Spaces:
Running
Running
File size: 11,820 Bytes
731a241 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 |
"""Integration tests for RAG integration.
These tests require OPENAI_API_KEY and may make real API calls.
Marked with @pytest.mark.integration to skip in unit test runs.
"""
import pytest
from src.services.llamaindex_rag import get_rag_service
from src.tools.rag_tool import create_rag_tool
from src.tools.search_handler import SearchHandler
from src.tools.tool_executor import execute_agent_task
from src.utils.config import settings
from src.utils.models import AgentTask, Citation, Evidence
@pytest.mark.integration
class TestRAGServiceIntegration:
"""Integration tests for LlamaIndexRAGService."""
@pytest.mark.asyncio
async def test_rag_service_ingest_and_retrieve(self):
"""RAG service should ingest and retrieve evidence."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Create RAG service
rag_service = get_rag_service(collection_name="test_integration")
# Create sample evidence
evidence_list = [
Evidence(
content="Metformin is a first-line treatment for type 2 diabetes. It works by reducing glucose production in the liver and improving insulin sensitivity.",
citation=Citation(
source="pubmed",
title="Metformin Mechanism of Action",
url="https://pubmed.ncbi.nlm.nih.gov/12345678/",
date="2024-01-15",
authors=["Smith J", "Johnson M"],
),
relevance=0.9,
),
Evidence(
content="Recent studies suggest metformin may have neuroprotective effects in Alzheimer's disease models.",
citation=Citation(
source="pubmed",
title="Metformin and Neuroprotection",
url="https://pubmed.ncbi.nlm.nih.gov/12345679/",
date="2024-02-20",
authors=["Brown K", "Davis L"],
),
relevance=0.85,
),
]
# Ingest evidence
rag_service.ingest_evidence(evidence_list)
# Retrieve evidence
results = rag_service.retrieve("metformin diabetes", top_k=2)
# Assert
assert len(results) > 0
assert any("metformin" in r["text"].lower() for r in results)
assert all("text" in r for r in results)
assert all("metadata" in r for r in results)
# Cleanup
rag_service.clear_collection()
@pytest.mark.asyncio
async def test_rag_service_query(self):
"""RAG service should synthesize responses from ingested evidence."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
rag_service = get_rag_service(collection_name="test_query")
# Ingest evidence
evidence_list = [
Evidence(
content="Python is a high-level programming language known for its simplicity and readability.",
citation=Citation(
source="pubmed",
title="Python Programming",
url="https://example.com/python",
date="2024",
authors=["Author"],
),
)
]
rag_service.ingest_evidence(evidence_list)
# Query
response = rag_service.query("What is Python?", top_k=1)
assert isinstance(response, str)
assert len(response) > 0
assert "python" in response.lower()
# Cleanup
rag_service.clear_collection()
@pytest.mark.integration
class TestRAGToolIntegration:
"""Integration tests for RAGTool."""
@pytest.mark.asyncio
async def test_rag_tool_search(self):
"""RAGTool should search RAG service and return Evidence objects."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Create RAG service and ingest evidence
rag_service = get_rag_service(collection_name="test_rag_tool")
evidence_list = [
Evidence(
content="Machine learning is a subset of artificial intelligence.",
citation=Citation(
source="pubmed",
title="ML Basics",
url="https://example.com/ml",
date="2024",
authors=["ML Expert"],
),
)
]
rag_service.ingest_evidence(evidence_list)
# Create RAG tool
tool = create_rag_tool(rag_service=rag_service)
# Search
results = await tool.search("machine learning", max_results=5)
# Assert
assert len(results) > 0
assert all(isinstance(e, Evidence) for e in results)
assert results[0].citation.source == "rag"
assert (
"machine learning" in results[0].content.lower()
or "artificial intelligence" in results[0].content.lower()
)
# Cleanup
rag_service.clear_collection()
@pytest.mark.asyncio
async def test_rag_tool_empty_collection(self):
"""RAGTool should return empty list when collection is empty."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
rag_service = get_rag_service(collection_name="test_empty")
rag_service.clear_collection() # Ensure empty
tool = create_rag_tool(rag_service=rag_service)
results = await tool.search("any query")
assert results == []
@pytest.mark.integration
class TestRAGAgentIntegration:
"""Integration tests for RAGAgent in tool executor."""
