Compare commits

..

8 Commits

Author SHA1 Message Date
Eduardo Chiarotti
870a092687 feat: add poetry.lock to uv migration 2024-10-18 15:38:24 -03:00
João Moura
53a9f107ca Avoiding exceptions 2024-10-18 08:32:06 -03:00
João Moura
6fa2b89831 fix tasks and agents ordering 2024-10-18 08:06:38 -03:00
João Moura
d72ebb9bb8 fixing annotations 2024-10-18 07:46:30 -03:00
João Moura
81ae07abdb preparing new version 2024-10-18 07:13:17 -03:00
Lorenze Jay
6d20ba70a1 Feat/memory base (#1444)
* byom - short/entity memory

* better

* rm uneeded

* fix text

* use context

* rm dep and sync

* type check fix

* fixed test using new cassete

* fixing types

* fixed types

* fix types

* fixed types

* fixing types

* fix type

* cassette update

* just mock the return of short term mem

* remove print

* try catch block

* added docs

* dding error handling here
2024-10-17 13:19:33 -03:00
Rok Benko
67f55bae2c Fix incorrect parameter name in Vision tool docs page (#1461)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-17 13:18:31 -03:00
Rip&Tear
9b59de1720 feat/updated CLI to allow for model selection & submitting API keys (#1430)
* updated CLI to allow for submitting API keys

* updated click prompt to remove default number

* removed all unnecessary comments

* feat: implement crew creation CLI command

- refactor code to multiple functions
- Added ability for users to select provider and model when uing crewai create command and ave API key to .env

* refactered select_choice function for early return

* refactored  select_provider to have an ealry return

* cleanup of comments

* refactor/Move functions into utils file, added new provider file and migrated fucntions thre, new constants file + general function refactor

* small comment cleanup

* fix unnecessary deps

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-10-17 10:05:07 -04:00
35 changed files with 832 additions and 1041 deletions

23
.github/SECURITY.md vendored
View File

@@ -1,23 +0,0 @@
CrewAI takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organization.
If you believe you have found a security vulnerability in any CrewAI product or service, please report it to us as described below.
## Reporting a Vulnerability
Please do not report security vulnerabilities through public GitHub issues.
To report a vulnerability, please email us at security@crewai.com.
Please include the requested information listed below so that we can triage your report more quickly
- Type of issue (e.g. SQL injection, cross-site scripting, etc.)
- Full paths of source file(s) related to the manifestation of the issue
- The location of the affected source code (tag/branch/commit or direct URL)
- Any special configuration required to reproduce the issue
- Step-by-step instructions to reproduce the issue (please include screenshots if needed)
- Proof-of-concept or exploit code (if possible)
- Impact of the issue, including how an attacker might exploit the issue
Once we have received your report, we will respond to you at the email address you provide. If the issue is confirmed, we will release a patch as soon as possible depending on the complexity of the issue.
At this time, we are not offering a bug bounty program. Any rewards will be at our discretion.

1
.gitignore vendored
View File

@@ -17,4 +17,3 @@ rc-tests/*
temp/*
.vscode/*
crew_tasks_output.json
.dccache

View File

@@ -6,7 +6,7 @@ icon: terminal
# CrewAI CLI Documentation
The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you to create, train, run, and manage crews & flows.
The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you to create, train, run, and manage crews and pipelines.
## Installation
@@ -146,34 +146,3 @@ crewai run
Make sure to run these commands from the directory where your CrewAI project is set up.
Some commands may require additional configuration or setup within your project structure.
</Note>
### 9. API Keys
When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.
Once you've selected an LLM provider, you will be prompted for API keys.
#### Initial API key providers
The CLI will initiallyprompt for API keys for the following services:
* OpenAI
* Groq
* Anthropic
* Google Gemini
When you select a provider, the CLI will prompt you to enter your API key.
#### Other Options
If you select option 6, you will be able to select from a list of LiteLLM supported providers.
When you select a provider, the CLI will prompt you to enter the Key name and the API key.
See the following link for each provider's key name:
* [LiteLLM Providers](https://docs.litellm.ai/docs/providers)

