Create codeql.yml

* Update issue templates

Add both Bug and Feature templates

* Update feature_request.md

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,35 @@
+---
+name: Bug report
+about: Create a report to help us improve CrewAI
+title: "[BUG]"
+labels: bug
+assignees: ''
+
+---
+
+**Description**
+Provide a clear and concise description of what the bug is.
+
+**Steps to Reproduce**
+Provide a step-by-step process to reproduce the behavior:
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots/Code snippets**
+If applicable, add screenshots or code snippets to help explain your problem.
+
+**Environment Details:**
+- **Operating System**: [e.g., Ubuntu 20.04, macOS Catalina, Windows 10]
+- **Python Version**: [e.g., 3.8, 3.9, 3.10]
+- **crewAI Version**: [e.g., 0.30.11]
+- **crewAI Tools Version**: [e.g., 0.2.6]
+
+**Logs**
+Include relevant logs or error messages if applicable.
+
+**Possible Solution**
+Have a solution in mind? Please suggest it here, or write "None".
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,21 @@
+---
+name: Feature request
+about: Suggest a Feature to improve CrewAI
+title: "[FEAT]"
+labels: feature-request, improvement
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+If possible attach the Issue related to it
+
+**Describe the solution you'd like / Use-case**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/codeql.yml

@@ -0,0 +1,93 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  schedule:
+    - cron: '28 20 * * 1'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: python
+          build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      shell: bash
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

docs/core-concepts/Pipeline.md

@@ -1,196 +0,0 @@
----
-title: crewAI Pipelines
-description: Understanding and utilizing pipelines in the crewAI framework for efficient multi-stage task processing.
----
-
-## What is a Pipeline?
-
-A pipeline in crewAI represents a structured workflow that allows for the sequential or parallel execution of multiple crews. It provides a way to organize complex processes involving multiple stages, where the output of one stage can serve as input for subsequent stages.
-
-## Key Terminology
-
-Understanding the following terms is crucial for working effectively with pipelines:
-
-- **Stage**: A distinct part of the pipeline, which can be either sequential (a single crew) or parallel (multiple crews executing concurrently).
-- **Run**: A specific execution of the pipeline for a given set of inputs, representing a single instance of processing through the pipeline.
-- **Branch**: Parallel executions within a stage (e.g., concurrent crew operations).
-- **Trace**: The journey of an individual input through the entire pipeline, capturing the path and transformations it undergoes.
-
-Example pipeline structure:
-
-```
-crew1 >> [crew2, crew3] >> crew4
-```
-
-This represents a pipeline with three stages:
-
-1. A sequential stage (crew1)
-2. A parallel stage with two branches (crew2 and crew3 executing concurrently)
-3. Another sequential stage (crew4)
-
-Each input creates its own run, flowing through all stages of the pipeline. Multiple runs can be processed concurrently, each following the defined pipeline structure.
-
-## Pipeline Attributes
-
-| Attribute  | Parameters | Description                                                                           |
-| :--------- | :--------- | :------------------------------------------------------------------------------------ |
-| **Stages** | `stages`   | A list of crews or lists of crews representing the stages to be executed in sequence. |
-
-## Creating a Pipeline
-
-When creating a pipeline, you define a series of stages, each consisting of either a single crew or a list of crews for parallel execution. The pipeline ensures that each stage is executed in order, with the output of one stage feeding into the next.
-
-### Example: Assembling a Pipeline
-
-```python
-from crewai import Crew, Agent, Task, Pipeline
-
-# Define your crews
-research_crew = Crew(
-    agents=[researcher],
-    tasks=[research_task],
-    process=Process.sequential
-)
-
-analysis_crew = Crew(
-    agents=[analyst],
-    tasks=[analysis_task],
-    process=Process.sequential
-)
-
-writing_crew = Crew(
-    agents=[writer],
-    tasks=[writing_task],
-    process=Process.sequential
-)
-
-# Assemble the pipeline
-my_pipeline = Pipeline(
-    stages=[research_crew, analysis_crew, writing_crew]
-)
-```
-
-## Pipeline Methods
-
-| Method           | Description                                                                                                                                                                    |
-| :--------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **process_runs** | Executes the pipeline, processing all stages and returning the results. This method initiates one or more runs through the pipeline, handling the flow of data between stages. |
-
-## Pipeline Output
-
-!!! note "Understanding Pipeline Outputs"
-The output of a pipeline in the crewAI framework is encapsulated within two main classes: `PipelineOutput` and `PipelineRunResult`. These classes provide a structured way to access the results of the pipeline's execution, including various formats such as raw strings, JSON, and Pydantic models.
-
-### Pipeline Output Attributes
-
-| Attribute       | Parameters    | Type                      | Description                                                                                               |
-| :-------------- | :------------ | :------------------------ | :-------------------------------------------------------------------------------------------------------- |
-| **ID**          | `id`          | `UUID4`                   | A unique identifier for the pipeline output.                                                              |
-| **Run Results** | `run_results` | `List[PipelineRunResult]` | A list of `PipelineRunResult` objects, each representing the output of a single run through the pipeline. |
-
-### Pipeline Output Methods
-
-| Method/Property    | Description                                            |
-| :----------------- | :----------------------------------------------------- |
-| **add_run_result** | Adds a `PipelineRunResult` to the list of run results. |
-
-### Pipeline Run Result Attributes
-
-| Attribute         | Parameters      | Type                       | Description                                                                                   |
-| :---------------- | :-------------- | :------------------------- | :-------------------------------------------------------------------------------------------- |
-| **ID**            | `id`            | `UUID4`                    | A unique identifier for the run result.                                                       |
-| **Raw**           | `raw`           | `str`                      | The raw output of the final stage in the pipeline run.                                        |
-| **Pydantic**      | `pydantic`      | `Optional[BaseModel]`      | A Pydantic model object representing the structured output of the final stage, if applicable. |
-| **JSON Dict**     | `json_dict`     | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the final stage, if applicable.                  |
-| **Token Usage**   | `token_usage`   | `Dict[str, Any]`           | A summary of token usage across all stages of the pipeline run.                               |
-| **Trace**         | `trace`         | `List[Any]`                | A trace of the journey of inputs through the pipeline run.                                    |
-| **Crews Outputs** | `crews_outputs` | `List[CrewOutput]`         | A list of `CrewOutput` objects, representing the outputs from each crew in the pipeline run.  |
-
-### Pipeline Run Result Methods and Properties
-
-| Method/Property | Description                                                                                              |
-| :-------------- | :------------------------------------------------------------------------------------------------------- |
-| **json**        | Returns the JSON string representation of the run result if the output format of the final task is JSON. |
-| **to_dict**     | Converts the JSON and Pydantic outputs to a dictionary.                                                  |
-| \***\*str\*\*** | Returns the string representation of the run result, prioritizing Pydantic, then JSON, then raw.         |
-
-### Accessing Pipeline Outputs
-
-Once a pipeline has been executed, its output can be accessed through the `PipelineOutput` object returned by the `process_runs` method. The `PipelineOutput` class provides access to individual `PipelineRunResult` objects, each representing a single run through the pipeline.
-
-#### Example
-
-```python
-# Define input data for the pipeline
-input_data = [{"initial_query": "Latest advancements in AI"}, {"initial_query": "Future of robotics"}]
-
-# Execute the pipeline
-pipeline_output = await my_pipeline.process_runs(input_data)
-
-# Access the results
-for run_result in pipeline_output.run_results:
-    print(f"Run ID: {run_result.id}")
-    print(f"Final Raw Output: {run_result.raw}")
-    if run_result.json_dict:
-        print(f"JSON Output: {json.dumps(run_result.json_dict, indent=2)}")
-    if run_result.pydantic:
-        print(f"Pydantic Output: {run_result.pydantic}")
-    print(f"Token Usage: {run_result.token_usage}")
-    print(f"Trace: {run_result.trace}")
-    print("Crew Outputs:")
-    for crew_output in run_result.crews_outputs:
-        print(f"  Crew: {crew_output.raw}")
-    print("\n")
-```
-
-This example demonstrates how to access and work with the pipeline output, including individual run results and their associated data.
-
-## Using Pipelines
-
-Pipelines are particularly useful for complex workflows that involve multiple stages of processing, analysis, or content generation. They allow you to:
-
-1. **Sequence Operations**: Execute crews in a specific order, ensuring that the output of one crew is available as input to the next.
-2. **Parallel Processing**: Run multiple crews concurrently within a stage for increased efficiency.
-3. **Manage Complex Workflows**: Break down large tasks into smaller, manageable steps executed by specialized crews.
-
-### Example: Running a Pipeline
-
-```python
-# Define input data for the pipeline
-input_data = [{"initial_query": "Latest advancements in AI"}]
-
-# Execute the pipeline, initiating a run for each input
-results = await my_pipeline.process_runs(input_data)
-
-# Access the results
-for result in results:
-    print(f"Final Output: {result.raw}")
-    print(f"Token Usage: {result.token_usage}")
-    print(f"Trace: {result.trace}")  # Shows the path of the input through all stages
-```
-
-## Advanced Features
-
-### Parallel Execution within Stages
-
-You can define parallel execution within a stage by providing a list of crews, creating multiple branches:
-
-```python
-parallel_analysis_crew = Crew(agents=[financial_analyst], tasks=[financial_analysis_task])
-market_analysis_crew = Crew(agents=[market_analyst], tasks=[market_analysis_task])
-
-my_pipeline = Pipeline(
-    stages=[
-        research_crew,
-        [parallel_analysis_crew, market_analysis_crew],  # Parallel execution (branching)
-        writing_crew
-    ]
-)
-```
-
-### Error Handling and Validation
-
-The Pipeline class includes validation mechanisms to ensure the robustness of the pipeline structure:
-
-- Validates that stages contain only Crew instances or lists of Crew instances.
-- Prevents double nesting of stages to maintain a clear structure.

docs/getting-started/Start-a-New-CrewAI-Project-Template-Method.md

@@ -20,7 +20,7 @@ Before getting started with CrewAI, make sure that you have installed it via pip
 $ pip install crewai crewai-tools
 ```
 
-### Virtual Environemnts
+### Virtual Environments
 It is highly recommended that you use virtual environments to ensure that your CrewAI project is isolated from other projects and dependencies. Virtual environments provide a clean, separate workspace for each project, preventing conflicts between different versions of packages and libraries. This isolation is crucial for maintaining consistency and reproducibility in your development process. You have multiple options for setting up virtual environments depending on your operating system and Python version:
 
 1. Use venv (Python's built-in virtual environment tool):

docs/how-to/Create-Custom-Tools.md

@@ -7,6 +7,7 @@ description: Comprehensive guide on crafting, using, and managing custom tools w
 This guide provides detailed instructions on creating custom tools for the crewAI framework and how to efficiently manage and utilize these tools, incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools, enabling agents to perform a wide range of actions.
 
 ### Prerequisites
+
 Before creating your own tools, ensure you have the crewAI extra tools package installed:
 
 ```bash
@@ -31,7 +32,7 @@ class MyCustomTool(BaseTool):
 
 ### Using the `tool` Decorator
 
-Alternatively, use the `tool` decorator for a direct approach to create tools. This requires specifying attributes and the tool's logic within a function.
+Alternatively, you can use the tool decorator `@tool`. This approach allows you to define the tool's attributes and functionality directly within a function, offering a concise and efficient way to create specialized tools tailored to your needs.
 
 ```python
 from crewai_tools import tool

docs/how-to/Force-Tool-Ouput-as-Result.md

@@ -16,7 +16,7 @@ Here's an example of how to force the tool output as the result of an agent's ta
 # Define a custom tool that returns the result as the answer
 coding_agent =Agent(
         role="Data Scientist",
-        goal="Product amazing resports on AI",
+        goal="Product amazing reports on AI",
         backstory="You work with data and AI",
         tools=[MyCustomTool(result_as_answer=True)],
     )

docs/how-to/LLM-Connections.md

@@ -6,33 +6,25 @@ description: Comprehensive guide on integrating CrewAI with various Large Langua
 ## Connect CrewAI to LLMs
 
 !!! note "Default LLM"
-    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
+    By default, CrewAI uses OpenAI's GPT-4o model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
+    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4") for language processing. You can configure your agents to use a different model or API as described in this guide.
 
-CrewAI offers flexibility in connecting to various LLMs, including local models via [Ollama](https://ollama.ai) and different APIs like Azure. It's compatible with all [LangChain LLM](https://python.langchain.com/docs/integrations/llms/) components, enabling diverse integrations for tailored AI solutions.
+CrewAI provides extensive versatility in integrating with various Language Models (LLMs), including local options through Ollama such as  Llama and Mixtral to cloud-based solutions like Azure. Its compatibility extends to all [LangChain LLM components](https://python.langchain.com/v0.2/docs/integrations/llms/), offering a wide range of integration possibilities for customized AI applications.
 
-## CrewAI Agent Overview
+The platform supports connections to an array of Generative AI models, including:
 
-The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's a comprehensive overview of the Agent class attributes and methods:
+ - OpenAI's suite of advanced language models
+ - Anthropic's cutting-edge AI offerings
+ - Ollama's diverse range of locally-hosted generative model & embeddings
+ - LM Studio's diverse range of locally hosted generative models & embeddings
+ - Groq's Super Fast LLM offerings
+ - Azures' generative AI offerings
+ - HuggingFace's generative AI offerings
 
-- **Attributes**:
-    - `role`: Defines the agent's role within the solution.
-    - `goal`: Specifies the agent's objective.
-    - `backstory`: Provides a background story to the agent.
-    - `cache` *Optional*: Determines whether the agent should use a cache for tool usage. Default is `True`.
-    - `max_rpm` *Optional*: Maximum number of requests per minute the agent's execution should respect. Optional.
-    - `verbose` *Optional*: Enables detailed logging of the agent's execution. Default is `False`.
-    - `allow_delegation` *Optional*: Allows the agent to delegate tasks to other agents, default is `True`.
-    - `tools`: Specifies the tools available to the agent for task execution. Optional.
-    - `max_iter` *Optional*: Maximum number of iterations for an agent to execute a task, default is 25.
-    - `max_execution_time` *Optional*: Maximum execution time for an agent to execute a task. Optional.
-    - `step_callback` *Optional*: Provides a callback function to be executed after each step. Optional.
-    - `llm` *Optional*: Indicates the Large Language Model the agent uses. By default, it uses the GPT-4 model defined in the environment variable "OPENAI_MODEL_NAME".
-    - `function_calling_llm` *Optional* :  Will turn the ReAct CrewAI agent into a function-calling agent.
-    - `callbacks` *Optional*: A list of callback functions from the LangChain library that are triggered during the agent's execution process.
-    - `system_template` *Optional*: Optional string to define the system format for the agent.
-    - `prompt_template` *Optional*: Optional string to define the prompt format for the agent.
-    - `response_template` *Optional*: Optional string to define the response format for the agent.
+This broad spectrum of LLM options enables users to select the most suitable model for their specific needs, whether prioritizing local deployment, specialized capabilities, or cloud-based scalability.
 
+## Changing the default LLM
+The default LLM is provided through the `langchain openai` package, which is installed by default when you install CrewAI. You can change this default LLM to a different model or API by setting the `OPENAI_MODEL_NAME` environment variable. This straightforward process allows you to harness the power of different OpenAI models, enhancing the flexibility and capabilities of your CrewAI implementation.
 ```python
 # Required
 os.environ["OPENAI_MODEL_NAME"]="gpt-4-0125-preview"
@@ -45,30 +37,27 @@ example_agent = Agent(
   verbose=True
 )
 ```
+## Ollama Local Integration
+Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, you will need the `langchain-ollama` package. You can then set the following environment variables to connect to your Ollama instance running locally on port 11434.
 
-## Ollama Integration
-Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, set the appropriate environment variables as shown below.
-
-### Setting Up Ollama
-- **Environment Variables Configuration**: To integrate Ollama, set the following environment variables:
 ```sh
-OPENAI_API_BASE='http://localhost:11434'
-OPENAI_MODEL_NAME='llama2'  # Adjust based on available model
-OPENAI_API_KEY=''
+os.environ[OPENAI_API_BASE]='http://localhost:11434'
+os.environ[OPENAI_MODEL_NAME]='llama2'  # Adjust based on available model
+os.environ[OPENAI_API_KEY]='' # No API Key required for Ollama
 ```
 
-## Ollama Integration (ex. for using Llama 2 locally)
-1. [Download Ollama](https://ollama.com/download).   
-2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.   
-3. Enjoy your free Llama2 model that powered up by excellent agents from crewai.   
+## Ollama Integration Step by Step (ex. for using Llama 3.1 8B locally)
+1. [Download and install Ollama](https://ollama.com/download).   
+2. After setting up the Ollama, Pull the Llama3.1 8B model by typing following lines into your terminal ```ollama run llama3.1```.   
+3. Llama3.1 should now be served locally on `http://localhost:11434`
 ```
 from crewai import Agent, Task, Crew
-from langchain.llms import Ollama
+from langchain_ollama import ChatOllama
 import os
 os.environ["OPENAI_API_KEY"] = "NA"
 
 llm = Ollama(
-    model = "llama2",
+    model = "llama3.1",
     base_url = "http://localhost:11434")
 
 general_agent = Agent(role = "Math Professor",
@@ -98,13 +87,14 @@ There are a couple of different ways you can use HuggingFace to host your LLM.
 
