Spaces:
Running
Running
File size: 6,264 Bytes
d7e5abb 4732667 d7e5abb 1f96735 d7e5abb 1f96735 d7e5abb 1f96735 9760706 1f96735 9760706 1f96735 d7e5abb 9760706 d7e5abb 9760706 d7e5abb 4732667 d7e5abb |
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 |
"""Judge handler for evidence assessment using PydanticAI."""
from typing import Any
import structlog
from pydantic_ai import Agent
from pydantic_ai.models.anthropic import AnthropicModel
from pydantic_ai.models.openai import OpenAIModel
from pydantic_ai.providers.anthropic import AnthropicProvider
from pydantic_ai.providers.openai import OpenAIProvider
from src.prompts.judge import (
SYSTEM_PROMPT,
format_empty_evidence_prompt,
format_user_prompt,
)
from src.utils.config import settings
from src.utils.models import AssessmentDetails, Evidence, JudgeAssessment
logger = structlog.get_logger()
def get_model() -> Any:
"""Get the LLM model based on configuration.
Explicitly passes API keys from settings to avoid requiring
users to export environment variables manually.
"""
llm_provider = settings.llm_provider
if llm_provider == "anthropic":
provider = AnthropicProvider(api_key=settings.anthropic_api_key)
return AnthropicModel(settings.anthropic_model, provider=provider)
if llm_provider != "openai":
logger.warning("Unknown LLM provider, defaulting to OpenAI", provider=llm_provider)
openai_provider = OpenAIProvider(api_key=settings.openai_api_key)
return OpenAIModel(settings.openai_model, provider=openai_provider)
class JudgeHandler:
"""
Handles evidence assessment using an LLM with structured output.
Uses PydanticAI to ensure responses match the JudgeAssessment schema.
"""
def __init__(self, model: Any = None) -> None:
"""
Initialize the JudgeHandler.
Args:
model: Optional PydanticAI model. If None, uses config default.
"""
self.model = model or get_model()
self.agent = Agent(
model=self.model,
output_type=JudgeAssessment,
system_prompt=SYSTEM_PROMPT,
retries=3,
)
async def assess(
self,
question: str,
evidence: list[Evidence],
) -> JudgeAssessment:
"""
Assess evidence and determine if it's sufficient.
Args:
question: The user's research question
evidence: List of Evidence objects from search
Returns:
JudgeAssessment with evaluation results
Raises:
JudgeError: If assessment fails after retries
"""
logger.info(
"Starting evidence assessment",
question=question[:100],
evidence_count=len(evidence),
)
# Format the prompt based on whether we have evidence
if evidence:
user_prompt = format_user_prompt(question, evidence)
else:
user_prompt = format_empty_evidence_prompt(question)
try:
# Run the agent with structured output
result = await self.agent.run(user_prompt)
assessment = result.output
logger.info(
"Assessment complete",
sufficient=assessment.sufficient,
recommendation=assessment.recommendation,
confidence=assessment.confidence,
)
return assessment
except Exception as e:
logger.error("Assessment failed", error=str(e))
# Return a safe default assessment on failure
return self._create_fallback_assessment(question, str(e))
def _create_fallback_assessment(
self,
question: str,
error: str,
) -> JudgeAssessment:
"""
Create a fallback assessment when LLM fails.
Args:
question: The original question
error: The error message
Returns:
Safe fallback JudgeAssessment
"""
return JudgeAssessment(
details=AssessmentDetails(
mechanism_score=0,
mechanism_reasoning="Assessment failed due to LLM error",
clinical_evidence_score=0,
clinical_reasoning="Assessment failed due to LLM error",
drug_candidates=[],
key_findings=[],
),
sufficient=False,
confidence=0.0,
recommendation="continue",
next_search_queries=[
f"{question} mechanism",
f"{question} clinical trials",
f"{question} drug candidates",
],
reasoning=f"Assessment failed: {error}. Recommend retrying with refined queries.",
)
class MockJudgeHandler:
"""
Mock JudgeHandler for testing without LLM calls.
Use this in unit tests to avoid API calls.
"""
def __init__(self, mock_response: JudgeAssessment | None = None) -> None:
"""
Initialize with optional mock response.
Args:
mock_response: The assessment to return. If None, uses default.
"""
self.mock_response = mock_response
self.call_count = 0
self.last_question: str | None = None
self.last_evidence: list[Evidence] | None = None
async def assess(
self,
question: str,
evidence: list[Evidence],
) -> JudgeAssessment:
"""Return the mock response."""
self.call_count += 1
self.last_question = question
self.last_evidence = evidence
if self.mock_response:
return self.mock_response
min_evidence = 3
# Default mock response
return JudgeAssessment(
details=AssessmentDetails(
mechanism_score=7,
mechanism_reasoning="Mock assessment - good mechanism evidence",
clinical_evidence_score=6,
clinical_reasoning="Mock assessment - moderate clinical evidence",
drug_candidates=["Drug A", "Drug B"],
key_findings=["Finding 1", "Finding 2"],
),
sufficient=len(evidence) >= min_evidence,
confidence=0.75,
recommendation="synthesize" if len(evidence) >= min_evidence else "continue",
next_search_queries=["query 1", "query 2"] if len(evidence) < min_evidence else [],
reasoning="Mock assessment for testing purposes",
)
|