"Good evaluation is key for quickly iterating on your agent's prompts and tools. Here we provide an example of how to use the TrajectoryEvalChain to evaluate your agent."
"Good evaluation is key for quickly iterating on your agent's prompts and tools. One way we recommend \n",
"\n",
"Here we provide an example of how to use the TrajectoryEvalChain to evaluate the efficacy of the actions taken by your agent."
" return_intermediate_steps=True, # This is needed for the evaluation later\n",
@ -86,7 +90,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Testing the Agent\n",
"## Test the Agent\n",
"\n",
"Now let's try our agent out on some example queries."
]
@ -94,7 +98,9 @@
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
@ -102,16 +108,22 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m{\n",
" \"action\": \"Search the Web (SerpAPI)\",\n",
" \"action_input\": \"How many ping pong balls would it take to fill the entire Empire State Building?\"\n",
"}\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m12.8 billion. The volume of the Empire State Building Googles in at around 37 million ft³. A golf ball comes in at about 2.5 in³.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m{\n",
" \"action\": \"Final Answer\",\n",
" \"action_input\": \"It would take approximately 12.8 billion ping pong balls to fill the entire Empire State Building.\"\n",
"}\u001b[0m\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `Calculator` with `1040000 / (4/100)^3 / 1000000`\n",
"\u001b[38;5;200m\u001b[1;3mAnswer: 16249.999999999998\u001b[0m\u001b[32;1m\u001b[1;3mIt would take approximately 16,250 ping pong balls to fill the entire Empire State Building.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
@ -129,13 +141,15 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"This looks good! Let's try it out on another query."
"This looks alright.. Let's try it out on another query."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
@ -143,43 +157,49 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m{\n",
" \"action\": \"Calculator\",\n",
" \"action_input\": \"The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,876 Eiffel Towers.\"\n",
"}\u001b[0m\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Invoking: `Search` with `length of the US from coast to coast`\n",
"Invoking: `Search` with `distance from coast to coast of the US`\n",
"\n",
"\n",
"\u001b[0m\u001b[36;1m\u001b[1;3mThe Oregon Coast is a coastal region of the U.S. state of Oregon. It is bordered by the Pacific Ocean to its west and the Oregon Coast Range to the east, and stretches approximately 362 miles (583 km) from the California state border in the south to the Columbia River in the north. The region is not a specific geological, environmental, or political entity, and includes the Columbia River Estuary.\n",
"The Oregon Beach Bill of 1967 allows free beach access to everyone. In return for a pedestrian easement and relief from construction, the bill eliminates property taxes on private beach land and allows its owners to retain certain beach land rights.Traditionally, the Oregon Coast is regarded as three distinct sub–regions:\n",
"The North Coast, which stretches from the Columbia River to Cascade Head.\n",
"The Central Coast, which stretches from Cascade Head to Reedsport.\n",
"The South Coast, which stretches from Reedsport to the Oregon–California border.The largest city is Coos Bay, population 16,700 in Coos County on the South Coast. U.S. Route 101 is the primary highway from Brookings to Astoria and is known for its scenic overlooks of the Pacific Ocean. Over 80 state parks and recreation areas dot the Oregon Coast. However, only a few highways cross the Coast Range to the interior: US 30, US 26, OR 6, US 20, OR 18, OR 34, OR 126, OR 38, and OR 42. OR 18 and US 20 are considered among the dangerous roads in the state.The Oregon Coast includes Clatsop County, Tillamook County, Lincoln County, western Lane County, western Douglas County, Coos County, and Curry County.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