 ### Your own HuggingFace endpoint
 ```python
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import HuggingFaceEndpoint,
 
 llm = HuggingFaceEndpoint(
-    endpoint_url="<YOUR_ENDPOINT_URL_HERE>",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
+    repo_id="microsoft/Phi-3-mini-4k-instruct",
     task="text-generation",
-    max_new_tokens=512
+    max_new_tokens=512,
+    do_sample=False,
+    repetition_penalty=1.03,
 )
 
 agent = Agent(
@@ -115,66 +105,50 @@ agent = Agent(
 )
 ```
 
-### From HuggingFaceHub endpoint
-```python
-from langchain_community.llms import HuggingFaceHub
-
-llm = HuggingFaceHub(
-    repo_id="HuggingFaceH4/zephyr-7b-beta",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
-    task="text-generation",
-)
-```
-
 ## OpenAI Compatible API Endpoints
 Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
 
 ### Configuration Examples
 #### FastChat
 ```sh
-OPENAI_API_BASE="http://localhost:8001/v1"
-OPENAI_MODEL_NAME='oh-2.5m7b-q51'
-OPENAI_API_KEY=NA
+os.environ[OPENAI_API_BASE]="http://localhost:8001/v1"
+os.environ[OPENAI_MODEL_NAME]='oh-2.5m7b-q51'
+os.environ[OPENAI_API_KEY]=NA
 ```
 
 #### LM Studio
 Launch [LM Studio](https://lmstudio.ai) and go to the Server tab. Then select a model from the dropdown menu and wait for it to load. Once it's loaded, click the green Start Server button and use the URL, port, and API key that's shown (you can modify them). Below is an example of the default settings as of LM Studio 0.2.19:
 ```sh
-OPENAI_API_BASE="http://localhost:1234/v1"
-OPENAI_API_KEY="lm-studio"
+os.environ[OPENAI_API_BASE]="http://localhost:1234/v1"
+os.environ[OPENAI_API_KEY]="lm-studio"
 ```
 
 #### Groq API
 ```sh
-OPENAI_API_KEY=your-groq-api-key
-OPENAI_MODEL_NAME='llama3-8b-8192'
-OPENAI_API_BASE=https://api.groq.com/openai/v1
+os.environ[OPENAI_API_KEY]=your-groq-api-key
+os.environ[OPENAI_MODEL_NAME]='llama3-8b-8192'
+os.environ[OPENAI_API_BASE]=https://api.groq.com/openai/v1
 ```
 
 #### Mistral API
 ```sh
-OPENAI_API_KEY=your-mistral-api-key
-OPENAI_API_BASE=https://api.mistral.ai/v1
-OPENAI_MODEL_NAME="mistral-small"
+os.environ[OPENAI_API_KEY]=your-mistral-api-key
+os.environ[OPENAI_API_BASE]=https://api.mistral.ai/v1
+os.environ[OPENAI_MODEL_NAME]="mistral-small"
 ```
 
 ### Solar
-```python
+```sh
 from langchain_community.chat_models.solar import SolarChat
-# Initialize language model
-os.environ["SOLAR_API_KEY"] = "your-solar-api-key"
-llm = SolarChat(max_tokens=1024)
+```
+```sh
+os.environ[SOLAR_API_BASE]="https://api.upstage.ai/v1/solar"
+os.environ[SOLAR_API_KEY]="your-solar-api-key"
+```
 
 # Free developer API key available here: https://console.upstage.ai/services/solar
 # Langchain Example: https://github.com/langchain-ai/langchain/pull/18556
-```
 
-### text-gen-web-ui
-```sh
-OPENAI_API_BASE=http://localhost:5000/v1
-OPENAI_MODEL_NAME=NA
-OPENAI_API_KEY=NA
-```
 
 ### Cohere
 ```python
@@ -190,10 +164,11 @@ llm = ChatCohere()
 ### Azure Open AI Configuration
 For Azure OpenAI API integration, set the following environment variables:
 ```sh
-AZURE_OPENAI_VERSION="2022-12-01"
-AZURE_OPENAI_DEPLOYMENT=""
-AZURE_OPENAI_ENDPOINT=""
-AZURE_OPENAI_KEY=""
+
+os.environ[AZURE_OPENAI_DEPLOYMENT] = "You deployment"
+os.environ["OPENAI_API_VERSION"] = "2023-12-01-preview"
+os.environ["AZURE_OPENAI_ENDPOINT"] = "Your Endpoint"
+os.environ["AZURE_OPENAI_API_KEY"] = "<Your API Key>"
 ```
 
 ### Example Agent with Azure LLM
@@ -216,6 +191,5 @@ azure_agent = Agent(
   llm=azure_llm
 )
 ```
-
 ## Conclusion
 Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

docs/index.md

@@ -46,11 +46,6 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Crews
                 </a>
             </li>
-            <li>
-                <a href="./core-concepts/Pipeline">
-                    Pipeline
-                </a>
-            </li>
             <li>
                 <a href="./core-concepts/Training-Crew">
                     Training

docs/tools/CodeInterpreterTool.md

@@ -1,9 +1,9 @@
 # CodeInterpreterTool
 
 ## Description
-This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code.
+This tool enables the Agent to execute Python 3 code that it has generated autonomously. The code is run in a secure, isolated environment, ensuring safety regardless of the content. 
 
-It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions.
+This functionality is particularly valuable as it allows the Agent to create code, execute it within the same ecosystem, obtain the results, and utilize that information to inform subsequent decisions and actions.
 
 ## Requirements
 

docs/tools/ComposioTool.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-This tools is a wrapper around the composio toolset and gives your agent access to a wide variety of tools from the composio SDK.
+This tools is a wrapper around the composio set of tools and gives your agent access to a wide variety of tools from the composio SDK.
 
 ## Installation
 
@@ -19,7 +19,7 @@ after the installation is complete, either run `composio login` or export your c
 
 The following example demonstrates how to initialize the tool and execute a github action:
 
-1. Initialize toolset
+1. Initialize Composio tools
 
 ```python
 from composio import App

docs/tools/SerperDevTool.md

@@ -40,10 +40,9 @@ The `SerperDevTool` comes with several parameters that will be passed to the API
 - **locale**: Optional. Specify the locale for the search results.
 - **n_results**: Number of search results to return. Default is `10`.
 
-The values for `country`, `location`, `lovale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
+The values for `country`, `location`, `locale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
 
 ## Example with Parameters
-
 Here is an example demonstrating how to use the tool with additional parameters:
 
 ```python

poetry.lock

@@ -1,14 +1,14 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "agentops"
-version = "0.3.4"
+version = "0.3.2"
 description = "Python SDK for developing AI agent evals and observability"
 optional = true
 python-versions = ">=3.7"
 files = [
-    {file = "agentops-0.3.4-py3-none-any.whl", hash = "sha256:126f7aed4ba43c1399b5488d67a03d10cb4c531e619c650776f826ca00c1aa24"},
-    {file = "agentops-0.3.4.tar.gz", hash = "sha256:a92c9cb7c511197f0ecb8cb5aca15d35022c15a3d2fd2aaaa34cd7e5dc59393f"},
+    {file = "agentops-0.3.2-py3-none-any.whl", hash = "sha256:b35988e04378624204572bb3d7a454094f879ea573f05b57d4e75ab0bfbb82af"},
+    {file = "agentops-0.3.2.tar.gz", hash = "sha256:55559ac4a43634831dfa8937c2597c28e332809dc7c6bb3bc3c8b233442e224c"},
 ]
 
 [package.dependencies]
@@ -355,17 +355,17 @@ lxml = ["lxml"]
 
 [[package]]
 name = "boto3"
-version = "1.34.149"
+version = "1.34.146"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "boto3-1.34.149-py3-none-any.whl", hash = "sha256:11edeeacdd517bda3b7615b754d8440820cdc9ddd66794cc995a9693ddeaa3be"},
-    {file = "boto3-1.34.149.tar.gz", hash = "sha256:f4e6489ba9dc7fb37d53e0e82dbc97f2cb0a4969ef3970e2c88b8f94023ae81a"},
+    {file = "boto3-1.34.146-py3-none-any.whl", hash = "sha256:7ec568fb19bce82a70be51f08fddac1ef927ca3fb0896cbb34303a012ba228d8"},
+    {file = "boto3-1.34.146.tar.gz", hash = "sha256:5686fe2a6d1aa1de8a88e9589cdcc33361640d3d7a13da718a30717248886124"},
 ]
 
 [package.dependencies]
-botocore = ">=1.34.149,<1.35.0"
+botocore = ">=1.34.146,<1.35.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.10.0,<0.11.0"
 
@@ -374,13 +374,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.34.149"
+version = "1.34.146"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "botocore-1.34.149-py3-none-any.whl", hash = "sha256:ae6c4be52eeee96f68c116b27d252bab069cd046d61a17cfe8e9da411cf22906"},
-    {file = "botocore-1.34.149.tar.gz", hash = "sha256:2e1eb5ef40102a3d796bb3dd05f2ac5e8fb43fe1ff114b4f6d33153437f5a372"},
+    {file = "botocore-1.34.146-py3-none-any.whl", hash = "sha256:3fd4782362bd29c192704ebf859c5c8c5189ad05719e391eefe23088434427ae"},
+    {file = "botocore-1.34.146.tar.gz", hash = "sha256:849cb8e54e042443aeabcd7822b5f2b76cb5cfe33fe3a71f91c7c069748a869c"},
 ]
 
 [package.dependencies]
@@ -1012,13 +1012,13 @@ idna = ">=2.0.0"
 
 [[package]]
 name = "embedchain"
-version = "0.1.119"
+version = "0.1.118"
 description = "Simplest open source retrieval (RAG) framework"
 optional = false
 python-versions = "<=3.13,>=3.9"
 files = [
-    {file = "embedchain-0.1.119-py3-none-any.whl", hash = "sha256:8ec3e7f139939fa1dc8fda898f8d8d9d31a5abfe08e184b607e38733d863d606"},
-    {file = "embedchain-0.1.119.tar.gz", hash = "sha256:0f4f45e092b7f3192ea6fe82575726532573b1231d7af6c22edc695b701b4223"},
+    {file = "embedchain-0.1.118-py3-none-any.whl", hash = "sha256:38ead471df9d9234bf42e6f7a32cab26431d50d6f2f894f18a6cabc0b02bf31a"},
+    {file = "embedchain-0.1.118.tar.gz", hash = "sha256:1fa1e799882a1dc4e63af344595b043f1c1f30fbd59461b6660b1934b85a1e4b"},
 ]
 
 [package.dependencies]
@@ -1032,7 +1032,7 @@ langchain = ">0.2,<=0.3"
 langchain-cohere = ">=0.1.4,<0.2.0"
 langchain-community = ">=0.2.6,<0.3.0"
 langchain-openai = ">=0.1.7,<0.2.0"
-mem0ai = ">=0.0.9,<0.0.10"
+mem0ai = ">=0.0.5,<0.0.6"
 openai = ">=1.1.1"
 posthog = ">=3.0.2,<4.0.0"
 pypdf = ">=4.0.1,<5.0.0"
@@ -1061,6 +1061,20 @@ together = ["together (>=1.2.1,<2.0.0)"]
 vertexai = ["langchain-google-vertexai (>=1.0.6,<2.0.0)"]
 weaviate = ["weaviate-client (>=3.24.1,<4.0.0)"]
 
+[[package]]
+name = "eval-type-backport"
+version = "0.2.0"
+description = "Like `typing._eval_type`, but lets older Python versions use newer typing features."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "eval_type_backport-0.2.0-py3-none-any.whl", hash = "sha256:ac2f73d30d40c5a30a80b8739a789d6bb5e49fdffa66d7912667e2015d9c9933"},
+    {file = "eval_type_backport-0.2.0.tar.gz", hash = "sha256:68796cfbc7371ebf923f03bdf7bef415f3ec098aeced24e054b253a0e78f7b37"},
+]
+
+[package.extras]
+tests = ["pytest"]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.2.2"
@@ -1388,13 +1402,13 @@ requests = ["requests (>=2.20.0,<3.0.0.dev0)"]
 
 [[package]]
 name = "google-cloud-aiplatform"
-version = "1.60.0"
+version = "1.59.0"
 description = "Vertex AI API client library"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "google-cloud-aiplatform-1.60.0.tar.gz", hash = "sha256:782c7f1ec0e77a7c7daabef3b65bfd506ed2b4b1dc2186753c43cd6faf8dd04e"},
-    {file = "google_cloud_aiplatform-1.60.0-py2.py3-none-any.whl", hash = "sha256:5f14159c9575f4b46335027e3ceb8fa57bd5eaa76a07f858105b8c6c034ec0d6"},
+    {file = "google-cloud-aiplatform-1.59.0.tar.gz", hash = "sha256:2bebb59c0ba3e3b4b568305418ca1b021977988adbee8691a5bed09b037e7e63"},
+    {file = "google_cloud_aiplatform-1.59.0-py2.py3-none-any.whl", hash = "sha256:549e6eb1844b0f853043309138ebe2db00de4bbd8197b3bde26804ac163ef52a"},
 ]
 
