andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-07 15:18:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Adding support for Crew throttling using RPM (#124)

Browse Source 
* Add translations
* fixing translations
* Adding support for Crew throttling with RPM
This commit is contained in:
João Moura
2024-01-13 11:20:30 -03:00
committed by GitHub
parent cbe688adbc
commit 53a32153a5
5 changed files with 784 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/crewai/agent.py
View File

@@ -12,6 +12,7 @@ from pydantic import (
ConfigDict,
Field,
InstanceOf,
PrivateAttr,
field_validator,
model_validator,
)
@@ -46,6 +47,8 @@ class Agent(BaseModel):
"""
__hash__ = object.__hash__
_request_within_rpm_limit: Any = PrivateAttr(default=None)
model_config = ConfigDict(arbitrary_types_allowed=True)
id: UUID4 = Field(
default_factory=uuid.uuid4,
@@ -139,6 +142,10 @@ class Agent(BaseModel):
self.tools_handler = ToolsHandler(cache=self.cache_handler)
self.__create_agent_executor()
def set_request_within_rpm_limit(self, ensure_function) -> None:
self._request_within_rpm_limit = ensure_function
self.__create_agent_executor()
def __create_agent_executor(self) -> CrewAgentExecutor:
"""Create an agent executor for the agent.
@@ -157,11 +164,12 @@ class Agent(BaseModel):
"verbose": self.verbose,
"handle_parsing_errors": True,
"max_iterations": self.max_iter,
"request_within_rpm_limit": self._request_within_rpm_limit,
}
if self.memory:
summary_memory = ConversationSummaryMemory(
llm=self.llm, memory_key="chat_history", input_key="input"
llm=self.llm, input_key="input", memory_key="chat_history"
)
executor_args["memory"] = summary_memory
agent_args["chat_history"] = lambda x: x["chat_history"]

42
src/crewai/agents/executor.py
View File

@@ -19,6 +19,7 @@ from crewai.tools.cache_tools import CacheTools
class CrewAgentExecutor(AgentExecutor):
i18n: I18N = I18N()
iterations: int = 0
request_within_rpm_limit: Any = None
max_iterations: Optional[int] = 15
force_answer_max_iterations: Optional[int] = None
@@ -54,29 +55,30 @@ class CrewAgentExecutor(AgentExecutor):
start_time = time.time()
# We now enter the agent loop (until it returns something).
while self._should_continue(self.iterations, time_elapsed):
next_step_output = self._take_next_step(
name_to_tool_map,
color_mapping,
inputs,
intermediate_steps,
run_manager=run_manager,
)
if isinstance(next_step_output, AgentFinish):
return self._return(
next_step_output, intermediate_steps, run_manager=run_manager
if not self.request_within_rpm_limit or self.request_within_rpm_limit():
next_step_output = self._take_next_step(
name_to_tool_map,
color_mapping,
inputs,
intermediate_steps,
run_manager=run_manager,
)
intermediate_steps.extend(next_step_output)
if len(next_step_output) == 1:
next_step_action = next_step_output[0]
# See if tool should return directly
tool_return = self._get_tool_return(next_step_action)
if tool_return is not None:
if isinstance(next_step_output, AgentFinish):
return self._return(
tool_return, intermediate_steps, run_manager=run_manager
next_step_output, intermediate_steps, run_manager=run_manager
)
self.iterations += 1
time_elapsed = time.time() - start_time
intermediate_steps.extend(next_step_output)
if len(next_step_output) == 1:
next_step_action = next_step_output[0]
# See if tool should return directly
tool_return = self._get_tool_return(next_step_action)
if tool_return is not None:
return self._return(
tool_return, intermediate_steps, run_manager=run_manager
)
self.iterations += 1
time_elapsed = time.time() - start_time
output = self.agent.return_stopped_response(
self.early_stopping_method, intermediate_steps, **inputs
)