View File

@@ -34,7 +34,7 @@ By default, the memory system is disabled, and you can ensure it is active by se
The memory will use OpenAI embeddings by default, but you can change it by setting `embedder` to a different model.
It's also possible to initialize the memory instance with your own instance.
The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG using the EmbedChain package.
The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG.
The **Long-Term Memory** uses SQLite3 to store task results. Currently, there is no way to override these storage implementations.
The data storage files are saved into a platform-specific location found using the appdirs package,
and the name of the project can be overridden using the **CREWAI_STORAGE_DIR** environment variable.
@@ -105,12 +105,9 @@ my_crew = Crew(
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "openai",
"config": {
"model": 'text-embedding-3-small'
}
}
embedder=embedding_functions.OpenAIEmbeddingFunction(
api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
)
)
```
@@ -125,14 +122,10 @@ my_crew = Crew(
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "google",
"config": {
"model": 'models/embedding-001',
"task_type": "retrieval_document",
"title": "Embeddings for Embedchain"
}
}
embedder=embedding_functions.OpenAIEmbeddingFunction(
api_key=os.getenv("OPENAI_API_KEY"),
model_name="text-embedding-ada-002"
)
)
```
@@ -147,30 +140,13 @@ my_crew = Crew(
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "azure_openai",
"config": {
"model": 'text-embedding-ada-002',
"deployment_name": "your_embedding_model_deployment_name"
}
}
)
```
### Using GPT4ALL embeddings
```python Code
from crewai import Crew, Agent, Task, Process
my_crew = Crew(
agents=[...],
tasks=[...],
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "gpt4all"
}
embedder=embedding_functions.OpenAIEmbeddingFunction(
api_key="YOUR_API_KEY",
api_base="YOUR_API_BASE_PATH",
api_type="azure",
api_version="YOUR_API_VERSION",
model_name="text-embedding-3-small"
)
)
```
@@ -185,12 +161,12 @@ my_crew = Crew(
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "vertexai",
"config": {
"model": 'textembedding-gecko'
}
}
embedder=embedding_functions.GoogleVertexEmbeddingFunction(
project_id="YOUR_PROJECT_ID",
region="YOUR_REGION",
api_key="YOUR_API_KEY",
model_name="textembedding-gecko"
)
)
```
@@ -205,13 +181,10 @@ my_crew = Crew(
process=Process.sequential,
memory=True,
verbose=True,
embedder={
"provider": "cohere",
"config": {
"model": "embed-english-v3.0",
"vector_dimension": 1024
}
}
embedder=embedding_functions.CohereEmbeddingFunction(
api_key=YOUR_API_KEY,
model_name="<model_name>"
)
)
```

View File

@@ -8,13 +8,13 @@ icon: eye
## Description
This tool is used to extract text from images. When passed to the agent it will extract the text from the image and then use it to generate a response, report or any other output.
This tool is used to extract text from images. When passed to the agent it will extract the text from the image and then use it to generate a response, report or any other output.
The URL or the PATH of the image should be passed to the Agent.
## Installation
Install the crewai_tools package
```shell
pip install 'crewai[tools]'
```
@@ -44,7 +44,6 @@ def researcher(self) -> Agent:
The VisionTool requires the following arguments:
| Argument | Type | Description |
|:---------------|:---------|:-------------------------------------------------------------------------------------------------------------------------------------|
| **image_path** | `string` | **Mandatory**. The path to the image file from which text needs to be extracted. |
| Argument | Type | Description |
| :----------------- | :------- | :------------------------------------------------------------------------------- |
| **image_path_url** | `string` | **Mandatory**. The path to the image file from which text needs to be extracted. |

View File

@@ -1,6 +1,6 @@
[project]
name = "crewai"
version = "0.70.1"
version = "0.74.0"
description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
readme = "README.md"
requires-python = ">=3.10,<=3.13"
@@ -16,19 +16,18 @@ dependencies = [
"opentelemetry-exporter-otlp-proto-http>=1.22.0",
"instructor>=1.3.3",
"regex>=2024.9.11",
"crewai-tools>=0.12.1",
"crewai-tools>=0.13.1",
"click>=8.1.7",
"python-dotenv>=1.0.0",
"appdirs>=1.4.4",
"jsonref>=1.1.0",
"agentops>=0.3.0",
"embedchain>=0.1.114",
"json-repair>=0.25.2",
"auth0-python>=4.7.1",
"litellm>=1.44.22",
"pyvis>=0.3.2",
"uv>=0.4.18",
"tomli-w>=1.1.0",
"chromadb>=0.4.24",
]
[project.urls]

View File

@@ -14,5 +14,5 @@ warnings.filterwarnings(
category=UserWarning,
module="pydantic.main",
)
__version__ = "0.70.1"
__version__ = "0.74.0"
__all__ = ["Agent", "Crew", "Process", "Task", "Pipeline", "Router", "LLM", "Flow"]

View File

@@ -1,7 +1,7 @@
import uuid
from abc import ABC, abstractmethod
from copy import copy as shallow_copy
from hashlib import sha256
from hashlib import md5
from typing import Any, Dict, List, Optional, TypeVar
from pydantic import (
@@ -181,7 +181,7 @@ class BaseAgent(ABC, BaseModel):
self._original_goal or self.goal,
self._original_backstory or self.backstory,
]
return sha256("|".join(source).encode()).hexdigest()
return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
@abstractmethod
def execute_task(

View File

@@ -17,7 +17,7 @@ if TYPE_CHECKING:
class CrewAgentExecutorMixin:
crew: Optional["Crew"]
crew_agent: Optional["BaseAgent"]
agent: Optional["BaseAgent"]
task: Optional["Task"]
iterations: int
have_forced_answer: bool
@@ -33,9 +33,9 @@ class CrewAgentExecutorMixin:
"""Create and save a short-term memory item if conditions are met."""
if (
self.crew
and self.crew_agent
and self.agent
and self.task
and "Action: Delegate work to coworker" not in output.log
and "Action: Delegate work to coworker" not in output.text
):
try:
if (
@@ -43,11 +43,11 @@ class CrewAgentExecutorMixin:
and self.crew._short_term_memory
):
self.crew._short_term_memory.save(
value=output.log,
value=output.text,
metadata={
"observation": self.task.description,
},
agent=self.crew_agent.role,
agent=self.agent.role,
)
except Exception as e:
print(f"Failed to add to short term memory: {e}")
@@ -61,18 +61,18 @@ class CrewAgentExecutorMixin:
and self.crew._long_term_memory
and self.crew._entity_memory
and self.task
and self.crew_agent
and self.agent
):
try:
ltm_agent = TaskEvaluator(self.crew_agent)
evaluation = ltm_agent.evaluate(self.task, output.log)
ltm_agent = TaskEvaluator(self.agent)
evaluation = ltm_agent.evaluate(self.task, output.text)
if isinstance(evaluation, ConverterError):
return
long_term_memory = LongTermMemoryItem(
task=self.task.description,
agent=self.crew_agent.role,
agent=self.agent.role,
quality=evaluation.quality,
datetime=str(time.time()),
expected_output=self.task.expected_output,

View File

@@ -19,6 +19,7 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
)
from crewai.utilities.logger import Logger
from crewai.utilities.training_handler import CrewTrainingHandler
from crewai.agents.agent_builder.base_agent import BaseAgent
class CrewAgentExecutor(CrewAgentExecutorMixin):
@@ -29,7 +30,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
llm: Any,
task: Any,
crew: Any,
agent: Any,
agent: BaseAgent,
prompt: dict[str, str],
max_iter: int,
tools: List[Any],
@@ -103,7 +104,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
if self.crew and self.crew._train:
self._handle_crew_training_output(formatted_answer)
self._create_short_term_memory(formatted_answer)
self._create_long_term_memory(formatted_answer)
return {"output": formatted_answer.output}
def _invoke_loop(self, formatted_answer=None):
@@ -176,6 +178,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
return formatted_answer
def _show_start_logs(self):
if self.agent is None:
raise ValueError("Agent cannot be None")
if self.agent.verbose or (
hasattr(self, "crew") and getattr(self.crew, "verbose", False)
):
@@ -188,6 +192,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
)
def _show_logs(self, formatted_answer: Union[AgentAction, AgentFinish]):
if self.agent is None:
raise ValueError("Agent cannot be None")
if self.agent.verbose or (
hasattr(self, "crew") and getattr(self.crew, "verbose", False)
):
@@ -306,7 +312,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
self, result: AgentFinish, human_feedback: str | None = None
) -> None:
"""Function to handle the process of the training data."""
agent_id = str(self.agent.id)
agent_id = str(self.agent.id) # type: ignore
# Load training data
training_handler = CrewTrainingHandler(TRAINING_DATA_FILE)
@@ -339,7 +345,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
"initial_output": result.output,
"human_feedback": human_feedback,
"agent": agent_id,
"agent_role": self.agent.role,
"agent_role": self.agent.role, # type: ignore
}
if self.crew is not None and hasattr(self.crew, "_train_iteration"):
train_iteration = self.crew._train_iteration

View File

@@ -1,14 +1,8 @@
from pathlib import Path
import click
from crewai.cli.utils import copy_template, load_env_vars, write_env_file
from crewai.cli.provider import (
get_provider_data,
select_provider,
select_model,
PROVIDERS,
)
from crewai.cli.provider import get_provider_data, select_provider, PROVIDERS
from crewai.cli.constants import ENV_VARS
import sys
def create_folder_structure(name, parent_folder=None):
@@ -20,19 +14,11 @@ def create_folder_structure(name, parent_folder=None):
else:
folder_path = Path(folder_name)
if folder_path.exists():
if not click.confirm(
f"Folder {folder_name} already exists. Do you want to override it?"
):
click.secho("Operation cancelled.", fg="yellow")
sys.exit(0)
click.secho(f"Overriding folder {folder_name}...", fg="green", bold=True)
else:
click.secho(
f"Creating {'crew' if parent_folder else 'folder'} {folder_name}...",
fg="green",
bold=True,
)
click.secho(
f"Creating {'crew' if parent_folder else 'folder'} {folder_name}...",
fg="green",
bold=True,
)
if not folder_path.exists():
folder_path.mkdir(parents=True)
@@ -41,6 +27,11 @@ def create_folder_structure(name, parent_folder=None):
(folder_path / "src" / folder_name).mkdir(parents=True)
(folder_path / "src" / folder_name / "tools").mkdir(parents=True)
(folder_path / "src" / folder_name / "config").mkdir(parents=True)
else:
click.secho(
f"\tFolder {folder_name} already exists.",
fg="yellow",