 [package.dependencies]
@@ -1416,8 +1430,8 @@ cloud-profiler = ["tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow
 datasets = ["pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)"]
 endpoint = ["requests (>=2.28.1)"]
 full = ["cloudpickle (<3.0)", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.109.1)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-cloud-logging (<4.0)", "google-vizier (>=0.1.6)", "httpx (>=0.23.0,<0.25.0)", "immutabledict", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.1.1)", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)", "pyarrow (>=6.0.1)", "pydantic (<2)", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<=2.9.3)", "ray[default] (>=2.5,<=2.9.3)", "requests (>=2.28.1)", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.4.0,<3.0.0dev)", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<2.1.0dev)"]
-langchain = ["langchain (>=0.1.16,<0.3)", "langchain-core (<0.3)", "langchain-google-vertexai (<2)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "tenacity (<=8.3)"]
-langchain-testing = ["absl-py", "cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "langchain (>=0.1.16,<0.3)", "langchain-core (<0.3)", "langchain-google-vertexai (<2)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.6.3,<3)", "pytest-xdist", "tenacity (<=8.3)"]
+langchain = ["langchain (>=0.1.16,<0.3)", "langchain-core (<0.2)", "langchain-google-vertexai (<2)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "tenacity (<=8.3)"]
+langchain-testing = ["absl-py", "cloudpickle (>=3.0,<4.0)", "langchain (>=0.1.16,<0.3)", "langchain-core (<0.2)", "langchain-google-vertexai (<2)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.6.3,<3)", "pytest-xdist", "tenacity (<=8.3)"]
 lit = ["explainable-ai-sdk (>=1.0.0)", "lit-nlp (==0.4.0)", "pandas (>=1.0.0)", "tensorflow (>=2.3.0,<3.0.0dev)"]
 metadata = ["numpy (>=1.15.0)", "pandas (>=1.0.0)"]
 pipelines = ["pyyaml (>=5.3.1,<7)"]
@@ -1427,7 +1441,7 @@ private-endpoints = ["requests (>=2.28.1)", "urllib3 (>=1.21.1,<1.27)"]
 rapid-evaluation = ["pandas (>=1.0.0,<2.2.0)", "tqdm (>=4.23.0)"]
 ray = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=6.0.1)", "pydantic (<2)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<=2.9.3)", "ray[default] (>=2.5,<=2.9.3)", "setuptools (<70.0.0)"]
 ray-testing = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=6.0.1)", "pydantic (<2)", "pytest-xdist", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<=2.9.3)", "ray[default] (>=2.5,<=2.9.3)", "ray[train] (==2.9.3)", "scikit-learn", "setuptools (<70.0.0)", "tensorflow", "torch (>=2.0.0,<2.1.0)", "xgboost", "xgboost-ray"]
-reasoningengine = ["cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.6.3,<3)"]
+reasoningengine = ["cloudpickle (>=3.0,<4.0)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.6.3,<3)"]
 tensorboard = ["tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.4.0,<3.0.0dev)", "werkzeug (>=2.0.0,<2.1.0dev)"]
 testing = ["bigframes", "cloudpickle (<3.0)", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.109.1)", "google-api-core (>=2.11,<3.0.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-cloud-logging (<4.0)", "google-vizier (>=0.1.6)", "grpcio-testing", "httpx (>=0.23.0,<0.25.0)", "immutabledict", "ipython", "kfp (>=2.6.0,<3.0.0)", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.1.1)", "nltk", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)", "pyarrow (>=6.0.1)", "pydantic (<2)", "pyfakefs", "pytest-asyncio", "pytest-xdist", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<=2.9.3)", "ray[default] (>=2.5,<=2.9.3)", "requests (>=2.28.1)", "requests-toolbelt (<1.0.0)", "scikit-learn", "sentencepiece (>=0.2.0)", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow (==2.13.0)", "tensorflow (==2.16.1)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.4.0,<3.0.0dev)", "torch (>=2.0.0,<2.1.0)", "torch (>=2.2.0)", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<2.1.0dev)", "xgboost"]
 tokenization = ["sentencepiece (>=0.2.0)"]
@@ -1742,6 +1756,25 @@ files = [
 backports-strenum = {version = ">=1.3", markers = "python_version < \"3.11\""}
 colorama = ">=0.4"
 
+[[package]]
+name = "groq"
+version = "0.9.0"
+description = "The official Python library for the groq API"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "groq-0.9.0-py3-none-any.whl", hash = "sha256:d0e46f4ad645504672bb09c8100af3ced3a7db0d5119dc13e4aca535fc455874"},
+    {file = "groq-0.9.0.tar.gz", hash = "sha256:130ed5e35d3acfaab46b9e7a078eeaebf91052f4a9d71f86f87fb319b5fec332"},
+]
+
+[package.dependencies]
+anyio = ">=3.5.0,<5"
+distro = ">=1.7.0,<2"
+httpx = ">=0.23.0,<1"
+pydantic = ">=1.9.0,<3"
+sniffio = "*"
+typing-extensions = ">=4.7,<5"
+
 [[package]]
 name = "grpc-google-iam-v1"
 version = "0.13.1"
@@ -2044,13 +2077,13 @@ files = [
 
 [[package]]
 name = "huggingface-hub"
-version = "0.24.3"
+version = "0.24.0"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "huggingface_hub-0.24.3-py3-none-any.whl", hash = "sha256:69ecce486dd6cdad69937ba76779e893c224a670a9d947636c1d5cbd049e44d8"},
-    {file = "huggingface_hub-0.24.3.tar.gz", hash = "sha256:bfdc05cc9b64a0e24e8614a44222698799183268f6b68be209aa2df70cff2cde"},
+    {file = "huggingface_hub-0.24.0-py3-none-any.whl", hash = "sha256:7ad92edefb93d8145c061f6df8d99df2ff85f8379ba5fac8a95aca0642afa5d7"},
+    {file = "huggingface_hub-0.24.0.tar.gz", hash = "sha256:6c7092736b577d89d57b3cdfea026f1b0dc2234ae783fa0d59caf1bf7d52dfa7"},
 ]
 
 [package.dependencies]
@@ -2128,22 +2161,22 @@ files = [
 
 [[package]]
 name = "importlib-metadata"
-version = "8.0.0"
+version = "7.1.0"
 description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "importlib_metadata-8.0.0-py3-none-any.whl", hash = "sha256:15584cf2b1bf449d98ff8a6ff1abef57bf20f3ac6454f431736cd3e660921b2f"},
-    {file = "importlib_metadata-8.0.0.tar.gz", hash = "sha256:188bd24e4c346d3f0a933f275c2fec67050326a856b9a359881d7c2a697e8812"},
+    {file = "importlib_metadata-7.1.0-py3-none-any.whl", hash = "sha256:30962b96c0c223483ed6cc7280e7f0199feb01a0e40cfae4d4450fc6fab1f570"},
+    {file = "importlib_metadata-7.1.0.tar.gz", hash = "sha256:b78938b926ee8d5f020fc4772d487045805a55ddbad2ecf21c6d60938dc7fcd2"},
 ]
 
 [package.dependencies]
 zipp = ">=0.5"
 
 [package.extras]
-doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
 perf = ["ipython"]
-test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
+testing = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
 
 [[package]]
 name = "importlib-resources"
@@ -2423,19 +2456,19 @@ tests = ["aiohttp", "duckdb", "pandas (>=1.4)", "polars (>=0.19)", "pytest", "py
 
 [[package]]
 name = "langchain"
-version = "0.2.11"
+version = "0.2.10"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain-0.2.11-py3-none-any.whl", hash = "sha256:5a7a8b4918f3d3bebce9b4f23b92d050699e6f7fb97591e8941177cf07a260a2"},
-    {file = "langchain-0.2.11.tar.gz", hash = "sha256:d7a9e4165f02dca0bd78addbc2319d5b9286b5d37c51d784124102b57e9fd297"},
+    {file = "langchain-0.2.10-py3-none-any.whl", hash = "sha256:b4fb58c7faf4f4999cfe3325474979a7121a1737dd101655a723a1d957ef0617"},
+    {file = "langchain-0.2.10.tar.gz", hash = "sha256:1f861c1b59ac9c91b02bb0fa58d3adad1c1d0686636872b5b357bbce3ce41d06"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
-langchain-core = ">=0.2.23,<0.3.0"
+langchain-core = ">=0.2.22,<0.3.0"
 langchain-text-splitters = ">=0.2.0,<0.3.0"
 langsmith = ">=0.1.17,<0.2.0"
 numpy = [
@@ -2471,20 +2504,20 @@ langchain-community = ["langchain-community (>=0.2.4)"]
 
 [[package]]
 name = "langchain-community"
-version = "0.2.10"
+version = "0.2.9"
 description = "Community contributed LangChain integrations."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_community-0.2.10-py3-none-any.whl", hash = "sha256:9f4d1b5ab7f0b0a704f538e26e50fce45a461da6d2bf6b7b636d24f22fbc088a"},
-    {file = "langchain_community-0.2.10.tar.gz", hash = "sha256:3a0404bad4bd07d6f86affdb62fb3d080a456c66191754d586a409d9d6024d62"},
+    {file = "langchain_community-0.2.9-py3-none-any.whl", hash = "sha256:b51d3adf9346a1161c1098917585b9e303cf24e2f5c71f5d232a0504edada5f2"},
+    {file = "langchain_community-0.2.9.tar.gz", hash = "sha256:1e7c180232916cbe35fe00509680dd1f805e32d7c87b5e80b3a9ec8754ecae37"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 dataclasses-json = ">=0.5.7,<0.7"
 langchain = ">=0.2.9,<0.3.0"
-langchain-core = ">=0.2.23,<0.3.0"
+langchain-core = ">=0.2.22,<0.3.0"
 langsmith = ">=0.1.0,<0.2.0"
 numpy = [
     {version = ">=1,<2", markers = "python_version < \"3.12\""},
@@ -2497,13 +2530,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-core"
-version = "0.2.24"
+version = "0.2.22"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_core-0.2.24-py3-none-any.whl", hash = "sha256:9444fc082d21ef075d925590a684a73fe1f9688a3d90087580ec929751be55e7"},
-    {file = "langchain_core-0.2.24.tar.gz", hash = "sha256:f2e3fa200b124e8c45d270da9bf836bed9c09532612c96ff3225e59b9a232f5a"},
+    {file = "langchain_core-0.2.22-py3-none-any.whl", hash = "sha256:7731a86440c0958b3186c003fb9b26b2d5a682a6344bda7bfb9174e2898f8b43"},
+    {file = "langchain_core-0.2.22.tar.gz", hash = "sha256:582d6f929a43b830139444e4124123cd415331ad62f25757b1406252958cdcac"},
 ]
 
 [package.dependencies]
@@ -2519,13 +2552,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-experimental"
-version = "0.0.63"
+version = "0.0.62"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_experimental-0.0.63-py3-none-any.whl", hash = "sha256:cb4ae7a685bb3c077d138b4533ed02e8df1f5f784333c3e52dcae8c80f031ca2"},
-    {file = "langchain_experimental-0.0.63.tar.gz", hash = "sha256:fc894599bfac43445004a9ff60d9a28751426b2fea1979e4b2fa453c847850c4"},
+    {file = "langchain_experimental-0.0.62-py3-none-any.whl", hash = "sha256:9240f9e3490e819976f20a37863970036e7baacb7104b9eb6833d19ab6d518c9"},
+    {file = "langchain_experimental-0.0.62.tar.gz", hash = "sha256:9737fbc8429d24457ea4d368e3c9ba9ed1cace0564fb5f1a96a3027a588bd0ac"},
 ]
 
 [package.dependencies]
@@ -2534,17 +2567,17 @@ langchain-core = ">=0.2.10,<0.3.0"
 
 [[package]]
 name = "langchain-openai"
-version = "0.1.19"
+version = "0.1.17"
 description = "An integration package connecting OpenAI and LangChain"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_openai-0.1.19-py3-none-any.whl", hash = "sha256:a7a739f1469d54cd988865420e7fc21b50fb93727b2e6da5ad30273fc61ecf19"},
-    {file = "langchain_openai-0.1.19.tar.gz", hash = "sha256:3bf342bb302d1444f4abafdf01c467dbd9b248497e1133808c4bae70396c79b3"},
+    {file = "langchain_openai-0.1.17-py3-none-any.whl", hash = "sha256:30bef5574ecbbbb91b8025b2dc5a1bd81fd62157d3ad1a35d820141f31c5b443"},
+    {file = "langchain_openai-0.1.17.tar.gz", hash = "sha256:c5d70ddecdcb93e146f376bdbadbb6ec69de9ac0f402cd5b83de50b655ba85ee"},
 ]
 
 [package.dependencies]
-langchain-core = ">=0.2.24,<0.3.0"
+langchain-core = ">=0.2.20,<0.3.0"
 openai = ">=1.32.0,<2.0.0"
 tiktoken = ">=0.7,<1"
 
@@ -2740,20 +2773,23 @@ files = [
 
 [[package]]
 name = "mem0ai"
-version = "0.0.9"
+version = "0.0.5"
 description = "Long-term memory for AI Agents"
 optional = false
 python-versions = "<4.0,>=3.8"
 files = [
-    {file = "mem0ai-0.0.9-py3-none-any.whl", hash = "sha256:d4de435729af4fd3d597d022ffb2af89a0630d6c3b4769792bbe27d2ce816858"},
-    {file = "mem0ai-0.0.9.tar.gz", hash = "sha256:e4374d5d04aa3f543cd3325f700e4b62f5358ae1c6fa5c44b2ff790c10c4e5f1"},
+    {file = "mem0ai-0.0.5-py3-none-any.whl", hash = "sha256:6f6e5356fd522adf0510322cd581476ea456fd7ccefca11b5ac050e9a6f00f36"},
+    {file = "mem0ai-0.0.5.tar.gz", hash = "sha256:f2ac35d15e4e620becb8d06b8ebeb1ffa85fac0b7cb2d3138056babec48dd5dd"},
 ]
 
 [package.dependencies]
+boto3 = ">=1.34.144,<2.0.0"
+groq = ">=0.9.0,<0.10.0"
 openai = ">=1.33.0,<2.0.0"
 posthog = ">=3.5.0,<4.0.0"
 pydantic = ">=2.7.3,<3.0.0"
 qdrant-client = ">=1.9.1,<2.0.0"
+together = ">=1.2.1,<2.0.0"
 
 [[package]]
 name = "mergedeep"
@@ -3302,13 +3338,13 @@ sympy = "*"
 
 [[package]]
 name = "openai"
-version = "1.37.1"
+version = "1.37.0"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.37.1-py3-none-any.whl", hash = "sha256:9a6adda0d6ae8fce02d235c5671c399cfa40d6a281b3628914c7ebf244888ee3"},
-    {file = "openai-1.37.1.tar.gz", hash = "sha256:faf87206785a6b5d9e34555d6a3242482a6852bc802e453e2a891f68ee04ce55"},
+    {file = "openai-1.37.0-py3-none-any.whl", hash = "sha256:a903245c0ecf622f2830024acdaa78683c70abb8e9d37a497b851670864c9f73"},
+    {file = "openai-1.37.0.tar.gz", hash = "sha256:dc8197fc40ab9d431777b6620d962cc49f4544ffc3011f03ce0a805e6eb54adb"},
 ]
 
 [package.dependencies]
@@ -3325,42 +3361,42 @@ datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Python API"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_api-1.26.0-py3-none-any.whl", hash = "sha256:7d7ea33adf2ceda2dd680b18b1677e4152000b37ca76e679da71ff103b943064"},
-    {file = "opentelemetry_api-1.26.0.tar.gz", hash = "sha256:2bd639e4bed5b18486fef0b5a520aaffde5a18fc225e808a1ac4df363f43a1ce"},
+    {file = "opentelemetry_api-1.25.0-py3-none-any.whl", hash = "sha256:757fa1aa020a0f8fa139f8959e53dec2051cc26b832e76fa839a6d76ecefd737"},
+    {file = "opentelemetry_api-1.25.0.tar.gz", hash = "sha256:77c4985f62f2614e42ce77ee4c9da5fa5f0bc1e1821085e9a47533a9323ae869"},
 ]
 
