock
- `AWS_REGION`: AWS region (e.g., "us-east-1")
- `BEDROCK_EMBEDDING_MODEL`: Model ID for embeddings
- `BEDROCK_GENERATION_MODEL`: Model ID for generation
- `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`: Optional credentials

### Ollama
- `OLLAMA_BASE_URL`: API URL
- `OLLAMA_EMBEDDING_MODEL`: Embedding model (default: "nomic-embed-text")
- `OLLAMA_GENERATION_MODEL`: Generation model

## AWS Bedrock Permissions Required

Minimal IAM policy:
```json
{
  "Effect": "Allow",
  "Action": ["bedrock:InvokeModel"],
  "Resource": ["arn:aws:bedrock:*::foundation-model/*"]
}
```

See `docs/bedrock-setup.md` for detailed setup instructions.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-16 11:36:58 +01:00

90 lines
3.3 KiB
Python

"""LLM provider abstraction for RAG evaluation.
DEPRECATED: This module is maintained for backward compatibility with RAG evaluation tests.
New code should use nextcloud_mcp_server.providers directly.
Supports Ollama (local), Anthropic (cloud), and Bedrock (AWS) providers for both ground truth
generation and evaluation.
"""
import os
from nextcloud_mcp_server.providers import (
AnthropicProvider,
BedrockProvider,
OllamaProvider,
Provider,
)
def create_llm_provider(
provider: str | None = None,
ollama_base_url: str | None = None,
ollama_model: str | None = None,
anthropic_api_key: str | None = None,
anthropic_model: str | None = None,
bedrock_region: str | None = None,
bedrock_model: str | None = None,
) -> Provider:
"""Create an LLM provider from environment variables or arguments.
Args:
provider: Provider type ('ollama', 'anthropic', or 'bedrock').
Defaults to RAG_EVAL_PROVIDER env var or 'ollama'
ollama_base_url: Ollama base URL. Defaults to RAG_EVAL_OLLAMA_BASE_URL or 'http://localhost:11434'
ollama_model: Ollama model. Defaults to RAG_EVAL_OLLAMA_MODEL or 'llama3.2:1b'
anthropic_api_key: Anthropic API key. Defaults to RAG_EVAL_ANTHROPIC_API_KEY env var
anthropic_model: Anthropic model. Defaults to RAG_EVAL_ANTHROPIC_MODEL or 'claude-3-5-sonnet-20241022'
bedrock_region: AWS region. Defaults to RAG_EVAL_BEDROCK_REGION or AWS_REGION env var
bedrock_model: Bedrock model ID. Defaults to RAG_EVAL_BEDROCK_MODEL or
'anthropic.claude-3-sonnet-20240229-v1:0'
Returns:
Provider instance
Raises:
ValueError: If provider is invalid or required credentials are missing
"""
# Get provider from args or env
provider = provider or os.environ.get("RAG_EVAL_PROVIDER", "ollama")
if provider == "ollama":
# Try RAG_EVAL_OLLAMA_BASE_URL, then OLLAMA_HOST, then default
base_url = (
ollama_base_url
or os.environ.get("RAG_EVAL_OLLAMA_BASE_URL")
or os.environ.get("OLLAMA_HOST")
or "http://localhost:11434"
)
model = ollama_model or os.environ.get("RAG_EVAL_OLLAMA_MODEL", "llama3.2:1b")
return OllamaProvider(
base_url=base_url, embedding_model=None, generation_model=model
)
elif provider == "anthropic":
api_key = anthropic_api_key or os.environ.get("RAG_EVAL_ANTHROPIC_API_KEY")
if not api_key:
raise ValueError(
"Anthropic API key required. Set RAG_EVAL_ANTHROPIC_API_KEY environment variable."
)
model = anthropic_model or os.environ.get(
"RAG_EVAL_ANTHROPIC_MODEL", "claude-3-5-sonnet-20241022"
)
return AnthropicProvider(api_key=api_key, model=model)
elif provider == "bedrock":
region = bedrock_region or os.environ.get(
"RAG_EVAL_BEDROCK_REGION", os.environ.get("AWS_REGION", "us-east-1")
)
model = bedrock_model or os.environ.get(
"RAG_EVAL_BEDROCK_MODEL", "anthropic.claude-3-sonnet-20240229-v1:0"
)
return BedrockProvider(
region_name=region, embedding_model=None, generation_model=model
)
else:
raise ValueError(
f"Invalid provider: {provider}. Must be 'ollama', 'anthropic', or 'bedrock'."
)