@pytest.mark.asyncio
async def test_rag_agent_execution(self):
"""RAGAgent should execute and return ToolAgentOutput."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Setup: Ingest evidence into RAG
rag_service = get_rag_service(collection_name="test_rag_agent")
evidence_list = [
Evidence(
content="Deep learning uses neural networks with multiple layers.",
citation=Citation(
source="pubmed",
title="Deep Learning",
url="https://example.com/dl",
date="2024",
authors=["DL Researcher"],
),
)
]
rag_service.ingest_evidence(evidence_list)
# Execute RAGAgent task
task = AgentTask(
agent="RAGAgent",
query="deep learning",
gap="Need information about deep learning",
)
result = await execute_agent_task(task)
# Assert
assert result.output
assert "deep learning" in result.output.lower() or "neural network" in result.output.lower()
assert len(result.sources) > 0
# Cleanup
rag_service.clear_collection()
@pytest.mark.integration
class TestRAGSearchHandlerIntegration:
"""Integration tests for RAG in SearchHandler."""
@pytest.mark.asyncio
async def test_search_handler_with_rag(self):
"""SearchHandler should work with RAG tool included."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Setup: Create RAG service and ingest some evidence
rag_service = get_rag_service(collection_name="test_search_handler")
evidence_list = [
Evidence(
content="Test evidence for search handler integration.",
citation=Citation(
source="pubmed",
title="Test Evidence",
url="https://example.com/test",
date="2024",
authors=["Tester"],
),
)
]
rag_service.ingest_evidence(evidence_list)
# Create SearchHandler with RAG
handler = SearchHandler(
tools=[], # No other tools
include_rag=True,
auto_ingest_to_rag=False, # Don't auto-ingest (already has data)
)
# Execute search
result = await handler.execute("test evidence", max_results_per_tool=5)
# Assert
assert result.total_found > 0
assert "rag" in result.sources_searched
assert any(e.citation.source == "rag" for e in result.evidence)
# Cleanup
rag_service.clear_collection()
@pytest.mark.asyncio
async def test_search_handler_auto_ingest(self):
"""SearchHandler should auto-ingest evidence into RAG."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Create empty RAG service
rag_service = get_rag_service(collection_name="test_auto_ingest")
rag_service.clear_collection()
# Create mock tool that returns evidence
from unittest.mock import AsyncMock
mock_tool = AsyncMock()
mock_tool.name = "pubmed"
mock_tool.search = AsyncMock(
return_value=[
Evidence(
content="Evidence to be ingested",
citation=Citation(
source="pubmed",
title="Test",
url="https://example.com",
date="2024",
authors=[],
),
)
]
)
# Create handler with auto-ingest enabled
handler = SearchHandler(
tools=[mock_tool],
include_rag=False, # Don't include RAG as search tool
auto_ingest_to_rag=True,
)
handler._rag_service = rag_service # Inject RAG service
# Execute search
await handler.execute("test query")
# Verify evidence was ingested
rag_results = rag_service.retrieve("Evidence to be ingested", top_k=1)
assert len(rag_results) > 0
# Cleanup
rag_service.clear_collection()
@pytest.mark.integration
class TestRAGHybridSearchIntegration:
"""Integration tests for hybrid search (RAG + database)."""
@pytest.mark.asyncio
async def test_hybrid_search_rag_and_pubmed(self):
"""SearchHandler should support RAG + PubMed hybrid search."""
if not settings.openai_api_key:
pytest.skip("OPENAI_API_KEY required for RAG integration tests")
# Setup: Ingest evidence into RAG
rag_service = get_rag_service(collection_name="test_hybrid")
evidence_list = [
Evidence(
content="Previously collected evidence about metformin.",
citation=Citation(
source="pubmed",
title="Previous Research",
url="https://example.com/prev",
date="2024",
authors=[],
),
)
]
rag_service.ingest_evidence(evidence_list)
# Note: This test would require real PubMed API access
# For now, we'll just test that the handler can be created with both tools
from src.tools.pubmed import PubMedTool
handler = SearchHandler(
tools=[PubMedTool()],
include_rag=True,
auto_ingest_to_rag=True,
)
# Verify handler has both tools
tool_names = [t.name for t in handler.tools]
assert "pubmed" in tool_names
assert "rag" in tool_names
# Cleanup
rag_service.clear_collection()
|