 [package.dependencies]
 deprecated = ">=1.2.6"
-importlib-metadata = ">=6.0,<=8.0.0"
+importlib-metadata = ">=6.0,<=7.1"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Protobuf encoding"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_common-1.26.0-py3-none-any.whl", hash = "sha256:ee4d8f8891a1b9c372abf8d109409e5b81947cf66423fd998e56880057afbc71"},
-    {file = "opentelemetry_exporter_otlp_proto_common-1.26.0.tar.gz", hash = "sha256:bdbe50e2e22a1c71acaa0c8ba6efaadd58882e5a5978737a44a4c4b10d304c92"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.25.0-py3-none-any.whl", hash = "sha256:15637b7d580c2675f70246563363775b4e6de947871e01d0f4e3881d1848d693"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.25.0.tar.gz", hash = "sha256:c93f4e30da4eee02bacd1e004eb82ce4da143a2f8e15b987a9f603e0a85407d3"},
 ]
 
 [package.dependencies]
-opentelemetry-proto = "1.26.0"
+opentelemetry-proto = "1.25.0"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.26.0-py3-none-any.whl", hash = "sha256:e2be5eff72ebcb010675b818e8d7c2e7d61ec451755b8de67a140bc49b9b0280"},
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.26.0.tar.gz", hash = "sha256:a65b67a9a6b06ba1ec406114568e21afe88c1cdb29c464f2507d529eb906d8ae"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.25.0-py3-none-any.whl", hash = "sha256:3131028f0c0a155a64c430ca600fd658e8e37043cb13209f0109db5c1a3e4eb4"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.25.0.tar.gz", hash = "sha256:c0b1661415acec5af87625587efa1ccab68b873745ca0ee96b69bb1042087eac"},
 ]
 
 [package.dependencies]
@@ -3368,39 +3404,39 @@ deprecated = ">=1.2.6"
 googleapis-common-protos = ">=1.52,<2.0"
 grpcio = ">=1.0.0,<2.0.0"
 opentelemetry-api = ">=1.15,<2.0"
-opentelemetry-exporter-otlp-proto-common = "1.26.0"
-opentelemetry-proto = "1.26.0"
-opentelemetry-sdk = ">=1.26.0,<1.27.0"
+opentelemetry-exporter-otlp-proto-common = "1.25.0"
+opentelemetry-proto = "1.25.0"
+opentelemetry-sdk = ">=1.25.0,<1.26.0"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_http-1.26.0-py3-none-any.whl", hash = "sha256:ee72a87c48ec977421b02f16c52ea8d884122470e0be573905237b540f4ee562"},
-    {file = "opentelemetry_exporter_otlp_proto_http-1.26.0.tar.gz", hash = "sha256:5801ebbcf7b527377883e6cbbdda35ee712dc55114fff1e93dfee210be56c908"},
+    {file = "opentelemetry_exporter_otlp_proto_http-1.25.0-py3-none-any.whl", hash = "sha256:2eca686ee11b27acd28198b3ea5e5863a53d1266b91cda47c839d95d5e0541a6"},
+    {file = "opentelemetry_exporter_otlp_proto_http-1.25.0.tar.gz", hash = "sha256:9f8723859e37c75183ea7afa73a3542f01d0fd274a5b97487ea24cb683d7d684"},
 ]
 
 [package.dependencies]
 deprecated = ">=1.2.6"
 googleapis-common-protos = ">=1.52,<2.0"
 opentelemetry-api = ">=1.15,<2.0"
-opentelemetry-exporter-otlp-proto-common = "1.26.0"
-opentelemetry-proto = "1.26.0"
-opentelemetry-sdk = ">=1.26.0,<1.27.0"
+opentelemetry-exporter-otlp-proto-common = "1.25.0"
+opentelemetry-proto = "1.25.0"
+opentelemetry-sdk = ">=1.25.0,<1.26.0"
 requests = ">=2.7,<3.0"
 
 [[package]]
 name = "opentelemetry-instrumentation"
-version = "0.47b0"
+version = "0.46b0"
 description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_instrumentation-0.47b0-py3-none-any.whl", hash = "sha256:88974ee52b1db08fc298334b51c19d47e53099c33740e48c4f084bd1afd052d5"},
-    {file = "opentelemetry_instrumentation-0.47b0.tar.gz", hash = "sha256:96f9885e450c35e3f16a4f33145f2ebf620aea910c9fd74a392bbc0f807a350f"},
+    {file = "opentelemetry_instrumentation-0.46b0-py3-none-any.whl", hash = "sha256:89cd721b9c18c014ca848ccd11181e6b3fd3f6c7669e35d59c48dc527408c18b"},
+    {file = "opentelemetry_instrumentation-0.46b0.tar.gz", hash = "sha256:974e0888fb2a1e01c38fbacc9483d024bb1132aad92d6d24e2e5543887a7adda"},
 ]
 
 [package.dependencies]
@@ -3410,55 +3446,55 @@ wrapt = ">=1.0.0,<2.0.0"
 
 [[package]]
 name = "opentelemetry-instrumentation-asgi"
-version = "0.47b0"
+version = "0.46b0"
 description = "ASGI instrumentation for OpenTelemetry"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_instrumentation_asgi-0.47b0-py3-none-any.whl", hash = "sha256:b798dc4957b3edc9dfecb47a4c05809036a4b762234c5071212fda39ead80ade"},
-    {file = "opentelemetry_instrumentation_asgi-0.47b0.tar.gz", hash = "sha256:e78b7822c1bca0511e5e9610ec484b8994a81670375e570c76f06f69af7c506a"},
+    {file = "opentelemetry_instrumentation_asgi-0.46b0-py3-none-any.whl", hash = "sha256:f13c55c852689573057837a9500aeeffc010c4ba59933c322e8f866573374759"},
+    {file = "opentelemetry_instrumentation_asgi-0.46b0.tar.gz", hash = "sha256:02559f30cf4b7e2a737ab17eb52aa0779bcf4cc06573064f3e2cb4dcc7d3040a"},
 ]
 
 [package.dependencies]
 asgiref = ">=3.0,<4.0"
 opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-instrumentation = "0.47b0"
-opentelemetry-semantic-conventions = "0.47b0"
-opentelemetry-util-http = "0.47b0"
+opentelemetry-instrumentation = "0.46b0"
+opentelemetry-semantic-conventions = "0.46b0"
+opentelemetry-util-http = "0.46b0"
 
 [package.extras]
 instruments = ["asgiref (>=3.0,<4.0)"]
 
 [[package]]
 name = "opentelemetry-instrumentation-fastapi"
-version = "0.47b0"
+version = "0.46b0"
 description = "OpenTelemetry FastAPI Instrumentation"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_instrumentation_fastapi-0.47b0-py3-none-any.whl", hash = "sha256:5ac28dd401160b02e4f544a85a9e4f61a8cbe5b077ea0379d411615376a2bd21"},
-    {file = "opentelemetry_instrumentation_fastapi-0.47b0.tar.gz", hash = "sha256:0c7c10b5d971e99a420678ffd16c5b1ea4f0db3b31b62faf305fbb03b4ebee36"},
+    {file = "opentelemetry_instrumentation_fastapi-0.46b0-py3-none-any.whl", hash = "sha256:e0f5d150c6c36833dd011f0e6ef5ede6d7406c1aed0c7c98b2d3b38a018d1b33"},
+    {file = "opentelemetry_instrumentation_fastapi-0.46b0.tar.gz", hash = "sha256:928a883a36fc89f9702f15edce43d1a7104da93d740281e32d50ffd03dbb4365"},
 ]
 
 [package.dependencies]
 opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-instrumentation = "0.47b0"
-opentelemetry-instrumentation-asgi = "0.47b0"
-opentelemetry-semantic-conventions = "0.47b0"
-opentelemetry-util-http = "0.47b0"
+opentelemetry-instrumentation = "0.46b0"
+opentelemetry-instrumentation-asgi = "0.46b0"
+opentelemetry-semantic-conventions = "0.46b0"
+opentelemetry-util-http = "0.46b0"
 
 [package.extras]
-instruments = ["fastapi (>=0.58,<1.0)", "fastapi-slim (>=0.111.0,<0.112.0)"]
+instruments = ["fastapi (>=0.58,<1.0)"]
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Python Proto"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_proto-1.26.0-py3-none-any.whl", hash = "sha256:6c4d7b4d4d9c88543bcf8c28ae3f8f0448a753dc291c18c5390444c90b76a725"},
-    {file = "opentelemetry_proto-1.26.0.tar.gz", hash = "sha256:c5c18796c0cab3751fc3b98dee53855835e90c0422924b484432ac852d93dc1e"},
+    {file = "opentelemetry_proto-1.25.0-py3-none-any.whl", hash = "sha256:f07e3341c78d835d9b86665903b199893befa5e98866f63d22b00d0b7ca4972f"},
+    {file = "opentelemetry_proto-1.25.0.tar.gz", hash = "sha256:35b6ef9dc4a9f7853ecc5006738ad40443701e52c26099e197895cbda8b815a3"},
 ]
 
 [package.dependencies]
@@ -3466,44 +3502,43 @@ protobuf = ">=3.19,<5.0"
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.26.0"
+version = "1.25.0"
 description = "OpenTelemetry Python SDK"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_sdk-1.26.0-py3-none-any.whl", hash = "sha256:feb5056a84a88670c041ea0ded9921fca559efec03905dddeb3885525e0af897"},
-    {file = "opentelemetry_sdk-1.26.0.tar.gz", hash = "sha256:c90d2868f8805619535c05562d699e2f4fb1f00dbd55a86dcefca4da6fa02f85"},
+    {file = "opentelemetry_sdk-1.25.0-py3-none-any.whl", hash = "sha256:d97ff7ec4b351692e9d5a15af570c693b8715ad78b8aafbec5c7100fe966b4c9"},
+    {file = "opentelemetry_sdk-1.25.0.tar.gz", hash = "sha256:ce7fc319c57707ef5bf8b74fb9f8ebdb8bfafbe11898410e0d2a761d08a98ec7"},
 ]
 
 [package.dependencies]
-opentelemetry-api = "1.26.0"
-opentelemetry-semantic-conventions = "0.47b0"
+opentelemetry-api = "1.25.0"
+opentelemetry-semantic-conventions = "0.46b0"
 typing-extensions = ">=3.7.4"
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.47b0"
+version = "0.46b0"
 description = "OpenTelemetry Semantic Conventions"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_semantic_conventions-0.47b0-py3-none-any.whl", hash = "sha256:4ff9d595b85a59c1c1413f02bba320ce7ea6bf9e2ead2b0913c4395c7bbc1063"},
-    {file = "opentelemetry_semantic_conventions-0.47b0.tar.gz", hash = "sha256:a8d57999bbe3495ffd4d510de26a97dadc1dace53e0275001b2c1b2f67992a7e"},
+    {file = "opentelemetry_semantic_conventions-0.46b0-py3-none-any.whl", hash = "sha256:6daef4ef9fa51d51855d9f8e0ccd3a1bd59e0e545abe99ac6203804e36ab3e07"},
+    {file = "opentelemetry_semantic_conventions-0.46b0.tar.gz", hash = "sha256:fbc982ecbb6a6e90869b15c1673be90bd18c8a56ff1cffc0864e38e2edffaefa"},
 ]
 
 [package.dependencies]
-deprecated = ">=1.2.6"
-opentelemetry-api = "1.26.0"
+opentelemetry-api = "1.25.0"
 
 [[package]]
 name = "opentelemetry-util-http"
-version = "0.47b0"
+version = "0.46b0"
 description = "Web util for OpenTelemetry"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "opentelemetry_util_http-0.47b0-py3-none-any.whl", hash = "sha256:3d3215e09c4a723b12da6d0233a31395aeb2bb33a64d7b15a1500690ba250f19"},
-    {file = "opentelemetry_util_http-0.47b0.tar.gz", hash = "sha256:352a07664c18eef827eb8ddcbd64c64a7284a39dd1655e2f16f577eb046ccb32"},
+    {file = "opentelemetry_util_http-0.46b0-py3-none-any.whl", hash = "sha256:8dc1949ce63caef08db84ae977fdc1848fe6dc38e6bbaad0ae3e6ecd0d451629"},
+    {file = "opentelemetry_util_http-0.46b0.tar.gz", hash = "sha256:03b6e222642f9c7eae58d9132343e045b50aca9761fcb53709bd2b663571fdf6"},
 ]
 
 [[package]]
@@ -3882,13 +3917,13 @@ test = ["coverage", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint"
 
 [[package]]
 name = "pre-commit"
-version = "3.8.0"
+version = "3.7.1"
 description = "A framework for managing and maintaining multi-language pre-commit hooks."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "pre_commit-3.8.0-py2.py3-none-any.whl", hash = "sha256:9a90a53bf82fdd8778d58085faf8d83df56e40dfe18f45b19446e26bf1b3a63f"},
-    {file = "pre_commit-3.8.0.tar.gz", hash = "sha256:8bb6494d4a20423842e198980c9ecf9f96607a07ea29549e180eef9ae80fe7af"},
+    {file = "pre_commit-3.7.1-py2.py3-none-any.whl", hash = "sha256:fae36fd1d7ad7d6a5a1c0b0d5adb2ed1a3bda5a21bf6c3e5372073d7a11cd4c5"},
+    {file = "pre_commit-3.7.1.tar.gz", hash = "sha256:8ca3ad567bc78a4972a3f1a477e94a79d4597e8140a6e0b651c5e33899c3654a"},
 ]
 
 [package.dependencies]
@@ -3917,22 +3952,22 @@ testing = ["google-api-core (>=1.31.5)"]
 
 [[package]]
 name = "protobuf"
-version = "4.25.4"
+version = "4.25.3"
 description = ""
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "protobuf-4.25.4-cp310-abi3-win32.whl", hash = "sha256:db9fd45183e1a67722cafa5c1da3e85c6492a5383f127c86c4c4aa4845867dc4"},
-    {file = "protobuf-4.25.4-cp310-abi3-win_amd64.whl", hash = "sha256:ba3d8504116a921af46499471c63a85260c1a5fc23333154a427a310e015d26d"},
-    {file = "protobuf-4.25.4-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:eecd41bfc0e4b1bd3fa7909ed93dd14dd5567b98c941d6c1ad08fdcab3d6884b"},
-    {file = "protobuf-4.25.4-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:4c8a70fdcb995dcf6c8966cfa3a29101916f7225e9afe3ced4395359955d3835"},
-    {file = "protobuf-4.25.4-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:3319e073562e2515c6ddc643eb92ce20809f5d8f10fead3332f71c63be6a7040"},
-    {file = "protobuf-4.25.4-cp38-cp38-win32.whl", hash = "sha256:7e372cbbda66a63ebca18f8ffaa6948455dfecc4e9c1029312f6c2edcd86c4e1"},
-    {file = "protobuf-4.25.4-cp38-cp38-win_amd64.whl", hash = "sha256:051e97ce9fa6067a4546e75cb14f90cf0232dcb3e3d508c448b8d0e4265b61c1"},
-    {file = "protobuf-4.25.4-cp39-cp39-win32.whl", hash = "sha256:90bf6fd378494eb698805bbbe7afe6c5d12c8e17fca817a646cd6a1818c696ca"},
-    {file = "protobuf-4.25.4-cp39-cp39-win_amd64.whl", hash = "sha256:ac79a48d6b99dfed2729ccccee547b34a1d3d63289c71cef056653a846a2240f"},
-    {file = "protobuf-4.25.4-py3-none-any.whl", hash = "sha256:bfbebc1c8e4793cfd58589acfb8a1026be0003e852b9da7db5a4285bde996978"},
-    {file = "protobuf-4.25.4.tar.gz", hash = "sha256:0dc4a62cc4052a036ee2204d26fe4d835c62827c855c8a03f29fe6da146b380d"},
+    {file = "protobuf-4.25.3-cp310-abi3-win32.whl", hash = "sha256:d4198877797a83cbfe9bffa3803602bbe1625dc30d8a097365dbc762e5790faa"},
+    {file = "protobuf-4.25.3-cp310-abi3-win_amd64.whl", hash = "sha256:209ba4cc916bab46f64e56b85b090607a676f66b473e6b762e6f1d9d591eb2e8"},
+    {file = "protobuf-4.25.3-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f1279ab38ecbfae7e456a108c5c0681e4956d5b1090027c1de0f934dfdb4b35c"},
+    {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:e7cb0ae90dd83727f0c0718634ed56837bfeeee29a5f82a7514c03ee1364c019"},
+    {file = "protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:7c8daa26095f82482307bc717364e7c13f4f1c99659be82890dcfc215194554d"},
+    {file = "protobuf-4.25.3-cp38-cp38-win32.whl", hash = "sha256:f4f118245c4a087776e0a8408be33cf09f6c547442c00395fbfb116fac2f8ac2"},
+    {file = "protobuf-4.25.3-cp38-cp38-win_amd64.whl", hash = "sha256:c053062984e61144385022e53678fbded7aea14ebb3e0305ae3592fb219ccfa4"},
+    {file = "protobuf-4.25.3-cp39-cp39-win32.whl", hash = "sha256:19b270aeaa0099f16d3ca02628546b8baefe2955bbe23224aaf856134eccf1e4"},
+    {file = "protobuf-4.25.3-cp39-cp39-win_amd64.whl", hash = "sha256:e3c97a1555fd6388f857770ff8b9703083de6bf1f9274a002a332d65fbb56c8c"},
+    {file = "protobuf-4.25.3-py3-none-any.whl", hash = "sha256:f0700d54bcf45424477e46a9f0944155b46fb0639d69728739c0e47bab83f2b9"},
+    {file = "protobuf-4.25.3.tar.gz", hash = "sha256:25b5d0b42fd000320bd7830b349e3b696435f3b329810427a6bcce6a5492cc5c"},
 ]
 
