Revert "Fix .md doc file 404 error on github (#564)"

This reverts commit 2bd30af72b.

.gitignore

@@ -8,4 +8,7 @@ assets/*
 test/
 docs_crew/
 chroma.sqlite3
-old_en.json
+old_en.json
+db/
+test.py
+rc-tests/*

README.md

@@ -30,7 +30,6 @@
 - [Connecting Your Crew to a Model](#connecting-your-crew-to-a-model)
 - [How CrewAI Compares](#how-crewai-compares)
 - [Contribution](#contribution)
-- [Hire CrewAI](#hire-crewai)
 - [Telemetry](#telemetry)
 - [License](#license)
 
@@ -49,7 +48,7 @@ To get started with CrewAI, follow these simple steps:
 pip install crewai
 ```
 
-If you want to also install crewai-tools, which is a package with tools that can be used by the agents, but more dependencies, you can install it with, example below uses it:
+If you want to install the 'crewai' package along with its optional features that include additional tools for agents, you can do so by using the following command: pip install 'crewai[tools]'. This command installs the basic package and also adds extra components which require more dependencies to function."
 
 ```shell
 pip install 'crewai[tools]'
@@ -83,7 +82,7 @@ researcher = Agent(
   verbose=True,
   allow_delegation=False,
   tools=[search_tool]
-  # You can pass an optional llm attribute specifying what mode you wanna use.
+  # You can pass an optional llm attribute specifying what model you wanna use.
   # It can be a local model through Ollama / LM Studio or a remote
   # model like OpenAI, Mistral, Antrophic or others (https://docs.crewai.com/how-to/LLM-Connections/)
   #
@@ -247,11 +246,6 @@ poetry build
 pip install dist/*.tar.gz
 ```
 
-## Hire CrewAI
-
-We're a company developing crewAI and crewAI Enterprise. We, for a limited time, are offering consulting with selected customers; to get them early access to our enterprise solution.
-If you are interested in having access to it, and hiring weekly hours with our team, feel free to email us at [joao@crewai.com](mailto:joao@crewai.com).
-
 ## Telemetry
 
 CrewAI uses anonymous telemetry to collect usage data with the main purpose of helping us improve the library by focusing our efforts on the most used features, integrations and tools.
@@ -259,6 +253,7 @@ CrewAI uses anonymous telemetry to collect usage data with the main purpose of h
 There is NO data being collected on the prompts, tasks descriptions agents backstories or goals nor tools usage, no API calls, nor responses nor any data that is being processed by the agents, nor any secrets and env vars.
 
 Data collected includes:
+
 - Version of crewAI
   - So we can understand how many users are using the latest version
 - Version of Python

crewAI.excalidraw

@@ -1463,11 +1463,11 @@
       "locked": false,
       "fontSize": 20,
       "fontFamily": 3,
-      "text": "Agents have the inert ability of\nreach out to another to delegate\nwork or ask questions.",
+      "text": "Agents have the innate ability of\nreach out to another to delegate\nwork or ask questions.",
       "textAlign": "right",
       "verticalAlign": "top",
       "containerId": null,
-      "originalText": "Agents have the inert ability of\nreach out to another to delegate\nwork or ask questions.",
+      "originalText": "Agents have the innate ability of\nreach out to another to delegate\nwork or ask questions.",
       "lineHeight": 1.2,
       "baseline": 68
     },
@@ -1734,4 +1734,4 @@
     "viewBackgroundColor": "#ffffff"
   },
   "files": {}
-}
+}

docs/core-concepts/Tools.md

@@ -107,7 +107,7 @@ Here is a list of the available tools and their descriptions:
 | **DirectoryReadTool**       | Facilitates reading and processing of directory structures and their contents.                |
 | **FileReadTool**            | Enables reading and extracting data from files, supporting various file formats.              |
 | **GithubSearchTool**        | A RAG tool for searching within GitHub repositories, useful for code and documentation search.|
-| **SeperDevTool**            | A specialized tool for development purposes, with specific functionalities under development. |
+| **SerperDevTool**            | A specialized tool for development purposes, with specific functionalities under development. |
 | **TXTSearchTool**           | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data.     |
 | **JSONSearchTool**          | A RAG tool designed for searching within JSON files, catering to structured data handling.     |
 | **MDXSearchTool**           | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation.      |
@@ -221,4 +221,4 @@ agent = Agent(
 ```
 