53
src/crewai/crew.py
View File

@@ -1,6 +1,8 @@
import json
import threading
import time
import uuid
from typing import Any, Dict, List, Optional, Union
from typing import Any, ClassVar, Dict, List, Optional, Union
from pydantic import (
UUID4,
@@ -9,6 +11,7 @@ from pydantic import (
Field,
InstanceOf,
Json,
PrivateAttr,
field_validator,
model_validator,
)
@@ -33,10 +36,16 @@ class Crew(BaseModel):
verbose: Indicates the verbosity level for logging during execution.
config: Configuration settings for the crew.
cache_handler: Handles caching for the crew's operations.
max_rpm: Maximum number of requests per minute for the crew execution to be respected.
rpm: Current number of requests per minute for the crew execution.
id: A unique identifier for the crew instance.
"""
__hash__ = object.__hash__
_timer: Optional[threading.Timer] = PrivateAttr(default=None)
lock: ClassVar[threading.Lock] = threading.Lock()
rpm: ClassVar[int] = 0
max_rpm: Optional[int] = Field(default=None)
model_config = ConfigDict(arbitrary_types_allowed=True)
tasks: List[Task] = Field(default_factory=list)
agents: List[Agent] = Field(default_factory=list)
@@ -64,6 +73,12 @@ class Crew(BaseModel):
def check_config_type(cls, v: Union[Json, Dict[str, Any]]):
return json.loads(v) if isinstance(v, Json) else v
@model_validator(mode="after")
def set_reset_counter(self):
if self.max_rpm:
self._reset_request_count()
return self
@model_validator(mode="after")
def check_config(self):
"""Validates that the crew is properly configured with agents and tasks."""
@@ -80,6 +95,7 @@ class Crew(BaseModel):
if self.agents:
for agent in self.agents:
agent.set_cache_handler(self.cache_handler)
agent.set_request_within_rpm_limit(self.ensure_request_within_rpm_limit)
return self
def _setup_from_config(self):
@@ -100,6 +116,24 @@ class Crew(BaseModel):
del task_config["agent"]
return Task(**task_config, agent=task_agent)
def ensure_request_within_rpm_limit(self):
if not self.max_rpm:
return True
with Crew.lock:
if Crew.rpm < self.max_rpm:
Crew.rpm += 1
return True
self._log("info", "Max RPM reached, waiting for next minute to start.")
return self._wait_for_next_minute()
def _wait_for_next_minute(self):
time.sleep(60)
with Crew.lock:
Crew.rpm = 0
return True
def kickoff(self) -> str:
"""Starts the crew to work on its assigned tasks."""
for agent in self.agents:
@@ -115,9 +149,8 @@ class Crew(BaseModel):
for task in self.tasks:
self._prepare_and_execute_task(task)
task_output = task.execute(task_output)
self._log(
"debug", f"\n\n[{task.agent.role}] Task output: {task_output}\n\n"
)
self._log("debug", f"\n[{task.agent.role}] Task output: {task_output}\n\n")
self._stop_timer()
return task_output
def _prepare_and_execute_task(self, task):
@@ -135,4 +168,14 @@ class Crew(BaseModel):
2 if isinstance(self.verbose, bool) and self.verbose else self.verbose
)
if verbose_level and level_map[level] <= verbose_level:
print(message)
print(f"\n{message}")
def _stop_timer(self):
if self._timer:
self._timer.cancel()
def _reset_request_count(self):
self._stop_timer()
self._timer = threading.Timer(60.0, self._reset_request_count)
self._timer.start()
Crew.rpm = 0