)
return folder_path, folder_name, class_name
@@ -83,73 +74,33 @@ def create_crew(name, parent_folder=None):
folder_path, folder_name, class_name = create_folder_structure(name, parent_folder)
env_vars = load_env_vars(folder_path)
existing_provider = None
for provider, env_keys in ENV_VARS.items():
if any(key in env_vars for key in env_keys):
existing_provider = provider
break
if existing_provider:
if not click.confirm(
f"Found existing environment variable configuration for {existing_provider.capitalize()}. Do you want to override it?"
):
click.secho("Keeping existing provider configuration.", fg="yellow")
return
provider_models = get_provider_data()
if not provider_models:
return
while True:
selected_provider = select_provider(provider_models)
if selected_provider is None: # User typed 'q'
click.secho("Exiting...", fg="yellow")
sys.exit(0)
if selected_provider: # Valid selection
break
click.secho(
"No provider selected. Please try again or press 'q' to exit.", fg="red"
)
selected_provider = select_provider(provider_models)
if not selected_provider:
return
provider = selected_provider
while True:
selected_model = select_model(selected_provider, provider_models)
if selected_model is None: # User typed 'q'
click.secho("Exiting...", fg="yellow")
sys.exit(0)
if selected_model: # Valid selection
break
click.secho(
"No model selected. Please try again or press 'q' to exit.", fg="red"
)
# selected_model = select_model(provider, provider_models)
# if not selected_model:
# return
# model = selected_model
if selected_provider in PROVIDERS:
api_key_var = ENV_VARS[selected_provider][0]
if provider in PROVIDERS:
api_key_var = ENV_VARS[provider][0]
else:
api_key_var = click.prompt(
f"Enter the environment variable name for your {selected_provider.capitalize()} API key",
f"Enter the environment variable name for your {provider.capitalize()} API key",
type=str,
default="",
)
api_key_value = ""
click.echo(
f"Enter your {selected_provider.capitalize()} API key (press Enter to skip): ",
nl=False,
)
try:
api_key_value = input()
except (KeyboardInterrupt, EOFError):
api_key_value = ""
env_vars = {api_key_var: "YOUR_API_KEY_HERE"}
write_env_file(folder_path, env_vars)
if api_key_value.strip():
env_vars = {api_key_var: api_key_value}
write_env_file(folder_path, env_vars)
click.secho("API key saved to .env file", fg="green")
else:
click.secho("No API key provided. Skipping .env file creation.", fg="yellow")
env_vars["MODEL"] = selected_model
click.secho(f"Selected model: {selected_model}", fg="green")
# env_vars['MODEL'] = model
# click.secho(f"Selected model: {model}", fg="green")
package_dir = Path(__file__).parent
templates_dir = package_dir / "templates" / "crew"

View File

@@ -6,8 +6,6 @@ import click
from pathlib import Path
from crewai.cli.constants import PROVIDERS, MODELS, JSON_URL
def select_choice(prompt_message, choices):
"""
Presents a list of choices to the user and prompts them to select one.
@@ -17,31 +15,20 @@ def select_choice(prompt_message, choices):
- choices (list): A list of options to present to the user.
Returns:
- str: The selected choice from the list, or None if the user chooses to quit.
- str: The selected choice from the list, or None if the operation is aborted or an invalid selection is made.
"""
provider_models = get_provider_data()
if not provider_models:
return
click.secho(prompt_message, fg="cyan")
for idx, choice in enumerate(choices, start=1):
click.secho(f"{idx}. {choice}", fg="cyan")
click.secho("q. Quit", fg="cyan")
while True:
choice = click.prompt("Enter the number of your choice or 'q' to quit", type=str)
if choice.lower() == 'q':
return None
try:
selected_index = int(choice) - 1
if 0 <= selected_index < len(choices):
return choices[selected_index]
except ValueError:
pass
click.secho("Invalid selection. Please select a number between 1 and 6 or 'q' to quit.", fg="red")
try:
selected_index = click.prompt("Enter the number of your choice", type=int) - 1
except click.exceptions.Abort:
click.secho("Operation aborted by the user.", fg="red")
return None
if not (0 <= selected_index < len(choices)):
click.secho("Invalid selection.", fg="red")
return None
return choices[selected_index]
def select_provider(provider_models):
"""
@@ -51,22 +38,21 @@ def select_provider(provider_models):
- provider_models (dict): A dictionary of provider models.
Returns:
- str: The selected provider
- None: If user explicitly quits
- str: The selected provider, or None if the operation is aborted or an invalid selection is made.
"""
predefined_providers = [p.lower() for p in PROVIDERS]
all_providers = sorted(set(predefined_providers + list(provider_models.keys())))
provider = select_choice("Select a provider to set up:", predefined_providers + ['other'])
if provider is None: # User typed 'q'
if not provider:
return None
provider = provider.lower()
if provider == 'other':
provider = select_choice("Select a provider from the full list:", all_providers)
if provider is None: # User typed 'q'
if not provider:
return None
return provider.lower() if provider else False
return provider
def select_model(provider, provider_models):
"""
@@ -197,4 +183,4 @@ def get_provider_data():
continue
if provider:
provider_models[provider].append(model_name)
return provider_models
return provider_models

View File

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
authors = [{ name = "Your Name", email = "you@example.com" }]
requires-python = ">=3.10,<=3.13"
dependencies = [
"crewai[tools]>=0.67.1,<1.0.0"
"crewai[tools]>=0.74.0,<1.0.0"
]
[project.scripts]

View File

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
authors = [{ name = "Your Name", email = "you@example.com" }]
requires-python = ">=3.10,<=3.13"
dependencies = [
"crewai[tools]>=0.67.1,<1.0.0",
"crewai[tools]>=0.74.0,<1.0.0",
"asyncio"
]

View File

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
[tool.poetry.dependencies]
python = ">=3.10,<=3.13"
crewai = { extras = ["tools"], version = ">=0.70.1,<1.0.0" }
crewai = { extras = ["tools"], version = ">=0.74.0,<1.0.0" }
asyncio = "*"
[tool.poetry.scripts]

View File

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
authors = ["Your Name <you@example.com>"]
requires-python = ">=3.10,<=3.13"
dependencies = [
"crewai[tools]>=0.67.1,<1.0.0"
"crewai[tools]>=0.74.0,<1.0.0"
]
[project.scripts]

View File

@@ -5,6 +5,6 @@ description = "Power up your crews with {{folder_name}}"
readme = "README.md"
requires-python = ">=3.10,<=3.13"
dependencies = [
"crewai[tools]>=0.70.1"
"crewai[tools]>=0.74.0"
]

View File

@@ -1,3 +1,4 @@
import os
import shutil
import tomli_w
@@ -94,6 +95,15 @@ def migrate_pyproject(input_file, output_file):
shutil.copy2(input_file, backup_file)
print(f"Original pyproject.toml backed up as {backup_file}")
# Rename the poetry.lock file
lock_file = "poetry.lock"
lock_backup = "poetry-old.lock"
if os.path.exists(lock_file):
os.rename(lock_file, lock_backup)
print(f"Original poetry.lock renamed to {lock_backup}")
else:
print("No poetry.lock file found to rename.")
# Write the new pyproject.toml
with open(output_file, "wb") as f:
tomli_w.dump(new_pyproject, f)

View File

@@ -4,7 +4,7 @@ import os
import uuid
import warnings
from concurrent.futures import Future
from hashlib import sha256
from hashlib import md5
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
from pydantic import (
@@ -126,8 +126,8 @@ class Crew(BaseModel):
default=None,
description="An Instance of the EntityMemory to be used by the Crew",
)
embedder: Optional[dict] = Field(
default={"provider": "openai"},
embedder: Optional[Any] = Field(
default=None,
description="Configuration for the embedder to be used for the crew.",
)
usage_metrics: Optional[UsageMetrics] = Field(
@@ -388,7 +388,7 @@ class Crew(BaseModel):
source = [agent.key for agent in self.agents] + [
task.key for task in self.tasks
]
return sha256("|".join(source).encode()).hexdigest()
return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
def _setup_from_config(self):
assert self.config is not None, "Config should not be None."
@@ -774,7 +774,9 @@ class Crew(BaseModel):
def _log_task_start(self, task: Task, role: str = "None"):
if self.output_log_file:
self._file_handler.log(task_name=task.name, task=task.description, agent=role, status="started")
self._file_handler.log(
task_name=task.name, task=task.description, agent=role, status="started"
)
def _update_manager_tools(self, task: Task):
if self.manager_agent:
@@ -796,7 +798,13 @@ class Crew(BaseModel):
def _process_task_result(self, task: Task, output: TaskOutput) -> None:
role = task.agent.role if task.agent is not None else "None"
if self.output_log_file:
self._file_handler.log(task_name=task.name, task=task.description, agent=role, status="completed", output=output.raw)
self._file_handler.log(
task_name=task.name,
task=task.description,
agent=role,
status="completed",
output=output.raw,
)
def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
if len(task_outputs) != 1:

View File

@@ -31,7 +31,9 @@ class ContextualMemory:
formatted as bullet points.
"""
stm_results = self.stm.search(query)
formatted_results = "\n".join([f"- {result}" for result in stm_results])
formatted_results = "\n".join(
[f"- {result['context']}" for result in stm_results]
)
return f"Recent Insights:\n{formatted_results}" if stm_results else ""
def _fetch_ltm_context(self, task) -> Optional[str]:

View File

@@ -1,4 +1,4 @@
from typing import Any, Dict
from typing import Any, Dict, List
from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
from crewai.memory.memory import Memory
@@ -28,7 +28,7 @@ class LongTermMemory(Memory):
datetime=item.datetime,
)
def search(self, task: str, latest_n: int = 3) -> Dict[str, Any]:
def search(self, task: str, latest_n: int = 3) -> List[Dict[str, Any]]: # type: ignore # signature of "search" incompatible with supertype "Memory"
return self.storage.load(task, latest_n) # type: ignore # BUG?: "Storage" has no attribute "load"
def reset(self) -> None:

View File

@@ -1,6 +1,6 @@
from typing import Any, Dict, Optional
from typing import Any, Dict, Optional, List
from crewai.memory.storage.interface import Storage
from crewai.memory.storage.rag_storage import RAGStorage
class Memory:
@@ -8,7 +8,7 @@ class Memory:
Base class for memory, now supporting agent tags and generic metadata.
"""
def __init__(self, storage: Storage):
