feat: add tool metrics

Author: feng-95

agent.py

@@ -0,0 +1,51 @@
+from veadk import Agent, Runner
+from veadk.config import getenv
+from veadk.knowledgebase import KnowledgeBase
+from veadk.memory.long_term_memory import LongTermMemory
+from veadk.memory.short_term_memory import ShortTermMemory
+from veadk.tools.builtin_tools.web_search import web_search
+from veadk.tools.demo_tools import get_city_weather
+from veadk.tracing.telemetry.exporters.apmplus_exporter import APMPlusExporter
+from veadk.tracing.telemetry.exporters.cozeloop_exporter import CozeloopExporter
+from veadk.tracing.telemetry.exporters.tls_exporter import TLSExporter
+from veadk.tracing.telemetry.opentelemetry_tracer import OpentelemetryTracer
+
+tracer = OpentelemetryTracer(
+    exporters=[
+       # CozeloopExporter(),
+        APMPlusExporter(),
+       TLSExporter(),
+    ]
+)
+
+agent = Agent(
+    name="test",
+    tracers=[tracer],
+    tools=[get_city_weather],
+   # long_term_memory=LongTermMemory(backend="local"),
+  #  knowledgebase=KnowledgeBase(backend="local", app_name="veadk_default_app"),
+)
+
+short_term_memory = ShortTermMemory()
+
+runner = Runner(agent=agent, short_term_memory=short_term_memory)
+
+import asyncio
+
+for i in range(0, 300):
+    res = asyncio.run(
+        runner.run(
+            messages="搜索我的记忆、知识库，看看能不能获取到北京天气",
+            session_id="test_session",
+            save_tracing_data=False,
+        )
+    )
+
+    print(res)
+
+    import time
+
+    time.sleep(5)
+
+
+# print(getenv("MODEL_AGENT_EXTRA_CONFIG"))

deep_eval_test.py

@@ -0,0 +1,21 @@
+
+import pytest
+from deepeval import assert_test
+from deepeval.metrics import GEval
+from deepeval.test_case import LLMTestCase, LLMTestCaseParams
+
+def test_case():
+    correctness_metric = GEval(
+        name="Correctness",
+        criteria="Determine if the 'actual output' is correct based on the 'expected output'.",
+        evaluation_params=[LLMTestCaseParams.ACTUAL_OUTPUT, LLMTestCaseParams.EXPECTED_OUTPUT],
+        threshold=0.5
+    )
+    test_case = LLMTestCase(
+        input="What if these shoes don't fit?",
+        # Replace this with the actual output from your LLM application
+        actual_output="You have 30 days to get a full refund at no extra cost.",
+        expected_output="We offer a 30-day full refund at no extra costs.",
+        retrieval_context=["All customers are eligible for a 30 day full refund at no extra costs."]
+    )
+    assert_test(test_case, [correctness_metric])