 ## Conclusion
-Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively. When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling, caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.
+Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively. When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling, caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.

docs/how-to/AgentOps-Observability.md

@@ -1,51 +1,52 @@
 ---
-title: (AgentOps) Observability using AgentOps
+title: Agent Monitoring with AgentOps
 description: Understanding and logging your agent performance with AgentOps.
 ---
 
 # Intro
-Observability is a key aspect of developing and deploying conversational AI agents. It allows developers to understand how the agent is performing, how users are interacting with the agent, and how the agent is responding to user inputs. 
+Observability is a key aspect of developing and deploying conversational AI agents. It allows developers to understand how their agents are performing, how their agents are interacting with users, and how their agents use external tools and APIs. AgentOps is a product independent of CrewAI that provides a comprehensive observability solution for agents. 
 
-AgentOps is a product, idependent of crewAI that provides a comprehensive observability solution for agents. 
-
-This notebook will provide an overview of AgentOps and how to use it with crewAI.
 
 ## AgentOps
 
-[AgentOps](https://agentops.ai) provides session replays, metrics, and monitoring for agents.
-[AgentOps Repo](https://github.com/AgentOps-AI/agentops)
+[AgentOps](https://agentops.ai/?=crew) provides session replays, metrics, and monitoring for agents.
+
+At a high level, AgentOps gives you the ability to monitor cost, token usage, latency, agent failures, session-wide statistics, and more. For more info, check out the [AgentOps Repo](https://github.com/AgentOps-AI/agentops).
 
 ### Overview
-AgentOps provides monotoring for agents in development and production. It provides a dashboard for monitoring agent performance, session replays, and custom reporting.
+AgentOps provides monitoring for agents in development and production. It provides a dashboard for tracking agent performance, session replays, and custom reporting.
 
-![agentops-overview.png](..%2Fassets%2Fagentops-overview.png)
+Additionally, AgentOps provides session drilldowns for viewing Crew agent interactions, LLM calls, and tool usage in real-time. This feature is useful for debugging and understanding how agents interact with users as well as other agents.
 
-Additionally, AgentOps provides session drilldowns that allows users to view the agent's interactions with users in real-time. This feature is useful for debugging and understanding how the agent interacts with users.
-
-![agentops-session.png](..%2Fassets%2Fagentops-session.png)
-![agentops-replay.png](..%2Fassets%2Fagentops-replay.png)
+![Overview of a select series of agent session runs](..%2Fassets%2Fagentops-overview.png)
+![Overview of session drilldowns for examining agent runs](..%2Fassets%2Fagentops-session.png)
+![Viewing a step-by-step agent replay execution graph](..%2Fassets%2Fagentops-replay.png)
 
 ### Features
-- LLM Cost management and tracking
-- Replay Analytics
-- Recursive thought detection
-- Custom Reporting
-- Analytics Dashboard
-- Public Model Testing
-- Custom Tests
-- Time Travel Debugging
-- Compliance and Security
+- **LLM Cost Management and Tracking**: Track spend with foundation model providers
+- **Replay Analytics**: Watch step-by-step agent execution graphs
+- **Recursive Thought Detection**: Identify when agents fall into infinite loops
+- **Custom Reporting**: Create custom analytics on agent performance
+- **Analytics Dashboard**: Monitor high level statistics about agents in development and production
+- **Public Model Testing**: Test your agents against benchmarks and leaderboards
+- **Custom Tests**: Run your agents against domain specific tests
+- **Time Travel Debugging**: Restart your sessions from checkpoints
+- **Compliance and Security**: Create audit logs and detect potential threats such as profanity and PII leaks
+- **Prompt Injection Detection**: Identify potential code injection and secret leaks
 
 ### Using AgentOps
 
-Create a user API key here: app.agentops.ai/account
+1. **Create an API Key:**
+Create a user API key here: [Create API Key](app.agentops.ai/account)
 
+2. **Configure Your Environment:**
 Add your API key to your environment variables
 
 ```
 AGENTOPS_API_KEY=<YOUR_AGENTOPS_API_KEY>
 ```
 
+3. **Install AgentOps:**
 Install AgentOps with:
 ```
 pip install crewai[agentops]
@@ -62,11 +63,26 @@ import agentops
 agentops.init()
 ```
 