def __init__(self, storage: RAGStorage):
self.storage = storage
def save(
@@ -23,5 +23,5 @@ class Memory:
self.storage.save(value, metadata)
def search(self, query: str) -> Dict[str, Any]:
def search(self, query: str) -> List[Dict[str, Any]]:
return self.storage.search(query)

View File

@@ -0,0 +1,76 @@
from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional
class BaseRAGStorage(ABC):
"""
Base class for RAG-based Storage implementations.
"""
app: Any | None = None
def __init__(
self,
type: str,
allow_reset: bool = True,
embedder_config: Optional[Any] = None,
crew: Any = None,
):
self.type = type
self.allow_reset = allow_reset
self.embedder_config = embedder_config
self.crew = crew
self.agents = self._initialize_agents()
def _initialize_agents(self) -> str:
if self.crew:
return "_".join(
[self._sanitize_role(agent.role) for agent in self.crew.agents]
)
return ""
@abstractmethod
def _sanitize_role(self, role: str) -> str:
"""Sanitizes agent roles to ensure valid directory names."""
pass
@abstractmethod
def save(self, value: Any, metadata: Dict[str, Any]) -> None:
"""Save a value with metadata to the storage."""
pass
@abstractmethod
def search(
self,
query: str,
limit: int = 3,
filter: Optional[dict] = None,
score_threshold: float = 0.35,
) -> List[Any]:
"""Search for entries in the storage."""
pass
@abstractmethod
def reset(self) -> None:
"""Reset the storage."""
pass
@abstractmethod
def _generate_embedding(
self, text: str, metadata: Optional[Dict[str, Any]] = None
) -> Any:
"""Generate an embedding for the given text and metadata."""
pass
@abstractmethod
def _initialize_app(self):
"""Initialize the vector db."""
pass
def setup_config(self, config: Dict[str, Any]):
"""Setup the config of the storage."""
pass
def initialize_client(self):
"""Initialize the client of the storage. This should setup the app and the db collection"""
pass

View File

@@ -1,4 +1,4 @@
from typing import Any, Dict
from typing import Any, Dict, List
class Storage:
@@ -7,7 +7,7 @@ class Storage:
def save(self, value: Any, metadata: Dict[str, Any]) -> None:
pass
def search(self, key: str) -> Dict[str, Any]: # type: ignore
def search(self, key: str) -> List[Dict[str, Any]]: # type: ignore
pass
def reset(self) -> None:

View File

@@ -3,10 +3,11 @@ import io
import logging
import os
import shutil
import uuid
from typing import Any, Dict, List, Optional
from crewai.memory.storage.interface import Storage
from crewai.memory.storage.base_rag_storage import BaseRAGStorage
from crewai.utilities.paths import db_storage_path
from chromadb.api import ClientAPI
@contextlib.contextmanager
@@ -24,61 +25,42 @@ def suppress_logging(
logger.setLevel(original_level)
class RAGStorage(Storage):
class RAGStorage(BaseRAGStorage):
"""
Extends Storage to handle embeddings for memory entries, improving
search efficiency.
"""
def __init__(self, type, allow_reset=True, embedder_config=None, crew=None):
super().__init__()
if (
not os.getenv("OPENAI_API_KEY")
and not os.getenv("OPENAI_BASE_URL") == "https://api.openai.com/v1"
):
os.environ["OPENAI_API_KEY"] = "fake"
app: ClientAPI | None = None
def __init__(self, type, allow_reset=True, embedder_config=None, crew=None):
super().__init__(type, allow_reset, embedder_config, crew)
agents = crew.agents if crew else []
agents = [self._sanitize_role(agent.role) for agent in agents]
agents = "_".join(agents)
self.agents = agents
config = {
"app": {
"config": {"name": type, "collect_metrics": False, "log_level": "ERROR"}
},
"chunker": {
"chunk_size": 5000,
"chunk_overlap": 100,
"length_function": "len",
"min_chunk_size": 150,
},
"vectordb": {
"provider": "chroma",
"config": {
"collection_name": type,
"dir": f"{db_storage_path()}/{type}/{agents}",
"allow_reset": allow_reset,
},
},
}
if embedder_config:
config["embedder"] = embedder_config
self.type = type
self.config = config
self.embedder_config = embedder_config or self._create_embedding_function()
self.allow_reset = allow_reset
self._initialize_app()
def _initialize_app(self):
from embedchain import App
from embedchain.llm.base import BaseLlm
import chromadb
class FakeLLM(BaseLlm):
pass
chroma_client = chromadb.PersistentClient(
path=f"{db_storage_path()}/{self.type}/{self.agents}"
)
self.app = chroma_client
self.app = App.from_config(config=self.config)
self.app.llm = FakeLLM()
if self.allow_reset:
self.app.reset()
try:
self.collection = self.app.get_collection(
name=self.type, embedding_function=self.embedder_config
)
except Exception:
self.collection = self.app.create_collection(
name=self.type, embedding_function=self.embedder_config
)
def _sanitize_role(self, role: str) -> str:
"""
@@ -87,11 +69,14 @@ class RAGStorage(Storage):
return role.replace("\n", "").replace(" ", "_").replace("/", "_")
def save(self, value: Any, metadata: Dict[str, Any]) -> None:
if not hasattr(self, "app"):
if not hasattr(self, "app") or not hasattr(self, "collection"):
self._initialize_app()
self._generate_embedding(value, metadata)
try:
self._generate_embedding(value, metadata)
except Exception as e:
logging.error(f"Error during {self.type} save: {str(e)}")
def search( # type: ignore # BUG?: Signature of "search" incompatible with supertype "Storage"
def search(
self,
query: str,
limit: int = 3,
@@ -100,31 +85,50 @@ class RAGStorage(Storage):
) -> List[Any]:
if not hasattr(self, "app"):
self._initialize_app()
from embedchain.vectordb.chroma import InvalidDimensionException
with suppress_logging():
try:
results = (
self.app.search(query, limit, where=filter)
if filter
else self.app.search(query, limit)
)
except InvalidDimensionException:
self.app.reset()
return []
return [r for r in results if r["metadata"]["score"] >= score_threshold]
try:
with suppress_logging():
response = self.collection.query(query_texts=query, n_results=limit)
def _generate_embedding(self, text: str, metadata: Dict[str, Any]) -> Any:
if not hasattr(self, "app"):
results = []
for i in range(len(response["ids"][0])):
result = {
"id": response["ids"][0][i],
"metadata": response["metadatas"][0][i],
"context": response["documents"][0][i],
"score": response["distances"][0][i],
}
if result["score"] >= score_threshold:
results.append(result)
return results
except Exception as e:
logging.error(f"Error during {self.type} search: {str(e)}")
return []
def _generate_embedding(self, text: str, metadata: Dict[str, Any]) -> None: # type: ignore
if not hasattr(self, "app") or not hasattr(self, "collection"):
self._initialize_app()
from embedchain.models.data_type import DataType
self.app.add(text, data_type=DataType.TEXT, metadata=metadata)
self.collection.add(
documents=[text],
metadatas=[metadata or {}],
ids=[str(uuid.uuid4())],
)
def reset(self) -> None:
try:
shutil.rmtree(f"{db_storage_path()}/{self.type}")
if self.app:
self.app.reset()
except Exception as e:
raise Exception(
f"An error occurred while resetting the {self.type} memory: {e}"
)
def _create_embedding_function(self):
import chromadb.utils.embedding_functions as embedding_functions
return embedding_functions.OpenAIEmbeddingFunction(
api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
)

View File

@@ -76,27 +76,13 @@ def crew(func) -> Callable[..., Crew]:
instantiated_agents = []
agent_roles = set()
# Collect methods from crew in order
all_functions = [
(name, getattr(self, name))
for name, attr in self.__class__.__dict__.items()
if callable(attr)
]
tasks = [
(name, method)
for name, method in all_functions
if hasattr(method, "is_task")
]
agents = [
(name, method)
for name, method in all_functions
if hasattr(method, "is_agent")
]
# Use the preserved task and agent information
tasks = self._original_tasks.items()
agents = self._original_agents.items()
# Instantiate tasks in order
for task_name, task_method in tasks:
task_instance = task_method()
task_instance = task_method(self)
instantiated_tasks.append(task_instance)
agent_instance = getattr(task_instance, "agent", None)
if agent_instance and agent_instance.role not in agent_roles:
@@ -105,7 +91,7 @@ def crew(func) -> Callable[..., Crew]:
# Instantiate agents not included by tasks
for agent_name, agent_method in agents:
agent_instance = agent_method()
agent_instance = agent_method(self)
if agent_instance.role not in agent_roles:
instantiated_agents.append(agent_instance)
agent_roles.add(agent_instance.role)

View File

@@ -34,6 +34,18 @@ def CrewBase(cls: T) -> T:
self.map_all_agent_variables()
self.map_all_task_variables()
# Preserve task and agent information
self._original_tasks = {
name: method
for name, method in cls.__dict__.items()
if hasattr(method, "is_task") and method.is_task
}
self._original_agents = {
name: method
for name, method in cls.__dict__.items()
if hasattr(method, "is_agent") and method.is_agent
}
@staticmethod
def load_yaml(config_path: Path):
try:

View File

@@ -5,7 +5,7 @@ import threading
import uuid
from concurrent.futures import Future
from copy import copy
from hashlib import sha256
from hashlib import md5
from typing import Any, Dict, List, Optional, Set, Tuple, Type, Union
from opentelemetry.trace import Span
@@ -196,7 +196,7 @@ class Task(BaseModel):
expected_output = self._original_expected_output or self.expected_output
source = [description, expected_output]
return sha256("|".join(source).encode()).hexdigest()
return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
def execute_async(
self,

View File

@@ -65,7 +65,7 @@ class Telemetry:
self.provider.add_span_processor(processor)
self.ready = True
except BaseException as e:
except Exception as e:
if isinstance(
e,
(SystemExit, KeyboardInterrupt, GeneratorExit, asyncio.CancelledError),
@@ -83,404 +83,33 @@ class Telemetry:
self.ready = False
self.trace_set = False
def _safe_telemetry_operation(self, operation):
if not self.ready:
return
try:
operation()
except Exception:
pass
def crew_creation(self, crew: Crew, inputs: dict[str, Any] | None):
"""Records the creation of a crew."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Created")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "python_version", platform.python_version())
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "crew_process", crew.process)
self._add_attribute(span, "crew_memory", crew.memory)
self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
if crew.share_crew:
self._add_attribute(
span,
"crew_agents",
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"goal": agent.goal,