 [[package]]
@@ -4282,13 +4317,13 @@ torch = ["torch"]
 
 [[package]]
 name = "pymdown-extensions"
-version = "10.9"
+version = "10.8.1"
 description = "Extension pack for Python Markdown."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pymdown_extensions-10.9-py3-none-any.whl", hash = "sha256:d323f7e90d83c86113ee78f3fe62fc9dee5f56b54d912660703ea1816fed5626"},
-    {file = "pymdown_extensions-10.9.tar.gz", hash = "sha256:6ff740bcd99ec4172a938970d42b96128bdc9d4b9bcad72494f29921dc69b753"},
+    {file = "pymdown_extensions-10.8.1-py3-none-any.whl", hash = "sha256:f938326115884f48c6059c67377c46cf631c733ef3629b6eed1349989d1b30cb"},
+    {file = "pymdown_extensions-10.8.1.tar.gz", hash = "sha256:3ab1db5c9e21728dabf75192d71471f8e50f216627e9a1fa9535ecb0231b9940"},
 ]
 
 [package.dependencies]
@@ -4353,13 +4388,13 @@ files = [
 
 [[package]]
 name = "pyright"
-version = "1.1.373"
+version = "1.1.372"
 description = "Command line wrapper for pyright"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "pyright-1.1.373-py3-none-any.whl", hash = "sha256:b805413227f2c209f27b14b55da27fe5e9fb84129c9f1eb27708a5d12f6f000e"},
-    {file = "pyright-1.1.373.tar.gz", hash = "sha256:f41bcfc8b9d1802b09921a394d6ae1ce19694957b628bc657629688daf8a83ff"},
+    {file = "pyright-1.1.372-py3-none-any.whl", hash = "sha256:25b15fb8967740f0949fd35b963777187f0a0404c0bd753cc966ec139f3eaa0b"},
+    {file = "pyright-1.1.372.tar.gz", hash = "sha256:a9f5e0daa955daaa17e3d1ef76d3623e75f8afd5e37b437d3ff84d5b38c15420"},
 ]
 
 [package.dependencies]
@@ -4393,13 +4428,13 @@ files = [
 
 [[package]]
 name = "pytest"
-version = "8.3.2"
+version = "8.3.1"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pytest-8.3.2-py3-none-any.whl", hash = "sha256:4ba08f9ae7dcf84ded419494d229b48d0903ea6407b030eaec46df5e6a73bba5"},
-    {file = "pytest-8.3.2.tar.gz", hash = "sha256:c132345d12ce551242c87269de812483f5bcc87cdbb4722e48487ba194f9fdce"},
+    {file = "pytest-8.3.1-py3-none-any.whl", hash = "sha256:e9600ccf4f563976e2c99fa02c7624ab938296551f280835ee6516df8bc4ae8c"},
+    {file = "pytest-8.3.1.tar.gz", hash = "sha256:7e8e5c5abd6e93cb1cc151f23e57adc31fcf8cfd2a3ff2da63e23f732de35db6"},
 ]
 
 [package.dependencies]
@@ -4413,24 +4448,6 @@ tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 [package.extras]
 dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
 
-[[package]]
-name = "pytest-asyncio"
-version = "0.23.8"
-description = "Pytest support for asyncio"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pytest_asyncio-0.23.8-py3-none-any.whl", hash = "sha256:50265d892689a5faefb84df80819d1ecef566eb3549cf915dfb33569359d1ce2"},
-    {file = "pytest_asyncio-0.23.8.tar.gz", hash = "sha256:759b10b33a6dc61cce40a8bd5205e302978bbbcc00e279a8b61d9a6a3c82e4d3"},
-]
-
-[package.dependencies]
-pytest = ">=7.0.0,<9"
-
-[package.extras]
-docs = ["sphinx (>=5.3)", "sphinx-rtd-theme (>=1.0)"]
-testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
-
 [[package]]
 name = "pytest-vcr"
 version = "1.0.2"
@@ -4866,22 +4883,22 @@ files = [
 
 [[package]]
 name = "selenium"
-version = "4.23.1"
+version = "4.22.0"
 description = "Official Python bindings for Selenium WebDriver"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "selenium-4.23.1-py3-none-any.whl", hash = "sha256:3a8d9f23dc636bd3840dd56f00c2739e32ec0c1e34a821dd553e15babef24477"},
-    {file = "selenium-4.23.1.tar.gz", hash = "sha256:128d099e66284437e7128d2279176ec7a06e6ec7426e167f5d34987166bd8f46"},
+    {file = "selenium-4.22.0-py3-none-any.whl", hash = "sha256:e424991196e9857e19bf04fe5c1c0a4aac076794ff5e74615b1124e729d93104"},
+    {file = "selenium-4.22.0.tar.gz", hash = "sha256:903c8c9d61b3eea6fcc9809dc7d9377e04e2ac87709876542cc8f863e482c4ce"},
 ]
 
 [package.dependencies]
 certifi = ">=2021.10.8"
 trio = ">=0.17,<1.0"
 trio-websocket = ">=0.9,<1.0"
-typing_extensions = ">=4.9,<5.0"
+typing_extensions = ">=4.9.0"
 urllib3 = {version = ">=1.26,<3", extras = ["socks"]}
-websocket-client = ">=1.8,<2.0"
+websocket-client = ">=1.8.0"
 
 [[package]]
 name = "semver"
@@ -4896,13 +4913,13 @@ files = [
 
 [[package]]
 name = "setuptools"
-version = "72.1.0"
+version = "71.1.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "setuptools-72.1.0-py3-none-any.whl", hash = "sha256:5a03e1860cf56bb6ef48ce186b0e557fdba433237481a9a625176c2831be15d1"},
-    {file = "setuptools-72.1.0.tar.gz", hash = "sha256:8d243eff56d095e5817f796ede6ae32941278f542e0f941867cc05ae52b162ec"},
+    {file = "setuptools-71.1.0-py3-none-any.whl", hash = "sha256:33874fdc59b3188304b2e7c80d9029097ea31627180896fb549c578ceb8a0855"},
+    {file = "setuptools-71.1.0.tar.gz", hash = "sha256:032d42ee9fb536e33087fb66cac5f840eb9391ed05637b3f2a76a7c8fb477936"},
 ]
 
 [package.extras]
@@ -5251,6 +5268,34 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["pytest", "ruff"]
 
+[[package]]
+name = "together"
+version = "1.2.3"
+description = "Python client for Together's Cloud Platform!"
+optional = false
+python-versions = "<4.0,>=3.8"
+files = [
+    {file = "together-1.2.3-py3-none-any.whl", hash = "sha256:bbafb4b8340e0f7e0ddb11ad447eb3467c591090910d0291cfbf74b47af045c1"},
+    {file = "together-1.2.3.tar.gz", hash = "sha256:4ea7626a9581d16fbf293e3eaf91557c43dea044627cf6dbe458bbf43408a6b2"},
+]
+
+[package.dependencies]
+aiohttp = ">=3.9.3,<4.0.0"
+click = ">=8.1.7,<9.0.0"
+eval-type-backport = ">=0.1.3,<0.3.0"
+filelock = ">=3.13.1,<4.0.0"
+numpy = [
+    {version = ">=1.23.5", markers = "python_version < \"3.12\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+]
+pillow = ">=10.3.0,<11.0.0"
+pyarrow = ">=10.0.1"
+pydantic = ">=2.6.3,<3.0.0"
+requests = ">=2.31.0,<3.0.0"
+tabulate = ">=0.9.0,<0.10.0"
+tqdm = ">=4.66.2,<5.0.0"
+typer = ">=0.9,<0.13"
+
 [[package]]
 name = "tokenizers"
 version = "0.19.1"
@@ -6099,4 +6144,4 @@ tools = ["crewai-tools"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<=3.13"
-content-hash = "8df022f5ec0997c0a0f5710476139d9117c1057889c158e958f2c8efd22a4756"
+content-hash = "f5ad9babb3c57c405e39232020e8cbfaaeb5c315c2e7c5bb8fdf66792f260343"

pyproject.toml

@@ -52,7 +52,6 @@ crewai-tools = "^0.4.26"
 pytest = "^8.0.0"
 pytest-vcr = "^1.0.2"
 python-dotenv = "1.0.0"
-pytest-asyncio = "^0.23.7"
 
 [tool.poetry.scripts]
 crewai = "crewai.cli.cli:crewai"

src/crewai/agents/agent_builder/utilities/base_token_process.py

@@ -1,4 +1,4 @@
-from crewai.types.usage_metrics import UsageMetrics
+from typing import Any, Dict
 
 
 class TokenProcess:
@@ -18,10 +18,10 @@ class TokenProcess:
     def sum_successful_requests(self, requests: int):
         self.successful_requests = self.successful_requests + requests
 
-    def get_summary(self) -> UsageMetrics:
-        return UsageMetrics(
-            total_tokens=self.total_tokens,
-            prompt_tokens=self.prompt_tokens,
-            completion_tokens=self.completion_tokens,
-            successful_requests=self.successful_requests,
-        )
+    def get_summary(self) -> Dict[str, Any]:
+        return {
+            "total_tokens": self.total_tokens,
+            "prompt_tokens": self.prompt_tokens,
+            "completion_tokens": self.completion_tokens,
+            "successful_requests": self.successful_requests,
+        }

src/crewai/agents/executor.py

@@ -1,6 +1,8 @@
 import threading
 import time
-from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterator, List, Literal, Optional, Tuple, Union
+import click
+
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
@@ -11,12 +13,21 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
 
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.summarize import load_summarize_chain
+
 from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.tools_handler import ToolsHandler
+
+
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 from crewai.utilities.training_handler import CrewTrainingHandler
+from crewai.utilities.logger import Logger
 
 
 class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
@@ -40,6 +51,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     system_template: Optional[str] = None
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
+    _logger: Logger = Logger(verbose_level=2)
+    _fit_context_window_strategy: Optional[Literal["summarize"]] = "summarize"
 
     def _call(
         self,
@@ -56,7 +69,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
         )
         intermediate_steps: List[Tuple[AgentAction, str]] = []
         # Allowing human input given task setting
-        if self.task and self.task.human_input:
+        if self.task.human_input:
             self.should_ask_for_human_input = True
 
         # Let's start tracking the number of iterations and time elapsed
@@ -131,7 +144,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
 
             # Call the LLM to see what to do.
-            output = self.agent.plan(  # type: ignore #  Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
+            output = self.agent.plan(
                 intermediate_steps,
                 callbacks=run_manager.get_child() if run_manager else None,
                 **inputs,
@@ -185,6 +198,27 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             yield AgentStep(action=output, observation=observation)
             return
 
+        except Exception as e:
+            if LLMContextLengthExceededException(str(e))._is_context_limit_error(
+                str(e)
+            ):
+                output = self._handle_context_length_error(
+                    intermediate_steps, run_manager, inputs
+                )
+
+                if isinstance(output, AgentFinish):
+                    yield output
+                elif isinstance(output, list):
+                    for step in output:
+                        yield step
+                return
+
+            yield AgentStep(
+                action=AgentAction("_Exception", str(e), str(e)),
+                observation=str(e),
+            )
+            return
+
         # If the tool chosen is the finishing tool, then we end and return.
         if isinstance(output, AgentFinish):
             if self.should_ask_for_human_input:
@@ -235,6 +269,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                 agent=self.crew_agent,
                 action=agent_action,
             )
+
             tool_calling = tool_usage.parse(agent_action.log)
 
             if isinstance(tool_calling, ToolUsageErrorException):
@@ -280,3 +315,91 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             CrewTrainingHandler(TRAINING_DATA_FILE).append(
                 self.crew._train_iteration, agent_id, training_data
             )
+
+    def _handle_context_length(
+        self, intermediate_steps: List[Tuple[AgentAction, str]]
+    ) -> List[Tuple[AgentAction, str]]:
+        text = intermediate_steps[0][1]
+        original_action = intermediate_steps[0][0]
+
+        text_splitter = RecursiveCharacterTextSplitter(
+            separators=["\n\n", "\n"],
+            chunk_size=8000,
+            chunk_overlap=500,
+        )
+
+        if self._fit_context_window_strategy == "summarize":
+            docs = text_splitter.create_documents([text])
+            self._logger.log(
+                "debug",
+                "Summarizing Content, it is recommended to use a RAG tool",
+                color="bold_blue",
+            )
+            summarize_chain = load_summarize_chain(
+                self.llm, chain_type="map_reduce", verbose=True
+            )
+            summarized_docs = []
+            for doc in docs:
+                summary = summarize_chain.invoke(
+                    {"input_documents": [doc]}, return_only_outputs=True
+                )
+
+                summarized_docs.append(summary["output_text"])
+
+            formatted_results = "\n\n".join(summarized_docs)
+            summary_step = AgentStep(
+                action=AgentAction(
+                    tool=original_action.tool,
+                    tool_input=original_action.tool_input,
+                    log=original_action.log,
+                ),
+                observation=formatted_results,
+            )
+            summary_tuple = (summary_step.action, summary_step.observation)
+            return [summary_tuple]
+
+        return intermediate_steps
+
+    def _handle_context_length_error(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        run_manager: Optional[CallbackManagerForChainRun],
+        inputs: Dict[str, str],
+    ) -> Union[AgentFinish, List[AgentStep]]:
+        self._logger.log(
+            "debug",
+            "Context length exceeded. Asking user if they want to use summarize prompt to fit, this will reduce context length.",
+            color="yellow",
+        )
+        user_choice = click.confirm(
+            "Context length exceeded. Do you want to summarize the text to fit models context window?"
+        )
+        if user_choice:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Using summarize prompt to fit, this will reduce context length.",
+                color="bold_blue",
+            )
+            intermediate_steps = self._handle_context_length(intermediate_steps)
+
+            output = self.agent.plan(
+                intermediate_steps,
+                callbacks=run_manager.get_child() if run_manager else None,
+                **inputs,
+            )
+
+            if isinstance(output, AgentFinish):
+                return output
+            elif isinstance(output, AgentAction):
+                return [AgentStep(action=output, observation=None)]
+            else:
+                return [AgentStep(action=action, observation=None) for action in output]
+        else:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
+                color="red",
+            )
+            raise SystemExit(
+                "Context length exceeded and user opted not to summarize. Consider using smaller text or RAG tools from crewai_tools."
+            )

src/crewai/crew.py

@@ -3,7 +3,7 @@ import json
 import uuid
 from concurrent.futures import Future
 from hashlib import md5
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
@@ -32,9 +32,11 @@ from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
-from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
+from crewai.utilities.constants import (
+    TRAINED_AGENTS_DATA_FILE,
+    TRAINING_DATA_FILE,
+)
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.formatter import (
@@ -50,9 +52,6 @@ try:
 except ImportError:
     agentops = None
 