+This will initiate an AgentOps session as well as automatically track Crew agents. For further info on how to outfit more complex agentic systems, check out the [AgentOps documentation](https://docs.agentops.ai) or join the [Discord](https://discord.gg/j4f3KbeH).
+
 ### Crew + AgentOps Examples
 - [Job Posting](https://github.com/joaomdmoura/crewAI-examples/tree/main/job-posting)
 - [Markdown Validator](https://github.com/joaomdmoura/crewAI-examples/tree/main/markdown_validator)
 - [Instagram Post](https://github.com/joaomdmoura/crewAI-examples/tree/main/instagram_post)
 
 
-### Futher Information
-To implement more features and better observability, please see the [AgentOps Repo](https://github.com/AgentOps-AI/agentops)
+### Further Information
+
+To get started, create an [AgentOps account](https://agentops.ai/?=crew).
+
+For feature requests or bug reports, please reach out to the AgentOps team on the [AgentOps Repo](https://github.com/AgentOps-AI/agentops).
+
+#### Extra links
+
+<a href="https://twitter.com/agentopsai/">🐦 Twitter</a>
+<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
+<a href="https://discord.gg/JHPt4C7r">📢 Discord</a>
+<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
+<a href="https://app.agentops.ai/?=crew">🖇️ AgentOps Dashboard</a>
+<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
+<a href="https://docs.agentops.ai/introduction">📙 Documentation</a>

docs/how-to/Installing-CrewAI.md

@@ -0,0 +1,21 @@
+---
+title: Installing crewAI
+description: A comprehensive guide to installing crewAI and its dependencies, including the latest updates and installation methods.
+---
+
+# Installing crewAI
+
+Welcome to crewAI! This guide will walk you through the installation process for crewAI and its dependencies. crewAI is a flexible and powerful AI framework that enables you to create and manage AI agents, tools, and tasks efficiently. Let's get started!
+
+## Installation
+
+To install crewAI, you need to have Python >=3.10 and <=3.13 installed on your system:
+
+```shell
+# Install the mains crewAI package
+pip install crewai
+
+# Install the main crewAI package and the tools package
+# that includes a series of helpful tools for your agents
+pip install 'crewai[tools]'
+```

docs/how-to/LLM-Connections.md

@@ -16,8 +16,8 @@ The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. He
     - `role`: Defines the agent's role within the solution.
     - `goal`: Specifies the agent's objective.
     - `backstory`: Provides a background story to the agent.
-    - `llm`: The language model that will run the agent. By default, it uses the GPT-4 model defined in the environment variable "OPENAI_MODEL_NAME".
-    - `function_calling_llm`: The language model that will handle the tool calling for this agent, overriding the crew function_calling_llm. Optional.
+    - `llm`: 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.
     - `max_iter`: Maximum number of iterations for an agent to execute a task, default is 15.
     - `memory`: Enables the agent to retain information during and a across executions. Default is `False`.
     - `max_rpm`: Maximum number of requests per minute the agent's execution should respect. Optional.
@@ -42,7 +42,7 @@ example_agent = Agent(
 ```
 
 ## 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. Note: Detailed Ollama setup is beyond this document's scope, but general guidance is provided.
+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:
@@ -52,6 +52,70 @@ OPENAI_MODEL_NAME='openhermes'  # Adjust based on available model
 OPENAI_API_KEY=''
 ```
 