"backstory": agent.backstory,
"verbose?": agent.verbose,
"max_iter": agent.max_iter,
"max_rpm": agent.max_rpm,
"i18n": agent.i18n.prompt_file,
"function_calling_llm": (
agent.function_calling_llm.model
if agent.function_calling_llm
else ""
),
"llm": agent.llm.model,
"delegation_enabled?": agent.allow_delegation,
"allow_code_execution?": agent.allow_code_execution,
"max_retry_limit": agent.max_retry_limit,
"tools_names": [
tool.name.casefold()
for tool in agent.tools or []
],
}
for agent in crew.agents
]
),
)
self._add_attribute(
span,
"crew_tasks",
json.dumps(
[
{
"key": task.key,
"id": str(task.id),
"description": task.description,
"expected_output": task.expected_output,
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": (
task.agent.role if task.agent else "None"
),
"agent_key": task.agent.key if task.agent else None,
"context": (
[task.description for task in task.context]
if task.context
else None
),
"tools_names": [
tool.name.casefold()
for tool in task.tools or []
],
}
for task in crew.tasks
]
),
)
self._add_attribute(span, "platform", platform.platform())
self._add_attribute(span, "platform_release", platform.release())
self._add_attribute(span, "platform_system", platform.system())
self._add_attribute(span, "platform_version", platform.version())
self._add_attribute(span, "cpus", os.cpu_count())
self._add_attribute(
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
else:
self._add_attribute(
span,
"crew_agents",
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"verbose?": agent.verbose,
"max_iter": agent.max_iter,
"max_rpm": agent.max_rpm,
"function_calling_llm": (
agent.function_calling_llm.model
if agent.function_calling_llm
else ""
),
"llm": agent.llm.model,
"delegation_enabled?": agent.allow_delegation,
"allow_code_execution?": agent.allow_code_execution,
"max_retry_limit": agent.max_retry_limit,
"tools_names": [
tool.name.casefold()
for tool in agent.tools or []
],
}
for agent in crew.agents
]
),
)
self._add_attribute(
span,
"crew_tasks",
json.dumps(
[
{
"key": task.key,
"id": str(task.id),
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": (
task.agent.role if task.agent else "None"
),
"agent_key": task.agent.key if task.agent else None,
"tools_names": [
tool.name.casefold()
for tool in task.tools or []
],
}
for task in crew.tasks
]
),
)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def task_started(self, crew: Crew, task: Task) -> Span | None:
"""Records task started in a crew."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
created_span = tracer.start_span("Task Created")
self._add_attribute(created_span, "crew_key", crew.key)
self._add_attribute(created_span, "crew_id", str(crew.id))
self._add_attribute(created_span, "task_key", task.key)
self._add_attribute(created_span, "task_id", str(task.id))
if crew.share_crew:
self._add_attribute(
created_span, "formatted_description", task.description
)
self._add_attribute(
created_span, "formatted_expected_output", task.expected_output
)
created_span.set_status(Status(StatusCode.OK))
created_span.end()
span = tracer.start_span("Task Execution")
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "task_key", task.key)
self._add_attribute(span, "task_id", str(task.id))
if crew.share_crew:
self._add_attribute(span, "formatted_description", task.description)
self._add_attribute(
span, "formatted_expected_output", task.expected_output
)
return span
except Exception:
pass
return None
def task_ended(self, span: Span, task: Task, crew: Crew):
"""Records task execution in a crew."""
if self.ready:
try:
if crew.share_crew:
self._add_attribute(
span,
"task_output",
task.output.raw if task.output else "",
)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
"""Records the repeated usage 'error' of a tool by an agent."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Repeated Usage")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "tool_name", tool_name)
self._add_attribute(span, "attempts", attempts)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def tool_usage(self, llm: Any, tool_name: str, attempts: int):
"""Records the usage of a tool by an agent."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Usage")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "tool_name", tool_name)
self._add_attribute(span, "attempts", attempts)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def tool_usage_error(self, llm: Any):
"""Records the usage of a tool by an agent."""
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Usage Error")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def individual_test_result_span(
self, crew: Crew, quality: float, exec_time: int, model_name: str
):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Individual Test Result")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "quality", str(quality))
self._add_attribute(span, "exec_time", str(exec_time))
self._add_attribute(span, "model_name", model_name)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def test_execution_span(
self,
crew: Crew,
iterations: int,
inputs: dict[str, Any] | None,
model_name: str,
):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Test Execution")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "iterations", str(iterations))
self._add_attribute(span, "model_name", model_name)
if crew.share_crew:
self._add_attribute(
span, "inputs", json.dumps(inputs) if inputs else None
)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def deploy_signup_error_span(self):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Deploy Signup Error")
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def start_deployment_span(self, uuid: Optional[str] = None):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Start Deployment")
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def create_crew_deployment_span(self):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Create Crew Deployment")
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def get_crew_logs_span(self, uuid: Optional[str], log_type: str = "deployment"):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Get Crew Logs")
self._add_attribute(span, "log_type", log_type)
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def remove_crew_span(self, uuid: Optional[str] = None):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Remove Crew")
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def crew_execution_span(self, crew: Crew, inputs: dict[str, Any] | None):
"""Records the complete execution of a crew.
This is only collected if the user has opted-in to share the crew.
"""
self.crew_creation(crew, inputs)
if (self.ready) and (crew.share_crew):
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Execution")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Created")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "python_version", platform.python_version())
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "crew_process", crew.process)
self._add_attribute(span, "crew_memory", crew.memory)
self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
if crew.share_crew:
self._add_attribute(
span,
"crew_agents",
@@ -496,8 +125,15 @@ class Telemetry:
"max_iter": agent.max_iter,
"max_rpm": agent.max_rpm,
"i18n": agent.i18n.prompt_file,
"function_calling_llm": (
agent.function_calling_llm.model
if agent.function_calling_llm
else ""
),
"llm": agent.llm.model,
"delegation_enabled?": agent.allow_delegation,
"allow_code_execution?": agent.allow_code_execution,
"max_retry_limit": agent.max_retry_limit,
"tools_names": [
tool.name.casefold() for tool in agent.tools or []
],
@@ -512,12 +148,15 @@ class Telemetry:
json.dumps(
[
{
"key": task.key,
"id": str(task.id),
"description": task.description,
"expected_output": task.expected_output,
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": task.agent.role if task.agent else "None",
"agent_role": (
task.agent.role if task.agent else "None"
),
"agent_key": task.agent.key if task.agent else None,
"context": (
[task.description for task in task.context]
@@ -532,78 +171,433 @@ class Telemetry:
]
),
)
return span
except Exception:
pass
def end_crew(self, crew, final_string_output):
if (self.ready) and (crew.share_crew):
try:
self._add_attribute(span, "platform", platform.platform())
self._add_attribute(span, "platform_release", platform.release())
self._add_attribute(span, "platform_system", platform.system())
self._add_attribute(span, "platform_version", platform.version())
self._add_attribute(span, "cpus", os.cpu_count())
self._add_attribute(
crew._execution_span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
else:
self._add_attribute(
crew._execution_span, "crew_output", final_string_output
)
self._add_attribute(
crew._execution_span,
"crew_tasks_output",
span,
"crew_agents",
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"verbose?": agent.verbose,
"max_iter": agent.max_iter,
"max_rpm": agent.max_rpm,
"function_calling_llm": (
agent.function_calling_llm.model
if agent.function_calling_llm
else ""
),
"llm": agent.llm.model,
"delegation_enabled?": agent.allow_delegation,
"allow_code_execution?": agent.allow_code_execution,
"max_retry_limit": agent.max_retry_limit,
"tools_names": [
tool.name.casefold() for tool in agent.tools or []
],
}
for agent in crew.agents
]
),
)
self._add_attribute(
span,
"crew_tasks",
json.dumps(
[
{
"key": task.key,
"id": str(task.id),
"description": task.description,
"output": task.output.raw_output,
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": (
task.agent.role if task.agent else "None"
),
"agent_key": task.agent.key if task.agent else None,
"tools_names": [
tool.name.casefold() for tool in task.tools or []
],
}
for task in crew.tasks
]
),
)
crew._execution_span.set_status(Status(StatusCode.OK))
crew._execution_span.end()
except Exception:
pass
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def task_started(self, crew: Crew, task: Task) -> Span | None:
"""Records task started in a crew."""
def operation():
tracer = trace.get_tracer("crewai.telemetry")
created_span = tracer.start_span("Task Created")
self._add_attribute(created_span, "crew_key", crew.key)
self._add_attribute(created_span, "crew_id", str(crew.id))
self._add_attribute(created_span, "task_key", task.key)
self._add_attribute(created_span, "task_id", str(task.id))
if crew.share_crew:
self._add_attribute(