-if TYPE_CHECKING:
-    from crewai.pipeline.pipeline import Pipeline
-
 
 class Crew(BaseModel):
     """
@@ -98,13 +97,12 @@ class Crew(BaseModel):
         default_factory=TaskOutputStorageHandler
     )
 
-    name: Optional[str] = Field(default=None)
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
     agents: List[BaseAgent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
-    verbose: int = Field(default=0)
+    verbose: Union[int, bool] = Field(default=0)
     memory: bool = Field(
         default=False,
         description="Whether the crew should use memory to store memories of it's execution",
@@ -113,7 +111,7 @@ class Crew(BaseModel):
         default={"provider": "openai"},
         description="Configuration for the embedder to be used for the crew.",
     )
-    usage_metrics: Optional[UsageMetrics] = Field(
+    usage_metrics: Optional[dict] = Field(
         default=None,
         description="Metrics for the LLM usage during all tasks execution.",
     )
@@ -149,8 +147,8 @@ class Crew(BaseModel):
         default=None,
         description="Path to the prompt json file to be used for the crew.",
     )
-    output_log_file: Optional[str] = Field(
-        default=None,
+    output_log_file: Optional[Union[bool, str]] = Field(
+        default=False,
         description="output_log_file",
     )
     planning: Optional[bool] = Field(
@@ -455,7 +453,7 @@ class Crew(BaseModel):
         if self.planning:
             self._handle_crew_planning()
 
-        metrics: List[UsageMetrics] = []
+        metrics = []
 
         if self.process == Process.sequential:
             result = self._run_sequential_process()
@@ -465,12 +463,11 @@ class Crew(BaseModel):
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
             )
-
         metrics += [agent._token_process.get_summary() for agent in self.agents]
 
-        self.usage_metrics = UsageMetrics()
-        for metric in metrics:
-            self.usage_metrics.add_usage_metrics(metric)
+        self.usage_metrics = {
+            key: sum([m[key] for m in metrics if m is not None]) for key in metrics[0]
+        }
 
         return result
 
@@ -479,7 +476,12 @@ class Crew(BaseModel):
         results: List[CrewOutput] = []
 
         # Initialize the parent crew's usage metrics
-        total_usage_metrics = UsageMetrics()
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
 
         for input_data in inputs:
             crew = self.copy()
@@ -487,7 +489,8 @@ class Crew(BaseModel):
             output = crew.kickoff(inputs=input_data)
 
             if crew.usage_metrics:
-                total_usage_metrics.add_usage_metrics(crew.usage_metrics)
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
 
             results.append(output)
 
@@ -516,10 +519,29 @@ class Crew(BaseModel):
 
         results = await asyncio.gather(*tasks)
 
-        total_usage_metrics = UsageMetrics()
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
         for crew in crew_copies:
             if crew.usage_metrics:
-                total_usage_metrics.add_usage_metrics(crew.usage_metrics)
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
+
+        self.usage_metrics = total_usage_metrics
+
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
+        for crew in crew_copies:
+            if crew.usage_metrics:
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
 
         self.usage_metrics = total_usage_metrics
         self._task_output_handler.reset()
@@ -910,18 +932,25 @@ class Crew(BaseModel):
             )
         self._telemetry.end_crew(self, final_string_output)
 
-    def calculate_usage_metrics(self) -> UsageMetrics:
+    def calculate_usage_metrics(self) -> Dict[str, int]:
         """Calculates and returns the usage metrics."""
-        total_usage_metrics = UsageMetrics()
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
 
         for agent in self.agents:
             if hasattr(agent, "_token_process"):
                 token_sum = agent._token_process.get_summary()
-                total_usage_metrics.add_usage_metrics(token_sum)
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += token_sum.get(key, 0)
 
         if self.manager_agent and hasattr(self.manager_agent, "_token_process"):
             token_sum = self.manager_agent._token_process.get_summary()
-            total_usage_metrics.add_usage_metrics(token_sum)
+            for key in total_usage_metrics:
+                total_usage_metrics[key] += token_sum.get(key, 0)
 
         return total_usage_metrics
 
@@ -940,17 +969,5 @@ class Crew(BaseModel):
 
         evaluator.print_crew_evaluation_result()
 
-    def __rshift__(self, other: "Crew") -> "Pipeline":
-        """
-        Implements the >> operator to add another Crew to an existing Pipeline.
-        """
-        from crewai.pipeline.pipeline import Pipeline
-
-        if not isinstance(other, Crew):
-            raise TypeError(
-                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
-            )
-        return Pipeline(stages=[self, other])
-
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/crews/crew_output.py

@@ -5,7 +5,6 @@ from pydantic import BaseModel, Field
 
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
-from crewai.types.usage_metrics import UsageMetrics
 
 
 class CrewOutput(BaseModel):
@@ -21,7 +20,9 @@ class CrewOutput(BaseModel):
     tasks_output: list[TaskOutput] = Field(
         description="Output of each task", default=[]
     )
-    token_usage: UsageMetrics = Field(description="Processed token summary", default={})
+    token_usage: Dict[str, Any] = Field(
+        description="Processed token summary", default={}
+    )
 
     @property
     def json(self) -> Optional[str]:

src/crewai/pipeline/__init__.py

@@ -1,3 +0,0 @@
-from crewai.pipeline.pipeline import Pipeline
-
-__all__ = ["Pipeline"]

src/crewai/pipeline/pipeline.py

@@ -1,371 +0,0 @@
-import asyncio
-import copy
-from typing import Any, Dict, List, Tuple, Union
-
-from pydantic import BaseModel, Field, model_validator
-
-from crewai.crew import Crew
-from crewai.crews.crew_output import CrewOutput
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-from crewai.types.usage_metrics import UsageMetrics
-
-Trace = Union[Union[str, Dict[str, Any]], List[Union[str, Dict[str, Any]]]]
-
-
-"""
-Developer Notes:
-
-This module defines a Pipeline class that represents a sequence of operations (stages)
-to process inputs. Each stage can be either sequential or parallel, and the pipeline
-can process multiple kickoffs concurrently.
-
-Core Loop Explanation:
-1. The `process_kickoffs` method processes multiple kickoffs in parallel, each going through
-   all pipeline stages.
-2. The `process_single_kickoff` method handles the processing of a single kickouff through
-   all stages, updating metrics and input data along the way.
-3. The `_process_stage` method determines whether a stage is sequential or parallel
-   and processes it accordingly.
-4. The `_process_single_crew` and `_process_parallel_crews` methods handle the
-   execution of single and parallel crew stages.
-5. The `_update_metrics_and_input` method updates usage metrics and the current input
-   with the outputs from a stage.
-6. The `_build_pipeline_kickoff_results` method constructs the final results of the
-   pipeline kickoff, including traces and outputs.
-
-Handling Traces and Crew Outputs:
-- During the processing of stages, we handle the results (traces and crew outputs)
-  for all stages except the last one differently from the final stage.
-- For intermediate stages, the primary focus is on passing the input data between stages.
-  This involves merging the output dictionaries from all crews in a stage into a single
-  dictionary and passing it to the next stage. This merged dictionary allows for smooth
-  data flow between stages.
-- For the final stage, in addition to passing the input data, we also need to prepare
-  the final outputs and traces to be returned as the overall result of the pipeline kickoff.
-  In this case, we do not merge the results, as each result needs to be included
-  separately in its own pipeline kickoff result.
-
-Pipeline Terminology:
-- Pipeline: The overall structure that defines a sequence of operations.
-- Stage: A distinct part of the pipeline, which can be either sequential or parallel.
-- Kickoff: A specific execution of the pipeline for a given set of inputs, representing a single instance of processing through the pipeline.
-- Branch: Parallel executions within a stage (e.g., concurrent crew operations).
-- Trace: The journey of an individual input through the entire pipeline.
-
-Example pipeline structure:
-crew1 >> crew2 >> crew3 
-
-This represents a pipeline with three sequential stages:
-1. crew1 is the first stage, which processes the input and passes its output to crew2.
-2. crew2 is the second stage, which takes the output from crew1 as its input, processes it, and passes its output to crew3.
-3. crew3 is the final stage, which takes the output from crew2 as its input and produces the final output of the pipeline.
-
-Each input creates its own kickoff, flowing through all stages of the pipeline.
-Multiple kickoffss can be processed concurrently, each following the defined pipeline structure.
-
-Another example pipeline structure:
-crew1 >> [crew2, crew3] >> crew4
-
-This represents a pipeline with three stages:
-1. A sequential stage (crew1)
-2. A parallel stage with two branches (crew2 and crew3 executing concurrently)
-3. Another sequential stage (crew4)
-
-Each input creates its own kickoff, flowing through all stages of the pipeline.
-Multiple kickoffs can be processed concurrently, each following the defined pipeline structure.
-"""
-
-
-class Pipeline(BaseModel):
-    stages: List[Union[Crew, List[Crew]]] = Field(
-        ..., description="List of crews representing stages to be executed in sequence"
-    )
-
-    @model_validator(mode="before")
-    @classmethod
-    def validate_stages(cls, values):
-        """
-        Validates the stages to ensure correct nesting and types.
-
-        Args:
-            values (dict): Dictionary containing the pipeline stages.
-
-        Returns:
-            dict: Validated stages.
-        """
-        stages = values.get("stages", [])
-
-        def check_nesting_and_type(item, depth=0):
-            if depth > 1:
-                raise ValueError("Double nesting is not allowed in pipeline stages")
-            if isinstance(item, list):
-                for sub_item in item:
-                    check_nesting_and_type(sub_item, depth + 1)
-            elif not isinstance(item, Crew):
-                raise ValueError(
-                    f"Expected Crew instance or list of Crews, got {type(item)}"
-                )
-
-        for stage in stages:
-            check_nesting_and_type(stage)
-        return values
-
-    async def kickoff(
-        self, inputs: List[Dict[str, Any]]
-    ) -> List[PipelineKickoffResult]:
-        """
-        Processes multiple runs in parallel, each going through all pipeline stages.
-
-        Args:
-            inputs (List[Dict[str, Any]]): List of inputs for each run.
-
-        Returns:
-            List[PipelineKickoffResult]: List of results from each run.
-        """
-        pipeline_results: List[PipelineKickoffResult] = []
-
-        # Process all runs in parallel
-        all_run_results = await asyncio.gather(
-            *(self.process_single_kickoff(input_data) for input_data in inputs)
-        )
-
-        # Flatten the list of lists into a single list of results
-        pipeline_results.extend(
-            result for run_result in all_run_results for result in run_result
-        )
-
-        return pipeline_results
-
-    async def process_single_kickoff(
-        self, kickoff_input: Dict[str, Any]
-    ) -> List[PipelineKickoffResult]:
-        """
-        Processes a single run through all pipeline stages.
-
-        Args:
-            input (Dict[str, Any]): The input for the run.
-
-        Returns:
-            List[PipelineKickoffResult]: The results of processing the run.
-        """
-        initial_input = copy.deepcopy(kickoff_input)
-        current_input = copy.deepcopy(kickoff_input)
-        pipeline_usage_metrics: Dict[str, UsageMetrics] = {}
-        all_stage_outputs: List[List[CrewOutput]] = []
-        traces: List[List[Union[str, Dict[str, Any]]]] = [[initial_input]]
-
-        for stage in self.stages:
-            stage_input = copy.deepcopy(current_input)
-            stage_outputs, stage_trace = await self._process_stage(stage, stage_input)
-
-            self._update_metrics_and_input(
-                pipeline_usage_metrics, current_input, stage, stage_outputs
-            )
-            traces.append(stage_trace)
-            all_stage_outputs.append(stage_outputs)
-
-        return self._build_pipeline_kickoff_results(
-            all_stage_outputs, traces, pipeline_usage_metrics
-        )
-
-    async def _process_stage(
-        self, stage: Union[Crew, List[Crew]], current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes a single stage of the pipeline, which can be either sequential or parallel.
-
-        Args:
-            stage (Union[Crew, List[Crew]]): The stage to process.
-            current_input (Dict[str, Any]): The input for the stage.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The outputs and trace of the stage.
-        """
-        if isinstance(stage, Crew):
-            return await self._process_single_crew(stage, current_input)
-        else:
-            return await self._process_parallel_crews(stage, current_input)
-
-    async def _process_single_crew(
-        self, crew: Crew, current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes a single crew.
-
-        Args:
-            crew (Crew): The crew to process.
-            current_input (Dict[str, Any]): The input for the crew.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The output and trace of the crew.
-        """
-        output = await crew.kickoff_async(inputs=current_input)
-        return [output], [crew.name or str(crew.id)]
-
-    async def _process_parallel_crews(
-        self, crews: List[Crew], current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes multiple crews in parallel.
-
-        Args:
-            crews (List[Crew]): The list of crews to process in parallel.
-            current_input (Dict[str, Any]): The input for the crews.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The outputs and traces of the crews.
-        """
-        parallel_outputs = await asyncio.gather(
-            *[crew.kickoff_async(inputs=current_input) for crew in crews]
-        )
-        return parallel_outputs, [crew.name or str(crew.id) for crew in crews]
-
-    def _update_metrics_and_input(
-        self,
-        usage_metrics: Dict[str, UsageMetrics],
-        current_input: Dict[str, Any],
-        stage: Union[Crew, List[Crew]],
-        outputs: List[CrewOutput],
-    ) -> None:
-        """
-        Updates metrics and current input with the outputs of a stage.
-
-        Args:
-            usage_metrics (Dict[str, Any]): The usage metrics to update.
-            current_input (Dict[str, Any]): The current input to update.
-            stage (Union[Crew, List[Crew]]): The stage that was processed.
-            outputs (List[CrewOutput]): The outputs of the stage.
-        """
-        for crew, output in zip([stage] if isinstance(stage, Crew) else stage, outputs):
-            usage_metrics[crew.name or str(crew.id)] = output.token_usage
-            current_input.update(output.to_dict())
-
-    def _build_pipeline_kickoff_results(
-        self,
-        all_stage_outputs: List[List[CrewOutput]],
-        traces: List[List[Union[str, Dict[str, Any]]]],
-        token_usage: Dict[str, UsageMetrics],
-    ) -> List[PipelineKickoffResult]:
-        """
-        Builds the results of a pipeline run.
-
-        Args:
-            all_stage_outputs (List[List[CrewOutput]]): All stage outputs.
-            traces (List[List[Union[str, Dict[str, Any]]]]): All traces.
-            token_usage (Dict[str, Any]): Token usage metrics.
-
-        Returns:
-            List[PipelineKickoffResult]: The results of the pipeline run.
-        """
-        formatted_traces = self._format_traces(traces)
-        formatted_crew_outputs = self._format_crew_outputs(all_stage_outputs)
-
-        return [
-            PipelineKickoffResult(
-                token_usage=token_usage,
-                trace=formatted_trace,
-                raw=crews_outputs[-1].raw,
-                pydantic=crews_outputs[-1].pydantic,
-                json_dict=crews_outputs[-1].json_dict,
-                crews_outputs=crews_outputs,
-            )
-            for crews_outputs, formatted_trace in zip(
-                formatted_crew_outputs, formatted_traces
-            )
-        ]
-
-    def _format_traces(
-        self, traces: List[List[Union[str, Dict[str, Any]]]]
-    ) -> List[List[Trace]]:
-        """
-        Formats the traces of a pipeline run.
-
-        Args:
-            traces (List[List[Union[str, Dict[str, Any]]]]): The traces to format.
-
-        Returns:
-            List[List[Trace]]: The formatted traces.
-        """
-        formatted_traces: List[Trace] = self._format_single_trace(traces[:-1])
-        return self._format_multiple_traces(formatted_traces, traces[-1])
-
-    def _format_single_trace(
-        self, traces: List[List[Union[str, Dict[str, Any]]]]
-    ) -> List[Trace]:
-        """
-        Formats single traces.
-
-        Args:
-            traces (List[List[Union[str, Dict[str, Any]]]]): The traces to format.
-
-        Returns:
-            List[Trace]: The formatted single traces.
-        """
-        formatted_traces: List[Trace] = []
-        for trace in traces:
-            formatted_traces.append(trace[0] if len(trace) == 1 else trace)
-        return formatted_traces
-
-    def _format_multiple_traces(
-        self,
-        formatted_traces: List[Trace],
-        final_trace: List[Union[str, Dict[str, Any]]],
-    ) -> List[List[Trace]]:
-        """
-        Formats multiple traces.
-
-        Args:
-            formatted_traces (List[Trace]): The formatted single traces.
-            final_trace (List[Union[str, Dict[str, Any]]]): The final trace to format.
-
-        Returns:
-            List[List[Trace]]: The formatted multiple traces.
-        """
-        traces_to_return: List[List[Trace]] = []
-        if len(final_trace) == 1:
-            formatted_traces.append(final_trace[0])
-            traces_to_return.append(formatted_traces)
-        else:
-            for trace in final_trace:
-                copied_traces = formatted_traces.copy()
-                copied_traces.append(trace)
-                traces_to_return.append(copied_traces)
-        return traces_to_return
-
-    def _format_crew_outputs(
-        self, all_stage_outputs: List[List[CrewOutput]]
-    ) -> List[List[CrewOutput]]:
-        """
-        Formats the outputs of all stages into a list of crew outputs.
-
-        Args:
-            all_stage_outputs (List[List[CrewOutput]]): All stage outputs.
-
-        Returns:
-            List[List[CrewOutput]]: Formatted crew outputs.
-        """
-        crew_outputs: List[CrewOutput] = [
-            output
-            for stage_outputs in all_stage_outputs[:-1]
-            for output in stage_outputs
-        ]
-        return [crew_outputs + [output] for output in all_stage_outputs[-1]]
-
-    def __rshift__(self, other: Any) -> "Pipeline":
-        """
-        Implements the >> operator to add another Stage (Crew or List[Crew]) to an existing Pipeline.
-
-        Args:
-            other (Any): The stage to add.
-
-        Returns:
-            Pipeline: A new pipeline with the added stage.
-        """
-        if isinstance(other, Crew):
-            return type(self)(stages=self.stages + [other])
-        elif isinstance(other, list) and all(isinstance(crew, Crew) for crew in other):
-            return type(self)(stages=self.stages + [other])
-        else:
-            raise TypeError(
-                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
-            )