+## 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. Create a ModelFile similar the one below in your project directory.
+```
+FROM llama2
+
+# Set parameters
+
+PARAMETER temperature 0.8
+PARAMETER stop Result
+
+# Sets a custom system message to specify the behavior of the chat assistant
+
+# Leaving it blank for now.
+
+SYSTEM """"""
+```
+4. Create a script to get the base model, which in our case is llama2, and create a model on top of that with ModelFile above. PS: this will be ".sh" file.     
+```
+#!/bin/zsh
+
+# variables
+model_name="llama2"
+custom_model_name="crewai-llama2"
+
+#get the base model
+ollama pull $model_name
+
+#create the model file
+ollama create $custom_model_name -f ./Llama2ModelFile
+```
+5. Go into the directory where the script file and ModelFile is located and run the script.   
+6. Enjoy your free Llama2 model that powered up by excellent agents from crewai.   
+```
+from crewai import Agent, Task, Crew
+from langchain_openai import ChatOpenAI
+import os
+os.environ["OPENAI_API_KEY"] = "NA"
+
+llm = ChatOpenAI(
+    model = "crewai-llama2",
+    base_url = "http://localhost:11434/v1")
+
+general_agent = Agent(role = "Math Professor",
+                      goal = """Provide the solution to the students that are asking mathematical questions and give them the answer.""",
+                      backstory = """You are an excellent math professor that likes to solve math questions in a way that everyone can understand your solution""",
+                      allow_delegation = False,
+                      verbose = True,
+                      llm = llm)
+task = Task (description="""what is 3 + 5""",
+             agent = general_agent)
+
+crew = Crew(
+            agents=[general_agent],
+            tasks=[task],
+            verbose=2
+        )
+
+result = crew.kickoff()
+
+print(result)
+```
+
 ## HuggingFace Integration
 There are a couple of different ways you can use HuggingFace to host your LLM.
 
@@ -97,10 +161,10 @@ 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 then 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:8000/v1"
-OPENAI_MODEL_NAME=NA
-OPENAI_API_KEY=NA
+OPENAI_API_BASE="http://localhost:1234/v1"
+OPENAI_API_KEY="lm-studio"
 ```
 
 #### Mistral API

docs/index.md

@@ -43,6 +43,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
     <div style="width:30%">
         <h2>How-To Guides</h2>
         <ul>
+            <li>
+                <a href="./how-to/Installing-CrewAI">
+                    Installing crewAI
+                </a>
+            </li>
             <li>
                 <a href="./how-to/Creating-a-Crew-and-kick-it-off">
                     Getting Started
@@ -79,8 +84,8 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                 </a>
             </li>
             <li>
-                <a href="./how-to/AgentOps-Observability.md">
-                    Agent Observability using AgentOps
+                <a href="./how-to/AgentOps-Observability">
+                    Agent Monitoring with AgentOps
                 </a>
             </li>
         </ul>

docs/tools/BrowserbaseLoadTool.md

@@ -0,0 +1,29 @@
+# BrowserbaseLoadTool
+
+## Description
+
+[Browserbase](https://browserbase.com) is a serverless platform for running headless browsers, it offers advanced debugging, session recordings, stealth mode, integrated proxies and captcha solving.
+
+## Installation
+
+- Get an API key from [browserbase.com](https://browserbase.com) and set it in environment variables (`BROWSERBASE_API_KEY`).
+- Install the [Browserbase SDK](http://github.com/browserbase/python-sdk) along with `crewai[tools]` package:
+
+```
+pip install browserbase 'crewai[tools]'
+```
+
+## Example
+
+Utilize the BrowserbaseLoadTool as follows to allow your agent to load websites:
+
+```python
+from crewai_tools import BrowserbaseLoadTool
+
+tool = BrowserbaseLoadTool()
+```
+
+## Arguments
+
+- `api_key`: Optional. Specifies Browserbase API key. Defaults is the `BROWSERBASE_API_KEY` environment variable.
+- `text_content`: Optional. Load pages as readable text. Default is `False`.

docs/tools/CodeDocsSearchTool.md

@@ -41,7 +41,7 @@ Note: Substitute 'https://docs.example.com/reference' with your target documenta
 By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
 
 ```python
-tool = YoutubeVideoSearchTool(
+tool = CodeDocsSearchTool(
     config=dict(
         llm=dict(
             provider="ollama", # or google, openai, anthropic, llama2, ...

docs/tools/GitHubSearchTool.md

@@ -22,15 +22,15 @@ from crewai_tools import GithubSearchTool
 
 # Initialize the tool for semantic searches within a specific GitHub repository
 tool = GithubSearchTool(
-    github_repo='https://github.com/example/repo',
-    content_types=['code', 'issue'] # Options: code, repo, pr, issue
+	github_repo='https://github.com/example/repo',
+	content_types=['code', 'issue'] # Options: code, repo, pr, issue
 )
 