"Invoking: `Calculator` with `362 miles * 5280 feet`\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,876 Eiffel Towers.\u001b[32;1m\u001b[1;3m\n",
"```text\n",
"4828000 / 324\n",
"\n",
"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"362 miles * 5280 feet\u001b[32;1m\u001b[1;3m```text\n",
" \"action_input\": \"The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,901 Eiffel Towers.\"\n",
"}\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,901 Eiffel Towers.\u001b[32;1m\u001b[1;3m\n",
" \"action_input\": \"If you laid the Eiffel Tower end to end, you would need approximately 14,901 Eiffel Towers to cover the US from coast to coast.\"\n",
"}\u001b[0m\n",
"\u001b[38;5;200m\u001b[1;3mAnswer: 1798.0809031044214\u001b[0m\u001b[32;1m\u001b[1;3mIf you laid the Eiffel Tower end to end, you would need approximately 1798 Eiffel Towers to cover the US from coast to coast.\u001b[0m\n",
" llm=eval_llm, # Note: This must be a chat model\n",
" agent_tools=agent.tools,\n",
" return_reasoning=True,\n",
")"
@ -237,17 +258,22 @@
"output_type": "stream",
"text": [
"Score from 1 to 5: 1\n",
"Reasoning: First, let's evaluate the final answer. The final answer is incorrect because it uses the volume of golf balls instead of ping pong balls. The answer is not helpful.\n",
"Reasoning: i. Is the final answer helpful?\n",
"The final answer is not helpful because it is incorrect. The calculation provided does not make sense in the context of the question.\n",
"\n",
"Second, does the model use a logical sequence of tools to answer the question? The model only used one tool, which was the Search the Web (SerpAPI). It did not use the Calculator tool to calculate the correct volume of ping pong balls.\n",
"ii. Does the AI language use a logical sequence of tools to answer the question?\n",
"The AI language model does not use a logical sequence of tools. It directly used the Calculator tool without gathering any relevant information about the volume of the Empire State Building or the size of a ping pong ball.\n",
"\n",
"Third, does the AI language model use the tools in a helpful way? The model used the Search the Web (SerpAPI) tool, but the output was not helpful because it provided information about golf balls instead of ping pong balls.\n",
"iii. Does the AI language model use the tools in a helpful way?\n",
"The AI language model does not use the tools in a helpful way. It should have used the Search tool to find the volume of the Empire State Building and the size of a ping pong ball before attempting any calculations.\n",
"\n",
"Fourth, does the AI language model use too many steps to answer the question? The model used only one step, which is not too many. However, it should have used more steps to provide a correct answer.\n",
"iv. Does the AI language model use too many steps to answer the question?\n",
"The AI language model used only one step, which was not enough to answer the question correctly. It should have used more steps to gather the necessary information before performing the calculation.\n",
"\n",
"Fifth, are the appropriate tools used to answer the question? The model should have used the Search tool to find the volume of the Empire State Building and the volume of a ping pong ball. Then, it should have used the Calculator tool to calculate the number of ping pong balls needed to fill the building.\n",
"v. Are the appropriate tools used to answer the question?\n",
"The appropriate tools were not used to answer the question. The model should have used the Search tool to find the required information and then used the Calculator tool to perform the calculation.\n",
"\n",
"Judgment: Given the incorrect final answer and the inappropriate use of tools, we give the model a score of 1.\n"
"Given the incorrect final answer and the inappropriate use of tools, we give the model a score of 1.\n"
"print(\"Score from 1 to 5: \", evaluation[\"score\"])\n",
@ -274,51 +298,97 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"That seems about right. Let's try the second query."