created_span, "formatted_description", task.description
)
self._add_attribute(
created_span, "formatted_expected_output", task.expected_output
)
created_span.set_status(Status(StatusCode.OK))
created_span.end()
span = tracer.start_span("Task Execution")
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "task_key", task.key)
self._add_attribute(span, "task_id", str(task.id))
if crew.share_crew:
self._add_attribute(span, "formatted_description", task.description)
self._add_attribute(
span, "formatted_expected_output", task.expected_output
)
return span
return self._safe_telemetry_operation(operation)
def task_ended(self, span: Span, task: Task, crew: Crew):
"""Records task execution in a crew."""
def operation():
if crew.share_crew:
self._add_attribute(
span,
"task_output",
task.output.raw if task.output else "",
)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
"""Records the repeated usage 'error' of a tool by an agent."""
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Repeated Usage")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "tool_name", tool_name)
self._add_attribute(span, "attempts", attempts)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def tool_usage(self, llm: Any, tool_name: str, attempts: int):
"""Records the usage of a tool by an agent."""
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Usage")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "tool_name", tool_name)
self._add_attribute(span, "attempts", attempts)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def tool_usage_error(self, llm: Any):
"""Records the usage of a tool by an agent."""
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Tool Usage Error")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
if llm:
self._add_attribute(span, "llm", llm.model)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def individual_test_result_span(
self, crew: Crew, quality: float, exec_time: int, model_name: str
):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Individual Test Result")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "quality", str(quality))
self._add_attribute(span, "exec_time", str(exec_time))
self._add_attribute(span, "model_name", model_name)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def test_execution_span(
self,
crew: Crew,
iterations: int,
inputs: dict[str, Any] | None,
model_name: str,
):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Test Execution")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(span, "iterations", str(iterations))
self._add_attribute(span, "model_name", model_name)
if crew.share_crew:
self._add_attribute(
span, "inputs", json.dumps(inputs) if inputs else None
)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def deploy_signup_error_span(self):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Deploy Signup Error")
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def start_deployment_span(self, uuid: Optional[str] = None):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Start Deployment")
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def create_crew_deployment_span(self):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Create Crew Deployment")
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def get_crew_logs_span(self, uuid: Optional[str], log_type: str = "deployment"):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Get Crew Logs")
self._add_attribute(span, "log_type", log_type)
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def remove_crew_span(self, uuid: Optional[str] = None):
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Remove Crew")
if uuid:
self._add_attribute(span, "uuid", uuid)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def crew_execution_span(self, crew: Crew, inputs: dict[str, Any] | None):
"""Records the complete execution of a crew.
This is only collected if the user has opted-in to share the crew.
"""
self.crew_creation(crew, inputs)
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Crew Execution")
self._add_attribute(
span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(span, "crew_key", crew.key)
self._add_attribute(span, "crew_id", str(crew.id))
self._add_attribute(
span, "crew_inputs", json.dumps(inputs) if inputs else None
)
self._add_attribute(
span,
"crew_agents",
json.dumps(
[
{
"key": agent.key,
"id": str(agent.id),
"role": agent.role,
"goal": agent.goal,
"backstory": agent.backstory,
"verbose?": agent.verbose,
"max_iter": agent.max_iter,
"max_rpm": agent.max_rpm,
"i18n": agent.i18n.prompt_file,
"llm": agent.llm.model,
"delegation_enabled?": agent.allow_delegation,
"tools_names": [
tool.name.casefold() for tool in agent.tools or []
],
}
for agent in crew.agents
]
),
)
self._add_attribute(
span,
"crew_tasks",
json.dumps(
[
{
"id": str(task.id),
"description": task.description,
"expected_output": task.expected_output,
"async_execution?": task.async_execution,
"human_input?": task.human_input,
"agent_role": task.agent.role if task.agent else "None",
"agent_key": task.agent.key if task.agent else None,
"context": (
[task.description for task in task.context]
if task.context
else None
),
"tools_names": [
tool.name.casefold() for tool in task.tools or []
],
}
for task in crew.tasks
]
),
)
return span
if crew.share_crew:
return self._safe_telemetry_operation(operation)
return None
def end_crew(self, crew, final_string_output):
def operation():
self._add_attribute(
crew._execution_span,
"crewai_version",
pkg_resources.get_distribution("crewai").version,
)
self._add_attribute(
crew._execution_span, "crew_output", final_string_output
)
self._add_attribute(
crew._execution_span,
"crew_tasks_output",
json.dumps(
[
{
"id": str(task.id),
"description": task.description,
"output": task.output.raw_output,
}
for task in crew.tasks
]
),
)
crew._execution_span.set_status(Status(StatusCode.OK))
crew._execution_span.end()
if crew.share_crew:
self._safe_telemetry_operation(operation)
def _add_attribute(self, span, key, value):
"""Add an attribute to a span."""
try:
def operation():
return span.set_attribute(key, value)
except Exception:
pass
self._safe_telemetry_operation(operation)
def flow_creation_span(self, flow_name: str):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Creation")
self._add_attribute(span, "flow_name", flow_name)
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Creation")
self._add_attribute(span, "flow_name", flow_name)
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def flow_plotting_span(self, flow_name: str, node_names: list[str]):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Plotting")
self._add_attribute(span, "flow_name", flow_name)
self._add_attribute(span, "node_names", json.dumps(node_names))
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Plotting")
self._add_attribute(span, "flow_name", flow_name)
self._add_attribute(span, "node_names", json.dumps(node_names))
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)
def flow_execution_span(self, flow_name: str, node_names: list[str]):
if self.ready:
try:
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Execution")
self._add_attribute(span, "flow_name", flow_name)
self._add_attribute(span, "node_names", json.dumps(node_names))
span.set_status(Status(StatusCode.OK))
span.end()
except Exception:
pass
def operation():
tracer = trace.get_tracer("crewai.telemetry")
span = tracer.start_span("Flow Execution")
self._add_attribute(span, "flow_name", flow_name)
self._add_attribute(span, "node_names", json.dumps(node_names))
span.set_status(Status(StatusCode.OK))
span.end()
self._safe_telemetry_operation(operation)

View File

@@ -1,4 +1,4 @@
from hashlib import sha256
import hashlib
from typing import Any, List, Optional
from crewai.agents.agent_builder.base_agent import BaseAgent
@@ -32,5 +32,5 @@ def test_key():
goal="test goal",
backstory="test backstory",
)
hash = sha256("test role|test goal|test backstory".encode()).hexdigest()
hash = hashlib.md5("test role|test goal|test backstory".encode()).hexdigest()
assert agent.key == hash

View File

@@ -1,6 +1,6 @@
"""Test Agent creation and execution basic functionality."""
from hashlib import sha256
import hashlib
import json
from concurrent.futures import Future
from unittest import mock
@@ -2328,7 +2328,7 @@ def test_key():
process=Process.sequential,
tasks=tasks,
)
hash = sha256(
hash = hashlib.md5(
f"{researcher.key}|{writer.key}|{tasks[0].key}|{tasks[1].key}".encode()
).hexdigest()
@@ -2368,7 +2368,7 @@ def test_key_with_interpolated_inputs():
process=Process.sequential,
tasks=tasks,
)
hash = sha256(
hash = hashlib.md5(
f"{researcher.key}|{writer.key}|{tasks[0].key}|{tasks[1].key}".encode()
).hexdigest()

File diff suppressed because one or more lines are too long

View File

@@ -1,5 +1,5 @@
import pytest
from unittest.mock import patch
from crewai.agent import Agent
from crewai.crew import Crew
from crewai.memory.short_term.short_term_memory import ShortTermMemory
@@ -26,7 +26,6 @@ def short_term_memory():
return ShortTermMemory(crew=Crew(agents=[agent], tasks=[task]))
@pytest.mark.vcr(filter_headers=["authorization"])
def test_save_and_search(short_term_memory):
memory = ShortTermMemoryItem(
data="""test value test value test value test value test value test value
@@ -35,12 +34,28 @@ def test_save_and_search(short_term_memory):
agent="test_agent",
metadata={"task": "test_task"},
)
short_term_memory.save(
value=memory.data,
metadata=memory.metadata,
agent=memory.agent,
)
find = short_term_memory.search("test value", score_threshold=0.01)[0]
assert find["context"] == memory.data, "Data value mismatch."
assert find["metadata"]["agent"] == "test_agent", "Agent value mismatch."
with patch.object(ShortTermMemory, "save") as mock_save:
short_term_memory.save(
value=memory.data,
metadata=memory.metadata,
agent=memory.agent,
)
mock_save.assert_called_once_with(
value=memory.data,
metadata=memory.metadata,
agent=memory.agent,
)
expected_result = [
{
"context": memory.data,
"metadata": {"agent": "test_agent"},
"score": 0.95,
}
]
with patch.object(ShortTermMemory, "search", return_value=expected_result):
find = short_term_memory.search("test value", score_threshold=0.01)[0]
assert find["context"] == memory.data, "Data value mismatch."
assert find["metadata"]["agent"] == "test_agent", "Agent value mismatch."

View File

@@ -1,6 +1,6 @@
"""Test Agent creation and execution basic functionality."""
