andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-11 00:58:30 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Updated calls and added tests to verify

Browse Source
This commit is contained in:
Brandon Hancock
2025-01-22 13:04:10 -05:00
parent a21e310d78
commit 105f2378f6
7 changed files with 687 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
src/crewai/llm.py
View File

@@ -5,6 +5,7 @@ import sys
import threading import threading
import warnings import warnings
from contextlib import contextmanager from contextlib import contextmanager
from functools import singledispatchmethod
from typing import Any, Dict, List, Optional, Union, cast from typing import Any, Dict, List, Optional, Union, cast
from dotenv import load_dotenv from dotenv import load_dotenv
@@ -165,32 +166,50 @@ class LLM:
def call( def call(
self, self,
messages: List[Dict[str, str]], messages: Union[str, List[Dict[str, str]]],
tools: Optional[List[dict]] = None, tools: Optional[List[dict]] = None,
callbacks: Optional[List[Any]] = None, callbacks: Optional[List[Any]] = None,
available_functions: Optional[Dict[str, Any]] = None, available_functions: Optional[Dict[str, Any]] = None,
) -> str: ) -> str:
""" """
High-level call method that: High-level llm call method that:
1) Calls litellm.completion 1) Accepts either a string or a list of messages
2) Checks for function/tool calls 2) Converts string input to the required message format
3) If a tool call is found: 3) Calls litellm.completion
a) executes the function 4) Handles function/tool calls if any
b) returns the result 5) Returns the final text response or tool result
4) If no tool call, returns the text response
:param messages: The conversation messages Parameters:
:param tools: Optional list of function schemas for function calling - messages (Union[str, List[Dict[str, str]]]): The input messages for the LLM.
:param callbacks: Optional list of callbacks - If a string is provided, it will be converted into a message list with a single entry.
:param available_functions: A dictionary mapping function_name -> actual Python function - If a list of dictionaries is provided, each dictionary should have 'role' and 'content' keys.
:return: Final text response from the LLM or the tool result - tools (Optional[List[dict]]): A list of tool schemas for function calling.
- callbacks (Optional[List[Any]]): A list of callback functions to be executed.
- available_functions (Optional[Dict[str, Any]]): A dictionary mapping function names to actual Python functions.
Returns:
- str: The final text response from the LLM or the result of a tool function call.
Examples:
---------
# Example 1: Using a string input
response = llm.call("Return the name of a random city in the world.")
print(response)
# Example 2: Using a list of messages
messages = [{"role": "user", "content": "What is the capital of France?"}]
response = llm.call(messages)
print(response)
""" """
if isinstance(messages, str):
messages = [{"role": "user", "content": messages}]
with suppress_warnings(): with suppress_warnings():
if callbacks and len(callbacks) > 0: if callbacks and len(callbacks) > 0:
self.set_callbacks(callbacks) self.set_callbacks(callbacks)
try: try:
# --- 1) Make the completion call # --- 1) Prepare the parameters for the completion call
params = { params = {
"model": self.model, "model": self.model,
"messages": messages, "messages": messages,
@@ -211,11 +230,13 @@ class LLM:
"api_version": self.api_version, "api_version": self.api_version,
"api_key": self.api_key, "api_key": self.api_key,
"stream": False, "stream": False,
"tools": tools, # pass the tool schema "tools": tools,
} }
# Remove None values from params
params = {k: v for k, v in params.items() if v is not None} params = {k: v for k, v in params.items() if v is not None}
# --- 2) Make the completion call
response = litellm.completion(**params) response = litellm.completion(**params)
response_message = cast(Choices, cast(ModelResponse, response).choices)[ response_message = cast(Choices, cast(ModelResponse, response).choices)[
0 0
@@ -223,7 +244,7 @@ class LLM:
text_response = response_message.content or "" text_response = response_message.content or ""
tool_calls = getattr(response_message, "tool_calls", []) tool_calls = getattr(response_message, "tool_calls", [])
# Ensure callbacks get the full response object with usage info # --- 3) Handle callbacks with usage info
if callbacks and len(callbacks) > 0: if callbacks and len(callbacks) > 0:
for callback in callbacks: for callback in callbacks:
if hasattr(callback, "log_success_event"): if hasattr(callback, "log_success_event"):
@@ -236,11 +257,11 @@ class LLM:
end_time=0, end_time=0,
) )
# --- 2) If no tool calls, return the text response # --- 4) If no tool calls, return the text response
if not tool_calls or not available_functions: if not tool_calls or not available_functions:
return text_response return text_response
# --- 3) Handle the tool call # --- 5) Handle the tool call
tool_call = tool_calls[0] tool_call = tool_calls[0]
function_name = tool_call.function.name function_name = tool_call.function.name
@@ -255,7 +276,6 @@ class LLM:
try: try:
# Call the actual tool function # Call the actual tool function
result = fn(**function_args) result = fn(**function_args)
return result return result
except Exception as e: except Exception as e:

102
tests/cassettes/test_llm_call_with_message_list.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '101'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6WjNfEOrHwwEEdSZZCRBiTpBMS\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568016,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The capital of France is Paris.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 14,\n \"completion_tokens\":
8,\n \"total_tokens\": 22,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dc63b805cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '355'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999974'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cdbed69c9c63658eb552b07f1220df19
http_version: HTTP/1.1
status_code: 200
version: 1

108
tests/cassettes/test_llm_call_with_string_input.yaml Normal file
View File

@@ -0,0 +1,108 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Return the name of a random
city in the world."}], "model": "gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '117'
content-type:
- application/json
cookie:
- _cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6UtbaNSMpNU9VJKxvn52t5eJTq\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568014,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"How about \\\"Lisbon\\\"? It\u2019s the
capital city of Portugal, known for its rich history and vibrant culture.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 18,\n \"completion_tokens\":
24,\n \"total_tokens\": 42,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dbcaefb5cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:55 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA;
path=/; expires=Wed, 22-Jan-25 18:16:55 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '449'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999971'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_898373758d2eae3cd84814050b2588e3
http_version: HTTP/1.1
status_code: 200
version: 1

102
tests/cassettes/test_llm_call_with_string_input_and_callbacks.yaml Normal file
View File

@@ -0,0 +1,102 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Tell me a joke."}], "model":
"gpt-4o-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '86'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZ6VyjuUcXYpChXmD8rUSy6nSGq8\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568015,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Why did the scarecrow win an award? \\n\\nBecause
he was outstanding in his field!\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
12,\n \"completion_tokens\": 19,\n \"total_tokens\": 31,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90615dc03b6c5cb1-RDU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:46:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '825'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999979'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4c1485d44e7461396d4a7316a63ff353
http_version: HTTP/1.1
status_code: 200
version: 1

111
tests/cassettes/test_llm_call_with_tool_and_message_list.yaml Normal file
View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the square of 5?"}],
"model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
"square_number", "description": "Returns the square of a number.", "parameters":
{"type": "object", "properties": {"number": {"type": "integer", "description":
"The number to square"}}, "required": ["number"]}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '361'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZL5nGOaVpcGnDOesTxBZPHhMoaS\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568919,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_i6JVJ1KxX79A4WzFri98E03U\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"square_number\",\n
\ \"arguments\": \"{\\\"number\\\":5}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
58,\n \"completion_tokens\": 15,\n \"total_tokens\": 73,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 906173d229b905f6-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 18:02:00 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=BYDpIoqfPZyRxl9xcFxkt4IzTUGe8irWQlZ.aYLt8Xc-1737568920-1.0.1.1-Y_cVFN7TbguWRBorSKZynVY02QUtYbsbHuR2gR1wJ8LHuqOF4xIxtK5iHVCpWWgIyPDol9xOXiqUkU8xRV_vHA;
path=/; expires=Wed, 22-Jan-25 18:32:00 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=etTqqA9SBOnENmrFAUBIexdW0v2ZeO1x9_Ek_WChlfU-1737568920137-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '642'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999976'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_388e63f9b8d4edc0dd153001f25388e5
http_version: HTTP/1.1
status_code: 200
version: 1

107
tests/cassettes/test_llm_call_with_tool_and_string_input.yaml Normal file
View File