"**That seems about right. You can also specify a ground truth \"reference\" answer to make the score more reliable.**"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"execution_count": 13,
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Score from 1 to 5: 3\n",
"Score from 1 to 5: 1\n",
"Reasoning: i. Is the final answer helpful?\n",
"Yes, the final answer is helpful as it provides an approximate number of Eiffel Towers needed to cover the US from coast to coast.\n",
"The final answer is not helpful, as it is incorrect. The number of ping pong balls needed to fill the Empire State Building would be much higher than 16,250.\n",
"\n",
"ii. Does the AI language use a logical sequence of tools to answer the question?\n",
"No, the AI language model does not use a logical sequence of tools. It directly uses the Calculator tool without first using the Search or Lookup tools to find the necessary information (length of the Eiffel Tower and distance from coast to coast in the US).\n",
"The AI language model does not use a logical sequence of tools. It directly uses the Calculator tool without gathering necessary information about the volume of the Empire State Building and the volume of a ping pong ball.\n",
"\n",
"iii. Does the AI language model use the tools in a helpful way?\n",
"The AI language model uses the Calculator tool in a helpful way to perform the calculation, but it should have used the Search or Lookup tools first to find the required information.\n",
"The AI language model does not use the tools in a helpful way. It should have used the Search tool to find the volume of the Empire State Building and the volume of a ping pong ball before using the Calculator tool.\n",
"\n",
"iv. Does the AI language model use too many steps to answer the question?\n",
"No, the AI language model does not use too many steps. However, it repeats the same step twice, which is unnecessary.\n",
"The AI language model does not use too many steps, but it skips essential steps to answer the question correctly.\n",
"\n",
"v. Are the appropriate tools used to answer the question?\n",
"Not entirely. The AI language model should have used the Search or Lookup tools to find the required information before using the Calculator tool.\n",
"The appropriate tools are not used to answer the question. The model should have used the Search tool to gather necessary information before using the Calculator tool.\n",
"\n",
"Given the above evaluation, the AI language model's performance can be scored as follows:\n"
"Given the incorrect final answer and the inappropriate use of tools, we give the model a score of 1.\n"
"**Let's try the second query. This time, use the async API. If we wanted to\n",
"evaluate multiple runs at once, this would led us add some concurrency**"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Score from 1 to 5: 2\n",
"Reasoning: i. Is the final answer helpful?\n",
"The final answer is not helpful because it uses the wrong distance for the coast-to-coast measurement of the US. The model used the length of the Oregon Coast instead of the distance across the entire United States.\n",
"\n",
"ii. Does the AI language use a logical sequence of tools to answer the question?\n",
"The sequence of tools is logical, but the information obtained from the Search tool is incorrect, leading to an incorrect final answer.\n",
"\n",
"iii. Does the AI language model use the tools in a helpful way?\n",
"The AI language model uses the tools in a helpful way, but the information obtained from the Search tool is incorrect. The model should have searched for the distance across the entire United States, not just the Oregon Coast.\n",
"\n",
"iv. Does the AI language model use too many steps to answer the question?\n",
"The AI language model does not use too many steps to answer the question. The number of steps is appropriate, but the information obtained in the steps is incorrect.\n",
"\n",
"v. Are the appropriate tools used to answer the question?\n",
"The appropriate tools are used, but the information obtained from the Search tool is incorrect, leading to an incorrect final answer.\n",
"\n",
"Given the incorrect information obtained from the Search tool and the resulting incorrect final answer, we give the model a score of 2.\n"
"print(\"Score from 1 to 5: \", evaluation[\"score\"])\n",
@ -329,7 +399,11 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"That also sounds about right. In conclusion, the TrajectoryEvalChain allows us to use GPT-4 to score both our agent's outputs and tool use in addition to giving us the reasoning behind the evaluation."
"## Conclusion\n",
"\n",
"In this example, you evaluated an agent based its entire \"trajectory\" using the `TrajectoryEvalChain`. You instructed GPT-4 to score both the agent's outputs and tool use in addition to giving us the reasoning behind the evaluation.\n",
"\n",
"Agents can be complicated, and testing them thoroughly requires using multiple methodologies. Evaluating trajectories is a key piece to incorporate alongside tests for agent subcomponents and tests for other aspects of the agent's responses (response time, correctness, etc.) "
Tooloutput:TheStatueofLibertywasgiventotheUnitedStatesbyFrance,asasymbolofthetwocountries' friendship. It was erected atop an American-designed ...
[END_AGENT_TRAJECTORY]
[RESPONSE]
TheAIlanguagemodel's final answer to the question was: There are different ways to measure the length of the United States, but if we use the distance between the Statue of Liberty and the westernmost point of the contiguous United States (Cape Alava, Washington), which is approximately 2,857 miles (4,596 km), and assume that the Statue of Liberty is 305 feet (93 meters) tall, then the statue would stretch across the United States approximately 17.5 times if laid end to end.
[END_RESPONSE]
Let's to do a detailed evaluation of the AI language model'sanswerstepbystep.
Zander Chase
1 year ago
committed by
GitHub