from hashlib import sha256
import hashlib
import json
import os
from unittest.mock import MagicMock, patch
@@ -819,7 +819,7 @@ def test_key():
description=original_description,
expected_output=original_expected_output,
)
hash = sha256(
hash = hashlib.md5(
f"{original_description}|{original_expected_output}".encode()
).hexdigest()

102
uv.lock generated
View File

@@ -627,15 +627,14 @@ wheels = [
[[package]]
name = "crewai"
version = "0.67.1"
version = "0.74.0"
source = { editable = "." }
dependencies = [
{ name = "agentops" },
{ name = "appdirs" },
{ name = "auth0-python" },
{ name = "chromadb" },
{ name = "click" },
{ name = "crewai-tools" },
{ name = "embedchain" },
{ name = "instructor" },
{ name = "json-repair" },
{ name = "jsonref" },
@@ -683,14 +682,13 @@ dev = [
[package.metadata]
requires-dist = [
{ name = "agentops", specifier = ">=0.3.0" },
{ name = "agentops", marker = "extra == 'agentops'", specifier = ">=0.3.0" },
{ name = "appdirs", specifier = ">=1.4.4" },
{ name = "auth0-python", specifier = ">=4.7.1" },
{ name = "chromadb", specifier = ">=0.4.24" },
{ name = "click", specifier = ">=8.1.7" },
{ name = "crewai-tools", specifier = ">=0.12.1" },
{ name = "crewai-tools", specifier = ">=0.13.1" },
{ name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.12.1" },
{ name = "embedchain", specifier = ">=0.1.114" },
{ name = "instructor", specifier = ">=1.3.3" },
{ name = "json-repair", specifier = ">=0.25.2" },
{ name = "jsonref", specifier = ">=1.1.0" },
@@ -730,7 +728,7 @@ dev = [
[[package]]
name = "crewai-tools"
version = "0.12.1"
version = "0.13.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "beautifulsoup4" },
@@ -748,9 +746,9 @@ dependencies = [
{ name = "requests" },
{ name = "selenium" },
]
sdist = { url = "https://files.pythonhosted.org/packages/11/60/1860127d927939f9143cab9af059cfbe6f160839b6ba1d652a9ed4e04fa6/crewai_tools-0.12.1.tar.gz", hash = "sha256:22fa3ea57936913faed77a2a64c131371f78b2ced207e63dcc71220eac445698", size = 420190 }
sdist = { url = "https://files.pythonhosted.org/packages/d5/81/b8a0bb984aea2af49b0072e074c87c75a6c4581902b81f3a3d46f95f01c7/crewai_tools-0.13.1.tar.gz", hash = "sha256:363c7ec717f4c6f9b61cec9314a5ec2fbd026d75e8e6278f49f715ed5915cd4d", size = 816254 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/23/e6/cc9acbc6ee828898956b18036643fc2150b6c1b976ab34f29b9cadc085b5/crewai_tools-0.12.1-py3-none-any.whl", hash = "sha256:e87d393dd1900834a224686644e025eb44e74171f317c4ff2df778aff6ade4b8", size = 463435 },
{ url = "https://files.pythonhosted.org/packages/09/8a/04c885da3e01d1f11478dd866d3506906bfb60d7587627dd4b132ff10f64/crewai_tools-0.13.1-py3-none-any.whl", hash = "sha256:62067e2502bf66c0ae2e3a833c60b900bd1f793a9a80895a1f10a9cfa1b5dc3c", size = 463444 },
]
[[package]]
@@ -921,7 +919,7 @@ wheels = [
[[package]]
name = "embedchain"
version = "0.1.122"
version = "0.1.123"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "alembic" },
@@ -934,6 +932,7 @@ dependencies = [
{ name = "langchain-cohere" },
{ name = "langchain-community" },
{ name = "langchain-openai" },
{ name = "langsmith" },
{ name = "mem0ai" },
{ name = "openai" },
{ name = "posthog" },
@@ -945,9 +944,9 @@ dependencies = [
{ name = "sqlalchemy" },
{ name = "tiktoken" },
]
sdist = { url = "https://files.pythonhosted.org/packages/25/9b/fa14dc95f8736c672bcebd677f48990670f1a9fac8ea1631222b8b820d69/embedchain-0.1.122.tar.gz", hash = "sha256:ea0a4d00a4a1909e0d662dc499fa6a0da119783ec4773df1271da74da3e8296b", size = 124799 }
sdist = { url = "https://files.pythonhosted.org/packages/5d/6a/955b5a72fa6727db203c4d46ae0e30ac47f4f50389f663cd5ea157b0d819/embedchain-0.1.123.tar.gz", hash = "sha256:aecaf81c21de05b5cdb649b6cde95ef68ffa759c69c54f6ff2eaa667f2ad0580", size = 124797 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/95/3f/42c97c1d3c9483076843987982a018115b6a28be02091fb475e6dbc743f2/embedchain-0.1.122-py3-none-any.whl", hash = "sha256:c137be81d0949b5ee16c689837d659837980cfabbb38643c2720cd1a794d8d27", size = 210911 },
{ url = "https://files.pythonhosted.org/packages/a7/51/0c78d26da4afbe68370306669556b274f1021cac02f3155d8da2be407763/embedchain-0.1.123-py3-none-any.whl", hash = "sha256:1210e993b6364d7c702b6bd44b053fc244dd77f2a65ea4b90b62709114ea6c25", size = 210909 },
]
[[package]]
@@ -1551,7 +1550,7 @@ wheels = [
[[package]]
name = "httpx"
version = "0.27.2"
version = "0.27.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "anyio" },
@@ -1560,9 +1559,9 @@ dependencies = [
{ name = "idna" },
{ name = "sniffio" },
]
sdist = { url = "https://files.pythonhosted.org/packages/78/82/08f8c936781f67d9e6b9eeb8a0c8b4e406136ea4c3d1f89a5db71d42e0e6/httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2", size = 144189 }
sdist = { url = "https://files.pythonhosted.org/packages/5c/2d/3da5bdf4408b8b2800061c339f240c1802f2e82d55e50bd39c5a881f47f0/httpx-0.27.0.tar.gz", hash = "sha256:a0cb88a46f32dc874e04ee956e4c2764aba2aa228f650b06788ba6bda2962ab5", size = 126413 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/56/95/9377bcb415797e44274b51d46e3249eba641711cf3348050f76ee7b15ffc/httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0", size = 76395 },
{ url = "https://files.pythonhosted.org/packages/41/7b/ddacf6dcebb42466abd03f368782142baa82e08fc0c1f8eaa05b4bae87d5/httpx-0.27.0-py3-none-any.whl", hash = "sha256:71d5465162c13681bff01ad59b2cc68dd838ea1f10e51574bac27103f00c91a5", size = 75590 },
]
[package.optional-dependencies]
@@ -1908,7 +1907,7 @@ wheels = [
[[package]]
name = "langchain"
version = "0.2.16"
version = "0.3.3"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "aiohttp" },
@@ -1923,30 +1922,31 @@ dependencies = [
{ name = "sqlalchemy" },
{ name = "tenacity" },
]
sdist = { url = "https://files.pythonhosted.org/packages/fd/53/8ebf21de8d17e7e0f0998f28d689f60d7ed420acb7ab2fba59ca04e80e54/langchain-0.2.16.tar.gz", hash = "sha256:ffb426a76a703b73ac69abad77cd16eaf03dda76b42cff55572f592d74944166", size = 414668 }
sdist = { url = "https://files.pythonhosted.org/packages/70/b2/258c6a33b5e5f817a57ecd22b1e74756f7246ac66f39d0cf6d2ef515fcb7/langchain-0.3.3.tar.gz", hash = "sha256:6435882996a029a60c61c356bbe51bab4a8f43a54210f5f03e3c4474d19d1842", size = 416891 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/0d/29/635343c0d155997569b544d26da5a2a9ebade2423baffc9cd6066b01a386/langchain-0.2.16-py3-none-any.whl", hash = "sha256:8f59ee8b45f268df4b924ea3b9c63e49286efa756d16b3f6a9de5c6e502c36e1", size = 1001195 },
{ url = "https://files.pythonhosted.org/packages/92/82/c17abaa44074ec716409305da4783f633b0eb9b09bb28ed5005220269bdb/langchain-0.3.3-py3-none-any.whl", hash = "sha256:05ac98c674853c2386d043172820e37ceac9b913aaaf1e51217f0fc424112c72", size = 1005176 },
]
[[package]]
name = "langchain-cohere"
version = "0.1.9"
version = "0.3.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "cohere" },
{ name = "langchain-core" },
{ name = "langchain-experimental" },
{ name = "pandas" },
{ name = "pydantic" },
{ name = "tabulate" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a4/a9/30462b68f8c15da886078fe5c96fab3085241168ea03d968eee1182e00a9/langchain_cohere-0.1.9.tar.gz", hash = "sha256:549620d23bc3d77f62d1045787095fe2c1cfa233dba69455139f9a2f65f952fa", size = 29987 }
sdist = { url = "https://files.pythonhosted.org/packages/ae/ea/53fd2515e353cac4ddd6d7a41dbb0651dfc9ffb0924acb7a1aa7a722f29b/langchain_cohere-0.3.1.tar.gz", hash = "sha256:990bd4db68e229371c90eee98a1a78b4f4d33a32c22c8da6c2cd30b5044de9eb", size = 36739 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/52/b1/ee8d44898cfe43703f05a0ffd95294d3ebe4c61879f19c6357c860131312/langchain_cohere-0.1.9-py3-none-any.whl", hash = "sha256:96d6a15125797319474ac84b54024e5024f3f5fc45032ebf228d95d6998c9b13", size = 35218 },
{ url = "https://files.pythonhosted.org/packages/64/5e/bbfb1b33703a973e7eef6582b523ae932e7e64c9b84ac7eecaa8af71475e/langchain_cohere-0.3.1-py3-none-any.whl", hash = "sha256:adf37542feb293562791b8dd1691580b0dcb2117fb987f2684f694912465f554", size = 43992 },
]
[[package]]
name = "langchain-community"
version = "0.2.17"
version = "0.3.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "aiohttp" },
@@ -1955,19 +1955,20 @@ dependencies = [
{ name = "langchain-core" },
{ name = "langsmith" },
{ name = "numpy" },
{ name = "pydantic-settings" },
{ name = "pyyaml" },
{ name = "requests" },
{ name = "sqlalchemy" },
{ name = "tenacity" },
]
sdist = { url = "https://files.pythonhosted.org/packages/1f/54/be928e3962d24b40c31899f5c5ed99b0c7ef7c3bb7601eb2fe7a6ce75dc4/langchain_community-0.2.17.tar.gz", hash = "sha256:b0745c1fcf1bd532ed4388f90b47139d6a6c6ba48a87aa68aa32d4d6bb97259d", size = 1589425 }
sdist = { url = "https://files.pythonhosted.org/packages/86/6e/119bbbd4d55ab14dc6fc4a82a2466b88f7ddb989bdbdfcf96327c5daba4e/langchain_community-0.3.2.tar.gz", hash = "sha256:469bf5357a08c915cebc4c506dca4617eec737d82a9b6e340df5f3b814dc89bc", size = 1608524 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ac/33/c6ee472412f751062311075bb391a7870ab57cdb8da5d47f359895b2d3c2/langchain_community-0.2.17-py3-none-any.whl", hash = "sha256:d07c31b641e425fb8c3e7148ad6a62e1b54a9adac6e1173021a7dd3148266063", size = 2339964 },
{ url = "https://files.pythonhosted.org/packages/cc/57/a8b4826eaa29d3663c957251ab32275a0c178bdb0e262a1204ed820f430c/langchain_community-0.3.2-py3-none-any.whl", hash = "sha256:fffcd484c7674e81ceaa72a809962338bfb17ec8f9e0377ce4e9d884e6fe8ca5", size = 2367818 },
]
[[package]]
name = "langchain-core"
version = "0.2.41"
version = "0.3.12"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "jsonpatch" },
@@ -1978,48 +1979,48 @@ dependencies = [
{ name = "tenacity" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/2a/92/2ad97f0c23b5ee5043df1a93d97edd4404136003e7d22b641de081738408/langchain_core-0.2.41.tar.gz", hash = "sha256:bc12032c5a298d85be754ccb129bc13ea21ccb1d6e22f8d7ba18b8da64315bb5", size = 316952 }
sdist = { url = "https://files.pythonhosted.org/packages/7b/15/76ec101e550e7e16de85e64fcb4ff2d281cb70cfe65c95ee6e56182a5f51/langchain_core-0.3.12.tar.gz", hash = "sha256:98a3c078e375786aa84939bfd1111263af2f3bc402bbe2cac9fa18a387459cf2", size = 327019 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/bc/02/2b2cf9550cee1a7ffa42fe60c55e2d0e7d397535609b42562611fb40e78d/langchain_core-0.2.41-py3-none-any.whl", hash = "sha256:3278fda5ba9a05defae8bb19f1226032add6aab21917db7b3bc74e750e263e84", size = 397013 },