src/crewai/pipeline/pipeline_kickoff_result.py

@@ -1,61 +0,0 @@
-import json
-import uuid
-from typing import Any, Dict, List, Optional, Union
-
-from pydantic import UUID4, BaseModel, Field
-
-from crewai.crews.crew_output import CrewOutput
-from crewai.types.usage_metrics import UsageMetrics
-
-
-class PipelineKickoffResult(BaseModel):
-    """Class that represents the result of a pipeline run."""
-
-    id: UUID4 = Field(
-        default_factory=uuid.uuid4,
-        frozen=True,
-        description="Unique identifier for the object, not set by user.",
-    )
-    raw: str = Field(description="Raw output of the pipeline run", default="")
-    pydantic: Any = Field(
-        description="Pydantic output of the pipeline run", default=None
-    )
-    json_dict: Union[Dict[str, Any], None] = Field(
-        description="JSON dict output of the pipeline run", default={}
-    )
-
-    token_usage: Dict[str, UsageMetrics] = Field(
-        description="Token usage for each crew in the run"
-    )
-    trace: List[Any] = Field(
-        description="Trace of the journey of inputs through the run"
-    )
-    crews_outputs: List[CrewOutput] = Field(
-        description="Output from each crew in the run",
-        default=[],
-    )
-
-    @property
-    def json(self) -> Optional[str]:
-        if self.crews_outputs[-1].tasks_output[-1].output_format != "json":
-            raise ValueError(
-                "No JSON output found in the final task of the final crew. Please make sure to set the output_json property in the final task in your crew."
-            )
-
-        return json.dumps(self.json_dict)
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert json_output and pydantic_output to a dictionary."""
-        output_dict = {}
-        if self.json_dict:
-            output_dict.update(self.json_dict)
-        elif self.pydantic:
-            output_dict.update(self.pydantic.model_dump())
-        return output_dict
-
-    def __str__(self):
-        if self.pydantic:
-            return str(self.pydantic)
-        if self.json_dict:
-            return str(self.json_dict)
-        return self.raw

src/crewai/pipeline/pipeline_output.py

@@ -1,20 +0,0 @@
-import uuid
-from typing import List
-
-from pydantic import UUID4, BaseModel, Field
-
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-
-
-class PipelineOutput(BaseModel):
-    id: UUID4 = Field(
-        default_factory=uuid.uuid4,
-        frozen=True,
-        description="Unique identifier for the object, not set by user.",
-    )
-    run_results: List[PipelineKickoffResult] = Field(
-        description="List of results for each run through the pipeline", default=[]
-    )
-
-    def add_run_result(self, result: PipelineKickoffResult):
-        self.run_results.append(result)

src/crewai/task.py

@@ -47,7 +47,6 @@ class Task(BaseModel):
     tools_errors: int = 0
     delegations: int = 0
     i18n: I18N = I18N()
-    name: Optional[str] = Field(default=None)
     prompt_context: Optional[str] = None
     description: str = Field(description="Description of the actual task.")
     expected_output: str = Field(

src/crewai/tools/tool_usage.py

@@ -16,7 +16,7 @@ try:
 except ImportError:
     agentops = None
 
-OPENAI_BIGGER_MODELS = ["gpt-4"]
+OPENAI_BIGGER_MODELS = ["gpt-4o"]
 
 
 class ToolUsageErrorException(Exception):

src/crewai/types/usage_metrics.py

@@ -1,36 +0,0 @@
-from pydantic import BaseModel, Field
-
-
-class UsageMetrics(BaseModel):
-    """
-    Model to track usage metrics for the crew's execution.
-
-    Attributes:
-        total_tokens: Total number of tokens used.
-        prompt_tokens: Number of tokens used in prompts.
-        completion_tokens: Number of tokens used in completions.
-        successful_requests: Number of successful requests made.
-    """
-
-    total_tokens: int = Field(default=0, description="Total number of tokens used.")
-    prompt_tokens: int = Field(
-        default=0, description="Number of tokens used in prompts."
-    )
-    completion_tokens: int = Field(
-        default=0, description="Number of tokens used in completions."
-    )
-    successful_requests: int = Field(
-        default=0, description="Number of successful requests made."
-    )
-
-    def add_usage_metrics(self, usage_metrics: "UsageMetrics"):
-        """
-        Add the usage metrics from another UsageMetrics object.
-
-        Args:
-            usage_metrics (UsageMetrics): The usage metrics to add.
-        """
-        self.total_tokens += usage_metrics.total_tokens
-        self.prompt_tokens += usage_metrics.prompt_tokens
-        self.completion_tokens += usage_metrics.completion_tokens
-        self.successful_requests += usage_metrics.successful_requests

src/crewai/utilities/__init__.py

@@ -7,6 +7,9 @@ from .parser import YamlParser
 from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
+from .exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 
 __all__ = [
     "Converter",
@@ -19,4 +22,5 @@ __all__ = [
     "Prompts",
     "RPMController",
     "YamlParser",
+    "LLMContextLengthExceededException",
 ]

src/crewai/utilities/exceptions/context_window_exceeding_exception.py

@@ -0,0 +1,26 @@
+class LLMContextLengthExceededException(Exception):
+    CONTEXT_LIMIT_ERRORS = [
+        "maximum context length",
+        "context length exceeded",
+        "context_length_exceeded",
+        "context window full",
+        "too many tokens",
+        "input is too long",
+        "exceeds token limit",
+    ]
+
+    def __init__(self, error_message: str):
+        self.original_error_message = error_message
+        super().__init__(self._get_error_message(error_message))
+
+    def _is_context_limit_error(self, error_message: str) -> bool:
+        return any(
+            phrase.lower() in error_message.lower()
+            for phrase in self.CONTEXT_LIMIT_ERRORS
+        )
+
+    def _get_error_message(self, error_message: str):
+        return (
+            f"LLM context length exceeded. Original error: {error_message}\n"
+            "Consider using a smaller input or implementing a text splitting strategy."
+        )

src/crewai/utilities/token_counter_callback.py

@@ -10,24 +10,24 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 class TokenCalcHandler(BaseCallbackHandler):
     model_name: str = ""
     token_cost_process: TokenProcess
+    encoding: tiktoken.Encoding
 
     def __init__(self, model_name, token_cost_process):
         self.model_name = model_name
         self.token_cost_process = token_cost_process
+        try:
+            self.encoding = tiktoken.encoding_for_model(self.model_name)
+        except KeyError:
+            self.encoding = tiktoken.get_encoding("cl100k_base")
 
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
-        try:
-            encoding = tiktoken.encoding_for_model(self.model_name)
-        except KeyError:
-            encoding = tiktoken.get_encoding("cl100k_base")
-
         if self.token_cost_process is None:
             return
 
         for prompt in prompts:
-            self.token_cost_process.sum_prompt_tokens(len(encoding.encode(prompt)))
+            self.token_cost_process.sum_prompt_tokens(len(self.encoding.encode(prompt)))
 
     async def on_llm_new_token(self, token: str, **kwargs) -> None:
         self.token_cost_process.sum_completion_tokens(1)

tests/agent_test.py

@@ -7,6 +7,7 @@ import pytest
 from langchain.tools import tool
 from langchain_core.exceptions import OutputParserException
 from langchain_openai import ChatOpenAI
+from langchain.schema import AgentAction
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
@@ -1014,3 +1015,75 @@ def test_agent_max_retry_limit():
                 ),
             ]
         )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    original_action = AgentAction(
+        tool="test_tool", tool_input="test_input", log="test_log"
+    )
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "y"
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.side_effect = ValueError(
+                    "Context length limit exceeded"
+                )
+
+                long_input = "This is a very long input. " * 10000
+
+                # Attempt to handle context length, expecting the mocked error
+                with pytest.raises(ValueError) as excinfo:
+                    agent.agent_executor._handle_context_length(
+                        [(original_action, long_input)]
+                    )
+
+                assert "Context length limit exceeded" in str(excinfo.value)
+                mock_handle_context.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit_cli_no():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    task = Task(description="test task", agent=agent, expected_output="test output")
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "n"
+            pytest.raises(SystemExit)
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.assert_not_called()

tests/cassettes/test_handle_context_length_exceeds_limit.yaml

@@ -0,0 +1,181 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \n you MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '938'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        The"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        is"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac1a40879b87d1f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 00:16:40 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MHUl15YVi607cmuLtQ84ESiH30IyJiIW1a40fopQ81w-1722471400-1.0.1.1-OGpq5Ezj6iE0ToM1diQllGb70.J3O_K2De9NbwZPWmW2qN07U20adJ_0yd6PKUNqMdL.xEnLcNAOWVmsfrLUrQ;
+        path=/; expires=Thu, 01-Aug-24 00:46:40 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=G2ZVNvfNfFk4DeKyZ7jMYetG7wOasINAGHstrOnuAY8-1722471400129-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '131'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15552000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b68b417b3fe1c67244279551e411b37a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_handle_context_length_exceeds_limit_cli_no.yaml

@@ -0,0 +1,162 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \n you MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '938'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac331b9eaee2b7f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 04:48:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OXht5zC71vWYFW_z_933m3sZfFS2xBez0DHv93FvT5s-1722487689-1.0.1.1-wE8JTR7MnwUgiiTDppYg8A7zLEiidth.MB0zrwONeAtNWRjKC1tuGf8LZYDlYIHUhqG73syYExpZ.5pZhzJkcg;
+        path=/; expires=Thu, 01-Aug-24 05:18:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=PAR7y4xRe4VzRT.7GK34Tq5r8vevY6xq0E.i.R40xnU-1722487689562-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '84'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15552000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_105dcfc53c9672dea0437249c12c3319
+    status:
+      code: 200
+      message: OK
+version: 1

tests/crew_test.py

@@ -18,7 +18,6 @@ from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
-from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import Logger, RPMController
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
@@ -598,10 +597,14 @@ def test_crew_kickoff_usage_metrics():
     assert len(results) == len(inputs)
     for result in results:
         # Assert that all required keys are in usage_metrics and their values are not None
-        assert result.token_usage.total_tokens > 0
-        assert result.token_usage.prompt_tokens > 0
-        assert result.token_usage.completion_tokens > 0
-        assert result.token_usage.successful_requests > 0
+        for key in [
+            "total_tokens",
+            "prompt_tokens",
+            "completion_tokens",
+            "successful_requests",
+        ]:
+            assert key in result.token_usage
+            assert result.token_usage[key] > 0
 
 
 def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
@@ -1312,12 +1315,12 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
 
     print(crew.usage_metrics)
 