@@ -0,0 +1,107 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the current year?"}],
"model": "gpt-4o-mini", "tools": [{"type": "function", "function": {"name":
"get_current_year", "description": "Returns the current year as a string.",
"parameters": {"type": "object", "properties": {}, "required": []}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '295'
content-type:
- application/json
cookie:
- _cfuvid=8NrWEBP3dDmc8p2.csR.EdsSwS8zFvzWI1kPICaK_fM-1737568015338-0.0.1.1-604800000;
__cf_bm=pKr3NwXmTZN9rMSlKvEX40VPKbrxF93QwDNHunL2v8Y-1737568015-1.0.1.1-nR0EA7hYIwWpIBYUI53d9xQrUnl5iML6lgz4AGJW4ZGPBDxFma3PZ2cBhlr_hE7wKa5fV3r32eMu_rNWMXD.eA
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AsZJ8HKXQU9nTB7xbGAkKxqrg9BZ2\",\n \"object\":
\"chat.completion\",\n \"created\": 1737568798,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_mfvEs2jngeFloVZpZOHZVaKY\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_current_year\",\n
\ \"arguments\": \"{}\"\n }\n }\n ],\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 46,\n \"completion_tokens\":
12,\n \"total_tokens\": 58,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 906170e038281775-IAD
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 22 Jan 2025 17:59:59 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '416'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999975'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4039a5e5772d1790a3131f0b1ea06139
http_version: HTTP/1.1
status_code: 200
version: 1

117
tests/llm_test.py
View File

@@ -4,6 +4,7 @@ import pytest
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
from crewai.llm import LLM from crewai.llm import LLM
from crewai.tools import tool
from crewai.utilities.token_counter_callback import TokenCalcHandler from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -37,3 +38,119 @@ def test_llm_callback_replacement():
assert usage_metrics_1.successful_requests == 1 assert usage_metrics_1.successful_requests == 1
assert usage_metrics_2.successful_requests == 1 assert usage_metrics_2.successful_requests == 1
assert usage_metrics_1 == calc_handler_1.token_cost_process.get_summary() assert usage_metrics_1 == calc_handler_1.token_cost_process.get_summary()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_string_input():
llm = LLM(model="gpt-4o-mini")
# Test the call method with a string input
result = llm.call("Return the name of a random city in the world.")
assert isinstance(result, str)
assert len(result.strip()) > 0 # Ensure the response is not empty
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_string_input_and_callbacks():
llm = LLM(model="gpt-4o-mini")
calc_handler = TokenCalcHandler(token_cost_process=TokenProcess())
# Test the call method with a string input and callbacks
result = llm.call(
"Tell me a joke.",
callbacks=[calc_handler],
)
usage_metrics = calc_handler.token_cost_process.get_summary()
assert isinstance(result, str)
assert len(result.strip()) > 0
assert usage_metrics.successful_requests == 1
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_message_list():
llm = LLM(model="gpt-4o-mini")
messages = [{"role": "user", "content": "What is the capital of France?"}]
# Test the call method with a list of messages
result = llm.call(messages)
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_tool_and_string_input():
llm = LLM(model="gpt-4o-mini")
def get_current_year() -> str:
"""Returns the current year as a string."""
from datetime import datetime
return str(datetime.now().year)
# Create tool schema
tool_schema = {
"type": "function",
"function": {
"name": "get_current_year",
"description": "Returns the current year as a string.",
"parameters": {
"type": "object",
"properties": {},
"required": [],
},
},
}
# Available functions mapping
available_functions = {"get_current_year": get_current_year}
# Test the call method with a string input and tool
result = llm.call(
"What is the current year?",
tools=[tool_schema],
available_functions=available_functions,
)
assert isinstance(result, str)
assert result == get_current_year()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_tool_and_message_list():
llm = LLM(model="gpt-4o-mini")
def square_number(number: int) -> int:
"""Returns the square of a number."""
return number * number
# Create tool schema
tool_schema = {
"type": "function",
"function": {
"name": "square_number",
"description": "Returns the square of a number.",
"parameters": {
"type": "object",
"properties": {
"number": {"type": "integer", "description": "The number to square"}
},
"required": ["number"],
},
},
}
# Available functions mapping
available_functions = {"square_number": square_number}
messages = [{"role": "user", "content": "What is the square of 5?"}]
# Test the call method with messages and tool
result = llm.call(
messages,
tools=[tool_schema],
available_functions=available_functions,
)
assert isinstance(result, int)
assert result == 25