{ url = "https://files.pythonhosted.org/packages/ce/4a/a6499d93805c3e6316e641b6934e23c98c011d00b9a2138835d567e976e5/langchain_core-0.3.12-py3-none-any.whl", hash = "sha256:46050d34f5fa36dc57dca971c6a26f505643dd05ee0492c7ac286d0a78a82037", size = 407737 },
]
[[package]]
name = "langchain-experimental"
version = "0.0.65"
version = "0.3.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "langchain-community" },
{ name = "langchain-core" },
]
sdist = { url = "https://files.pythonhosted.org/packages/e1/e0/d92210398a006f6e43ddd25166537f79cb3e9ccc32e316e70d349353842b/langchain_experimental-0.0.65.tar.gz", hash = "sha256:83706df07d8a7e6ec1bda74174add7e4431b5f4a8818e19b65986b94c9c99b25", size = 138516 }
sdist = { url = "https://files.pythonhosted.org/packages/bf/41/84d3eac564261aaab45bc02bdc43b5e49242439c6f2844a24b81404a17cd/langchain_experimental-0.3.2.tar.gz", hash = "sha256:d41cc28c46f58616d18a1230595929f80a58d1982c4053dc3afe7f1c03f22426", size = 139583 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/97/ca/93913b7530b36869946ca8f93b161bea294ea46a367e748943a78bc3553c/langchain_experimental-0.0.65-py3-none-any.whl", hash = "sha256:2a0f268cfb8c79d43cedf9c4840f70bd8b25934e595311e6690804d0355dd7ee", size = 207160 },
{ url = "https://files.pythonhosted.org/packages/63/f6/d80592aa8d335af734054f5cfe130ecd38fdfb9c4f90ba0007f0419f2fce/langchain_experimental-0.3.2-py3-none-any.whl", hash = "sha256:b6a26f2a05e056a27ad30535ed306a6b9d8cc2e3c0326d15030d11b6e7505dbb", size = 208126 },
]
[[package]]
name = "langchain-openai"
version = "0.1.25"
version = "0.2.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "langchain-core" },
{ name = "openai" },
{ name = "tiktoken" },
]
sdist = { url = "https://files.pythonhosted.org/packages/2f/cb/98fe365f2e5eee39d0130279959a84182ab414879b666ffc2b9d69b95633/langchain_openai-0.1.25.tar.gz", hash = "sha256:eb116f744f820247a72f54313fb7c01524fba0927120d4e899e5e4ab41ad3928", size = 45224 }
sdist = { url = "https://files.pythonhosted.org/packages/55/4c/0a88c51192b0aeef5212019060da7112191750ab7a185195d8b45835578c/langchain_openai-0.2.2.tar.gz", hash = "sha256:9ae8e2ec7d1ca84fd3bfa82186724528d68e1510a1dc9cdf617a7c669b7a7768", size = 42364 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/7f/2e/a4430cad7a98e29e9612648f8b12d7449ab635a742c19bf1d62f8713ecaa/langchain_openai-0.1.25-py3-none-any.whl", hash = "sha256:f0b34a233d0d9cb8fce6006c903e57085c493c4f0e32862b99063b96eaedb109", size = 51550 },
{ url = "https://files.pythonhosted.org/packages/b0/4e/c62ce98a5412f031f7f03dda5c35b6ed474e0083986261073ca9da5554d5/langchain_openai-0.2.2-py3-none-any.whl", hash = "sha256:3a203228cb38e4711ebd8c0a3bd51854e447f1d017e8475b6467b07ce7dd3e88", size = 49687 },
]
[[package]]
name = "langchain-text-splitters"
version = "0.2.4"
version = "0.3.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "langchain-core" },
]
sdist = { url = "https://files.pythonhosted.org/packages/83/b3/b1ccde47c86c5fe2585dc012555cff7949c556bd6993dd9c09e49a356190/langchain_text_splitters-0.2.4.tar.gz", hash = "sha256:f7daa7a3b0aa8309ce248e2e2b6fc8115be01118d336c7f7f7dfacda0e89bf29", size = 20236 }
sdist = { url = "https://files.pythonhosted.org/packages/57/35/08ac1ca01c58da825f070bd1fdc9192a9ff52c0a048f74c93b05df70c127/langchain_text_splitters-0.3.0.tar.gz", hash = "sha256:f9fe0b4d244db1d6de211e7343d4abc4aa90295aa22e1f0c89e51f33c55cd7ce", size = 20234 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/8f/f3/d01591229e9d0eec1e8106ed6f9b670f299beb1c94fed4aa335afa78acb0/langchain_text_splitters-0.2.4-py3-none-any.whl", hash = "sha256:2702dee5b7cbdd595ccbe43b8d38d01a34aa8583f4d6a5a68ad2305ae3e7b645", size = 25552 },
{ url = "https://files.pythonhosted.org/packages/da/6a/d1303b722a3fa7a0a8c2f8f5307e42f0bdbded46d99cca436f3db0df5294/langchain_text_splitters-0.3.0-py3-none-any.whl", hash = "sha256:e84243e45eaff16e5b776cd9c81b6d07c55c010ebcb1965deb3d1792b7358e83", size = 25543 },
]
[[package]]
@@ -2166,7 +2167,7 @@ wheels = [
[[package]]
name = "mem0ai"
version = "0.1.17"
version = "0.1.19"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "langchain-community" },
@@ -2179,9 +2180,9 @@ dependencies = [
{ name = "rank-bm25" },
{ name = "sqlalchemy" },
]
sdist = { url = "https://files.pythonhosted.org/packages/9b/23/fc537f7125c88efeb81190b661b4e17786d039d4e00da2975ea253b45c8f/mem0ai-0.1.17.tar.gz", hash = "sha256:3b24c5904c96717c2285847f7ad98be0167421fd67b23c19771e81bef00ec2f1", size = 51167 }
sdist = { url = "https://files.pythonhosted.org/packages/6e/12/23f8f250a2ce798a51841417acbbfc9c12c294d3ae427e81a0a0dbab54f6/mem0ai-0.1.19.tar.gz", hash = "sha256:faf7c198a85df2f502ac41fe2bc1593ca0383f993b431a4e4a36e0aed3fa533c", size = 51167 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/89/49/4fa5e5f759004e90fa9b4adbc9f224f09f09e182bf3d4dfebed69b10fe8a/mem0ai-0.1.17-py3-none-any.whl", hash = "sha256:6505bc45880c26b25edf0a17242d71939ebaab27be0ae09b77f25fd400f61b76", size = 73252 },
{ url = "https://files.pythonhosted.org/packages/7e/43/04d22bc9cac6fa19b10a405c59c21e94b8ae2a180b40307ec4a577f6ee39/mem0ai-0.1.19-py3-none-any.whl", hash = "sha256:dfff9cfe191072abd34ed8bb4fcbee2819603eed430d89611ef3181b1a46fff9", size = 73240 },
]
[[package]]
@@ -2496,6 +2497,8 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b2/07/8cbb75d6cfbe8712d8f7f6a5615f083c6e710ab916b748fbb20373ddb142/multiprocess-0.70.17-py311-none-any.whl", hash = "sha256:2884701445d0177aec5bd5f6ee0df296773e4fb65b11903b94c613fb46cfb7d1", size = 144346 },
{ url = "https://files.pythonhosted.org/packages/a4/69/d3f343a61a2f86ef10ed7865a26beda7c71554136ce187b0384b1c2c9ca3/multiprocess-0.70.17-py312-none-any.whl", hash = "sha256:2818af14c52446b9617d1b0755fa70ca2f77c28b25ed97bdaa2c69a22c47b46c", size = 147990 },
{ url = "https://files.pythonhosted.org/packages/c8/b7/2e9a4fcd871b81e1f2a812cd5c6fb52ad1e8da7bf0d7646c55eaae220484/multiprocess-0.70.17-py313-none-any.whl", hash = "sha256:20c28ca19079a6c879258103a6d60b94d4ffe2d9da07dda93fb1c8bc6243f522", size = 149843 },
{ url = "https://files.pythonhosted.org/packages/ae/d7/fd7a092fc0ab1845a1a97ca88e61b9b7cc2e9d6fcf0ed24e9480590c2336/multiprocess-0.70.17-py38-none-any.whl", hash = "sha256:1d52f068357acd1e5bbc670b273ef8f81d57863235d9fbf9314751886e141968", size = 132635 },
{ url = "https://files.pythonhosted.org/packages/f9/41/0618ac724b8a56254962c143759e04fa01c73b37aa69dd433f16643bd38b/multiprocess-0.70.17-py39-none-any.whl", hash = "sha256:c3feb874ba574fbccfb335980020c1ac631fbf2a3f7bee4e2042ede62558a021", size = 133359 },
]
[[package]]
@@ -3179,8 +3182,6 @@ version = "5.9.8"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/90/c7/6dc0a455d111f68ee43f27793971cf03fe29b6ef972042549db29eec39a2/psutil-5.9.8.tar.gz", hash = "sha256:6be126e3225486dff286a8fb9a06246a5253f4c7c53b475ea5f5ac934e64194c", size = 503247 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/fe/5f/c26deb822fd3daf8fde4bdb658bf87d9ab1ffd3fca483816e89a9a9a9084/psutil-5.9.8-cp27-none-win32.whl", hash = "sha256:36f435891adb138ed3c9e58c6af3e2e6ca9ac2f365efe1f9cfef2794e6c93b4e", size = 248660 },
{ url = "https://files.pythonhosted.org/packages/32/1d/cf66073d74d6146187e2d0081a7616df4437214afa294ee4f16f80a2f96a/psutil-5.9.8-cp27-none-win_amd64.whl", hash = "sha256:bd1184ceb3f87651a67b2708d4c3338e9b10c5df903f2e3776b62303b26cb631", size = 251966 },
{ url = "https://files.pythonhosted.org/packages/e7/e3/07ae864a636d70a8a6f58da27cb1179192f1140d5d1da10886ade9405797/psutil-5.9.8-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:aee678c8720623dc456fa20659af736241f575d79429a0e5e9cf88ae0605cc81", size = 248702 },
{ url = "https://files.pythonhosted.org/packages/b3/bd/28c5f553667116b2598b9cc55908ec435cb7f77a34f2bff3e3ca765b0f78/psutil-5.9.8-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8cb6403ce6d8e047495a701dc7c5bd788add903f8986d523e3e20b98b733e421", size = 285242 },
{ url = "https://files.pythonhosted.org/packages/c5/4f/0e22aaa246f96d6ac87fe5ebb9c5a693fbe8877f537a1022527c47ca43c5/psutil-5.9.8-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d06016f7f8625a1825ba3732081d77c94589dca78b7a3fc072194851e88461a4", size = 288191 },
@@ -3387,6 +3388,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/a9/f9/b6bcaf874f410564a78908739c80861a171788ef4d4f76f5009656672dfe/pydantic_core-2.23.4-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:9a5bce9d23aac8f0cf0836ecfc033896aa8443b501c58d0602dbfd5bd5b37753", size = 1920344 },
]
[[package]]
name = "pydantic-settings"
version = "2.6.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "pydantic" },
{ name = "python-dotenv" },
]
sdist = { url = "https://files.pythonhosted.org/packages/6c/66/5f1a9da10675bfb3b9da52f5b689c77e0a5612263fcce510cfac3e99a168/pydantic_settings-2.6.0.tar.gz", hash = "sha256:44a1804abffac9e6a30372bb45f6cafab945ef5af25e66b1c634c01dd39e0188", size = 75232 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/34/19/26bb6bdb9fdad5f0dfce538780814084fb667b4bc37fcb28459c14b8d3b5/pydantic_settings-2.6.0-py3-none-any.whl", hash = "sha256:4a819166f119b74d7f8c765196b165f95cc7487ce58ea27dec8a5a26be0970e0", size = 28578 },
]
[[package]]
name = "pygments"
version = "2.18.0"
@@ -3436,14 +3450,14 @@ wheels = [
[[package]]
name = "pypdf"
version = "4.3.1"
version = "5.0.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "typing-extensions", marker = "python_full_version < '3.11'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/f0/65/2ed7c9e1d31d860f096061b3dd2d665f501e09faaa0409a3f0d719d2a16d/pypdf-4.3.1.tar.gz", hash = "sha256:b2f37fe9a3030aa97ca86067a56ba3f9d3565f9a791b305c7355d8392c30d91b", size = 293266 }
sdist = { url = "https://files.pythonhosted.org/packages/9d/28/6bc2ca8a521512f2904e6aa3028af43a864fe2b66c77ea01bbbc97f52b98/pypdf-5.0.1.tar.gz", hash = "sha256:a361c3c372b4a659f9c8dd438d5ce29a753c79c620dc6e1fd66977651f5547ea", size = 4999113 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/3c/60/eccdd92dd4af3e4bea6d6a342f7588c618a15b9bec4b968af581e498bcc4/pypdf-4.3.1-py3-none-any.whl", hash = "sha256:64b31da97eda0771ef22edb1bfecd5deee4b72c3d1736b7df2689805076d6418", size = 295825 },
{ url = "https://files.pythonhosted.org/packages/48/8f/9bbf22ba6a00001a45dbc54337e5bbbd43e7d8f34c8158c92cddc45736af/pypdf-5.0.1-py3-none-any.whl", hash = "sha256:ff8a32da6c7a63fea9c32fa4dd837cdd0db7966adf6c14f043e3f12592e992db", size = 294470 },
]
[[package]]