-    assert crew.usage_metrics == UsageMetrics(
-        total_tokens=219,
-        prompt_tokens=201,
-        completion_tokens=18,
-        successful_requests=1,
-    )
+    assert crew.usage_metrics == {
+        "total_tokens": 219,
+        "prompt_tokens": 201,
+        "completion_tokens": 18,
+        "successful_requests": 1,
+    }
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

tests/pipeline/test_pipeline.py

@@ -1,468 +0,0 @@
-import json
-from unittest.mock import MagicMock
-
-import pytest
-from crewai.agent import Agent
-from crewai.crew import Crew
-from crewai.crews.crew_output import CrewOutput
-from crewai.pipeline.pipeline import Pipeline
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-from crewai.process import Process
-from crewai.task import Task
-from crewai.tasks.task_output import TaskOutput
-from crewai.types.usage_metrics import UsageMetrics
-from pydantic import BaseModel, ValidationError
-
-DEFAULT_TOKEN_USAGE = UsageMetrics(
-    total_tokens=100, prompt_tokens=50, completion_tokens=50, successful_requests=3
-)
-
-
-@pytest.fixture
-def mock_crew_factory():
-    def _create_mock_crew(name: str, output_json_dict=None, pydantic_output=None):
-        crew = MagicMock(spec=Crew)
-        task_output = TaskOutput(
-            description="Test task", raw="Task output", agent="Test Agent"
-        )
-        crew_output = CrewOutput(
-            raw="Test output",
-            tasks_output=[task_output],
-            token_usage=DEFAULT_TOKEN_USAGE,
-            json_dict=output_json_dict if output_json_dict else None,
-            pydantic=pydantic_output,
-        )
-
-        async def async_kickoff(inputs=None):
-            print("inputs in async_kickoff", inputs)
-            return crew_output
-
-        crew.kickoff_async.side_effect = async_kickoff
-
-        # Add more attributes that Procedure might be expecting
-        crew.verbose = False
-        crew.output_log_file = None
-        crew.max_rpm = None
-        crew.memory = False
-        crew.process = Process.sequential
-        crew.config = None
-        crew.cache = True
-        crew.name = name
-
-        # Add non-empty agents and tasks
-        mock_agent = MagicMock(spec=Agent)
-        mock_task = MagicMock(spec=Task)
-        mock_task.agent = mock_agent
-        mock_task.async_execution = False
-        mock_task.context = None
-
-        crew.agents = [mock_agent]
-        crew.tasks = [mock_task]
-
-        return crew
-
-    return _create_mock_crew
-
-
-def test_pipeline_initialization(mock_crew_factory):
-    """
-    Test that a Pipeline is correctly initialized with the given stages.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    crew2 = mock_crew_factory(name="Crew 2")
-
-    pipeline = Pipeline(stages=[crew1, crew2])
-    assert len(pipeline.stages) == 2
-    assert pipeline.stages[0] == crew1
-    assert pipeline.stages[1] == crew2
-
-
-@pytest.mark.asyncio
-async def test_pipeline_with_empty_input(mock_crew_factory):
-    """
-    Ensure the pipeline handles an empty input list correctly.
-    """
-    crew = mock_crew_factory(name="Test Crew")
-    pipeline = Pipeline(stages=[crew])
-
-    input_data = []
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    assert (
-        len(pipeline_results) == 0
-    ), "Pipeline should return empty results for empty input"
-
-
-@pytest.mark.asyncio
-async def test_pipeline_process_streams_single_input(mock_crew_factory):
-    """
-    Test that Pipeline.process_streams() correctly processes a single input
-    and returns the expected CrewOutput.
-    """
-    crew_name = "Test Crew"
-    mock_crew = mock_crew_factory(name="Test Crew")
-    pipeline = Pipeline(stages=[mock_crew])
-    input_data = [{"key": "value"}]
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    mock_crew.kickoff_async.assert_called_once_with(inputs={"key": "value"})
-
-    for pipeline_result in pipeline_results:
-        assert isinstance(pipeline_result, PipelineKickoffResult)
-        assert pipeline_result.raw == "Test output"
-        assert len(pipeline_result.crews_outputs) == 1
-        print("pipeline_result.token_usage", pipeline_result.token_usage)
-        assert pipeline_result.token_usage == {crew_name: DEFAULT_TOKEN_USAGE}
-        assert pipeline_result.trace == [input_data[0], "Test Crew"]
-
-
-@pytest.mark.asyncio
-async def test_pipeline_result_ordering(mock_crew_factory):
-    """
-    Ensure that results are returned in the same order as the inputs, especially with parallel processing.
-    """
-    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"output": "crew1"})
-    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"output": "crew2"})
-    crew3 = mock_crew_factory(name="Crew 3", output_json_dict={"output": "crew3"})
-
-    pipeline = Pipeline(
-        stages=[crew1, [crew2, crew3]]
-    )  # Parallel stage to test ordering
-
-    input_data = [{"id": 1}, {"id": 2}, {"id": 3}]
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    assert (
-        len(pipeline_results) == 6
-    ), "Should have 2 results for each input due to the parallel final stage"
-
-    # Group results by their original input id
-    grouped_results = {}
-    for result in pipeline_results:
-        input_id = result.trace[0]["id"]
-        if input_id not in grouped_results:
-            grouped_results[input_id] = []
-        grouped_results[input_id].append(result)
-
-    # Check that we have the correct number of groups and results per group
-    assert len(grouped_results) == 3, "Should have results for each of the 3 inputs"
-    for input_id, results in grouped_results.items():
-        assert (
-            len(results) == 2
-        ), f"Each input should have 2 results, but input {input_id} has {len(results)}"
-
-    # Check the ordering and content of the results
-    for input_id in range(1, 4):
-        group = grouped_results[input_id]
-        assert group[0].trace == [
-            {"id": input_id},
-            "Crew 1",
-            "Crew 2",
-        ], f"Unexpected trace for first result of input {input_id}"
-        assert group[1].trace == [
-            {"id": input_id},
-            "Crew 1",
-            "Crew 3",
-        ], f"Unexpected trace for second result of input {input_id}"
-        assert (
-            group[0].json_dict["output"] == "crew2"
-        ), f"Unexpected output for first result of input {input_id}"
-        assert (
-            group[1].json_dict["output"] == "crew3"
-        ), f"Unexpected output for second result of input {input_id}"
-
-
-class TestPydanticOutput(BaseModel):
-    key: str
-    value: int
-
-
-@pytest.mark.asyncio
-async def test_pipeline_process_streams_single_input_pydantic_output(mock_crew_factory):
-    crew_name = "Test Crew"
-    mock_crew = mock_crew_factory(
-        name=crew_name,
-        output_json_dict=None,
-        pydantic_output=TestPydanticOutput(key="test", value=42),
-    )
-    pipeline = Pipeline(stages=[mock_crew])
-    input_data = [{"key": "value"}]
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    assert len(pipeline_results) == 1
-    pipeline_result = pipeline_results[0]
-
-    print("pipeline_result.trace", pipeline_result.trace)
-
-    assert isinstance(pipeline_result, PipelineKickoffResult)
-    assert pipeline_result.raw == "Test output"
-    assert len(pipeline_result.crews_outputs) == 1
-    assert pipeline_result.token_usage == {crew_name: DEFAULT_TOKEN_USAGE}
-    print("INPUT DATA POST PROCESS", input_data)
-    assert pipeline_result.trace == [input_data[0], "Test Crew"]
-
-    assert isinstance(pipeline_result.pydantic, TestPydanticOutput)
-    assert pipeline_result.pydantic.key == "test"
-    assert pipeline_result.pydantic.value == 42
-    assert pipeline_result.json_dict is None
-
-
-@pytest.mark.asyncio
-async def test_pipeline_preserves_original_input(mock_crew_factory):
-    crew_name = "Test Crew"
-    mock_crew = mock_crew_factory(
-        name=crew_name,
-        output_json_dict={"new_key": "new_value"},
-    )
-    pipeline = Pipeline(stages=[mock_crew])
-
-    # Create a deep copy of the input data to ensure we're not comparing references
-    original_input_data = [{"key": "value", "nested": {"a": 1}}]
-    input_data = json.loads(json.dumps(original_input_data))
-
-    await pipeline.kickoff(input_data)
-
-    # Assert that the original input hasn't been modified
-    assert (
-        input_data == original_input_data
-    ), "The original input data should not be modified"
-
-    # Ensure that even nested structures haven't been modified
-    assert (
-        input_data[0]["nested"] == original_input_data[0]["nested"]
-    ), "Nested structures should not be modified"
-
-    # Verify that adding new keys to the crew output doesn't affect the original input
-    assert (
-        "new_key" not in input_data[0]
-    ), "New keys from crew output should not be added to the original input"
-
-
-@pytest.mark.asyncio
-async def test_pipeline_process_streams_multiple_inputs(mock_crew_factory):
-    """
-    Test that Pipeline.process_streams() correctly processes multiple inputs
-    and returns the expected CrewOutputs.
-    """
-    mock_crew = mock_crew_factory(name="Test Crew")
-    pipeline = Pipeline(stages=[mock_crew])
-    input_data = [{"key1": "value1"}, {"key2": "value2"}]
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    assert mock_crew.kickoff_async.call_count == 2
-    assert len(pipeline_results) == 2
-    for pipeline_result in pipeline_results:
-        print("pipeline_result,", pipeline_result)
-        assert all(
-            isinstance(crew_output, CrewOutput)
-            for crew_output in pipeline_result.crews_outputs
-        )
-
-
-@pytest.mark.asyncio
-async def test_pipeline_with_parallel_stages(mock_crew_factory):
-    """
-    Test that Pipeline correctly handles parallel stages.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    crew2 = mock_crew_factory(name="Crew 2")
-    crew3 = mock_crew_factory(name="Crew 3")
-
-    pipeline = Pipeline(stages=[crew1, [crew2, crew3]])
-    input_data = [{"initial": "data"}]
-
-    pipeline_result = await pipeline.kickoff(input_data)
-
-    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
-
-    assert len(pipeline_result) == 2
-    pipeline_result_1, pipeline_result_2 = pipeline_result
-
-    pipeline_result_1.trace = [
-        "Crew 1",
-        "Crew 2",
-    ]
-    pipeline_result_2.trace = [
-        "Crew 1",
-        "Crew 3",
-    ]
-
-    expected_token_usage = {
-        "Crew 1": DEFAULT_TOKEN_USAGE,
-        "Crew 2": DEFAULT_TOKEN_USAGE,
-        "Crew 3": DEFAULT_TOKEN_USAGE,
-    }
-
-    assert pipeline_result_1.token_usage == expected_token_usage
-    assert pipeline_result_2.token_usage == expected_token_usage
-
-
-@pytest.mark.asyncio
-async def test_pipeline_with_parallel_stages_end_in_single_stage(mock_crew_factory):
-    """
-    Test that Pipeline correctly handles parallel stages.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    crew2 = mock_crew_factory(name="Crew 2")
-    crew3 = mock_crew_factory(name="Crew 3")
-    crew4 = mock_crew_factory(name="Crew 4")
-
-    pipeline = Pipeline(stages=[crew1, [crew2, crew3], crew4])
-    input_data = [{"initial": "data"}]
-
-    pipeline_result = await pipeline.kickoff(input_data)
-
-    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
-
-    assert len(pipeline_result) == 1
-    pipeline_result_1 = pipeline_result[0]
-
-    pipeline_result_1.trace = [
-        input_data[0],
-        "Crew 1",
-        ["Crew 2", "Crew 3"],
-        "Crew 4",
-    ]
-
-    expected_token_usage = {
-        "Crew 1": DEFAULT_TOKEN_USAGE,
-        "Crew 2": DEFAULT_TOKEN_USAGE,
-        "Crew 3": DEFAULT_TOKEN_USAGE,
-        "Crew 4": DEFAULT_TOKEN_USAGE,
-    }
-
-    assert pipeline_result_1.token_usage == expected_token_usage
-
-
-def test_pipeline_rshift_operator(mock_crew_factory):
-    """
-    Test that the >> operator correctly creates a Pipeline from Crews and lists of Crews.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    crew2 = mock_crew_factory(name="Crew 2")
-    crew3 = mock_crew_factory(name="Crew 3")
-
-    # Test single crew addition
-    pipeline = Pipeline(stages=[]) >> crew1
-    assert len(pipeline.stages) == 1
-    assert pipeline.stages[0] == crew1
-
-    # Test adding a list of crews
-    pipeline = Pipeline(stages=[crew1])
-    pipeline = pipeline >> [crew2, crew3]
-    print("pipeline.stages:", pipeline.stages)
-    assert len(pipeline.stages) == 2
-    assert pipeline.stages[1] == [crew2, crew3]
-
-    # Test error case: trying to shift with non-Crew object
-    with pytest.raises(TypeError):
-        pipeline >> "not a crew"
-
-
-@pytest.mark.asyncio
-async def test_pipeline_parallel_crews_to_parallel_crews(mock_crew_factory):
-    """
-    Test that feeding parallel crews to parallel crews works correctly.
-    """
-    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"output1": "crew1"})
-    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"output2": "crew2"})
-    crew3 = mock_crew_factory(name="Crew 3", output_json_dict={"output3": "crew3"})
-    crew4 = mock_crew_factory(name="Crew 4", output_json_dict={"output4": "crew4"})
-
-    pipeline = Pipeline(stages=[[crew1, crew2], [crew3, crew4]])
-
-    input_data = [{"input": "test"}]
-    pipeline_results = await pipeline.kickoff(input_data)
-
-    assert len(pipeline_results) == 2, "Should have 2 results for final parallel stage"
-
-    pipeline_result_1, pipeline_result_2 = pipeline_results
-
-    # Check the outputs
-    assert pipeline_result_1.json_dict == {"output3": "crew3"}
-    assert pipeline_result_2.json_dict == {"output4": "crew4"}
-
-    # Check the traces
-    expected_traces = [
-        [{"input": "test"}, ["Crew 1", "Crew 2"], "Crew 3"],
-        [{"input": "test"}, ["Crew 1", "Crew 2"], "Crew 4"],
-    ]
-
-    for result, expected_trace in zip(pipeline_results, expected_traces):
-        assert result.trace == expected_trace, f"Unexpected trace: {result.trace}"
-
-
-def test_pipeline_double_nesting_not_allowed(mock_crew_factory):
-    """
-    Test that double nesting in pipeline stages is not allowed.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    crew2 = mock_crew_factory(name="Crew 2")
-    crew3 = mock_crew_factory(name="Crew 3")
-    crew4 = mock_crew_factory(name="Crew 4")
-
-    with pytest.raises(ValidationError) as exc_info:
-        Pipeline(stages=[crew1, [[crew2, crew3], crew4]])
-
-    error_msg = str(exc_info.value)
-    print(f"Full error message: {error_msg}")  # For debugging
-    assert (
-        "Double nesting is not allowed in pipeline stages" in error_msg
-    ), f"Unexpected error message: {error_msg}"
-
-
-def test_pipeline_invalid_crew(mock_crew_factory):
-    """
-    Test that non-Crew objects are not allowed in pipeline stages.
-    """
-    crew1 = mock_crew_factory(name="Crew 1")
-    not_a_crew = "This is not a crew"
-
-    with pytest.raises(ValidationError) as exc_info:
-        Pipeline(stages=[crew1, not_a_crew])
-
-    error_msg = str(exc_info.value)
-    print(f"Full error message: {error_msg}")  # For debugging
-    assert (
-        "Expected Crew instance or list of Crews, got <class 'str'>" in error_msg
-    ), f"Unexpected error message: {error_msg}"
-
-
-"""
-TODO: Figure out what is the proper output for a pipeline with multiple stages
-
-Options:
-- Should the final output only include the last stage's output?
-- Should the final output include the accumulation of previous stages' outputs?
-"""
-
-
-@pytest.mark.asyncio
-async def test_pipeline_data_accumulation(mock_crew_factory):
-    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"key1": "value1"})
-    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"key2": "value2"})
-
-    pipeline = Pipeline(stages=[crew1, crew2])
-    input_data = [{"initial": "data"}]
-    results = await pipeline.kickoff(input_data)
-
-    # Check that crew1 was called with only the initial input
-    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
-
-    # Check that crew2 was called with the combined input from the initial data and crew1's output
-    crew2.kickoff_async.assert_called_once_with(
-        inputs={"initial": "data", "key1": "value1"}
-    )
-
-    # Check the final output
-    assert len(results) == 1
-    final_result = results[0]
-    assert final_result.json_dict == {"key2": "value2"}
-
-    # Check that the trace includes all stages
-    assert final_result.trace == [{"initial": "data"}, "Crew 1", "Crew 2"]
-
-    # Check that crews_outputs contain the correct information
-    assert len(final_result.crews_outputs) == 2
-    assert final_result.crews_outputs[0].json_dict == {"key1": "value1"}
-    assert final_result.crews_outputs[1].json_dict == {"key2": "value2"}