666
tests/cassettes/test_api_calls_throttling.yaml Normal file
View File

@@ -0,0 +1,666 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]This is the summary of your work
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
"temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1055'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQL7bRtT6PceuMWF91CSHDk1cziN\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121717,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
get_final_answer\\nAction Input: [1, 2, 3]\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
226,\n \"completion_tokens\": 30,\n \"total_tokens\": 256\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0bccfc300301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:55:19 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
path=/; expires=Sat, 13-Jan-24 05:25:19 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1751'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299760'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 48ms
x-request-id:
- ae0de27cb07da02e7bce2d30958b7e14
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]This is the summary of your work
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: [1, 2, 3]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1171'
content-type:
- application/json
cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQL9CyNZOIEDKgfmDn68aH26tLrn\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121719,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? Yes\\nAction:
get_final_answer\\nAction Input: [4, 5, 6]\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
265,\n \"completion_tokens\": 28,\n \"total_tokens\": 293\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0bdaee800301-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:55:22 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2615'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299731'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 53ms
x-request-id:
- 9d85a22aa63ee4cea3ad01a3b68316b4
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]This is the summary of your work
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: "}], "model":
"gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1278'
content-type:
- application/json
cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQMARI9zwx2Z1Uel5us1xzxPAuGJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121782,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? Yes\\nAction:
get_final_answer\\nAction Input: [7, 8, 9]\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
301,\n \"completion_tokens\": 28,\n \"total_tokens\": 329\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0d63fa7a02ee-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:56:24 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1878'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299705'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 58ms
x-request-id:
- d98dffd5ba9915b41051dcad49109eba
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]This is the summary of your work
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\nObservation:
42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1385'
content-type:
- application/json
cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQMC51udijWPWSLCk1Cx36OVtDUX\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121784,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? Yes\\nAction:
get_final_answer\\nAction Input: [10, 11, 12]\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
337,\n \"completion_tokens\": 28,\n \"total_tokens\": 365\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0d72cbbd02ee-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:56:27 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2939'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299680'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 64ms
x-request-id:
- 528f38b4e5dd09a1fd25893edb27e4b4
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goalTOOLS:\n------\nYou have access to the following
tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo
use a tool, please use the exact following format:\n\n```\nThought: Do I need
to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]This is the summary of your work
so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\nObservation:
42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
Input: [10, 11, 12]\nObservation: I''ve used too many tools for this task. I''m
going to give you my absolute BEST Final answer now and not use any more tools.\nThought:
"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1616'
content-type:
- application/json
cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQMGpMHplpQ8ApiUZmhbX4z9gVuK\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121788,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
I've used the tool 'get_final_answer' multiple times and have observed the result.
However, as per my task, I am to keep using this tool and not provide a final
answer.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 399,\n \"completion_tokens\":
52,\n \"total_tokens\": 451\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0d86a87f02ee-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:56:31 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '3227'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299624'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 75ms
x-request-id:
- 7a91d2e523c43f5fc9a1191437491d68
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
give a Final Answer, instead keep using the `get_final_answer` tool.\nAI: I''ve
used the tool ''get_final_answer'' multiple times and have observed the result.
However, as per my task, I am to keep using this tool and not provide a final
answer.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1094'
content-type:
- application/json
cookie:
- __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
_cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.7.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.7.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8gQMJYMA8HO4tGJr8wUqEIJYn1xUa\",\n \"object\":
\"chat.completion\",\n \"created\": 1705121791,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human instructs the AI not to give
a final answer, but to continue using the 'get_final_answer' tool. The AI acknowledges
that it has used the tool multiple times and understands the directive to continue
using it without providing a final answer.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
195,\n \"completion_tokens\": 50,\n \"total_tokens\": 245\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 844b0d9dafa902ee-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sat, 13 Jan 2024 04:56:34 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2830'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299742'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 51ms
x-request-id:
- 0192af0bde71c3bb536287175e1a4458
http_version: HTTP/1.1
status_code: 200
version: 1

39
tests/crew_test.py
View File

@@ -266,3 +266,42 @@ def test_cache_hitting_between_agents():
read.return_value = "12"
crew.kickoff()
read.assert_called_with("multiplier", "2,6")
@pytest.mark.vcr(filter_headers=["authorization"])
def test_api_calls_throttling(capsys):
from unittest.mock import patch
from langchain.tools import tool
@tool
def get_final_answer(numbers) -> float:
"""Get the final answer but don't give it yet, just re-use this
tool non-stop."""
return 42
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
max_iter=5,
allow_delegation=False,
verbose=True,
)
task = Task(
description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
tools=[get_final_answer],
agent=agent,
)
tasks = task
crew = Crew(agents=[agent], tasks=[tasks], max_rpm=2, verbose=2)
with patch.object(Crew, "_wait_for_next_minute") as moveon:
moveon.return_value = True
crew.kickoff()
captured = capsys.readouterr()
assert "Max RPM reached, waiting for next minute to start." in captured.out
moveon.assert_called()