 # OR
 
 # Initialize the tool for semantic searches within a specific GitHub repository, so the agent can search any repository if it learns about during its execution
 tool = GithubSearchTool(
-    content_types=['code', 'issue'] # Options: code, repo, pr, issue
+	content_types=['code', 'issue'] # Options: code, repo, pr, issue
 )
 ```
 

docs/tools/PGSearchTool.md

@@ -19,7 +19,7 @@ pip install 'crewai[tools]'
 Below is a proposed example showcasing how to use the PGSearchTool for conducting a semantic search on a table within a PostgreSQL database:
 
 ```python
-rom crewai_tools import PGSearchTool
+from crewai_tools import PGSearchTool
 
 # Initialize the tool with the database URI and the target table name
 tool = PGSearchTool(db_uri='postgresql://user:password@localhost:5432/mydatabase', table_name='employees')
@@ -57,4 +57,4 @@ tool = PGSearchTool(
         ),
     )
 )
-```
+```

docs/tools/XMLSearchTool.md

@@ -17,7 +17,7 @@ pip install 'crewai[tools]'
 Here are two examples demonstrating how to use the XMLSearchTool. The first example shows searching within a specific XML file, while the second example illustrates initiating a search without predefining an XML path, providing flexibility in search scope.
 
 ```python
-from crewai_tools.tools.xml_search_tool import XMLSearchTool
+from crewai_tools import XMLSearchTool
 
 # Allow agents to search within any XML file's content as it learns about their paths during execution
 tool = XMLSearchTool()

mkdocs.yml

@@ -128,6 +128,7 @@ nav:
     - Collaboration: 'core-concepts/Collaboration.md'
     - Memory: 'core-concepts/Memory.md'
   - How to Guides:
+    - Installing CrewAI: 'how-to/Installing-CrewAI.md'
     - Getting Started: 'how-to/Creating-a-Crew-and-kick-it-off.md'
     - Create Custom Tools: 'how-to/Create-Custom-Tools.md'
     - Using Sequential Process: 'how-to/Sequential.md'
@@ -135,9 +136,10 @@ nav:
     - Connecting to any LLM: 'how-to/LLM-Connections.md'
     - Customizing Agents: 'how-to/Customizing-Agents.md'
     - Human Input on Execution: 'how-to/Human-Input-on-Execution.md'
-    - Agent Observability using AgentOps: 'how-to/AgentOps-Observability.md'
+    - Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
   - Tools Docs:
     - Google Serper Search: 'tools/SerperDevTool.md'
+    - Browserbase Web Loader: 'tools/BrowserbaseLoadTool.md'
     - Scrape Website: 'tools/ScrapeWebsiteTool.md'
     - Directory Read: 'tools/DirectoryReadTool.md'
     - File Read: 'tools/FileReadTool.md'

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.28.7"
+version = "0.30.0rc6"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -23,9 +23,9 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "^0.5.2"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.1.7", optional = true }
+crewai-tools = { version = "^0.2.3", optional = true }
 click = "^8.1.7"
-python-dotenv = "1.0.0"
+python-dotenv = "^1.0.0"
 embedchain = "^0.1.98"
 appdirs = "^1.4.4"
 
@@ -44,7 +44,7 @@ mkdocs-material = {extras = ["imaging"], version = "^9.5.7"}
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.1.7"
+crewai-tools = "^0.2.3"
 
 [tool.isort]
 profile = "black"

src/crewai/agent.py

@@ -121,6 +121,15 @@ class Agent(BaseModel):
     callbacks: Optional[List[InstanceOf[BaseCallbackHandler]]] = Field(
         default=None, description="Callback to be executed"
     )
+    system_template: Optional[str] = Field(
+        default=None, description="System format for the agent."
+    )
+    prompt_template: Optional[str] = Field(
+        default=None, description="Prompt format for the agent."
+    )
+    response_template: Optional[str] = Field(
+        default=None, description="Response format for the agent."
+    )
 
     _original_role: str | None = None
     _original_goal: str | None = None
@@ -161,10 +170,16 @@ class Agent(BaseModel):
         """set agent executor is set."""
         if hasattr(self.llm, "model_name"):
             token_handler = TokenCalcHandler(self.llm.model_name, self._token_process)
-            if isinstance(self.llm.callbacks, list):
+
+            # Ensure self.llm.callbacks is a list
+            if not isinstance(self.llm.callbacks, list):
+                self.llm.callbacks = []
+
+            # Check if an instance of TokenCalcHandler already exists in the list
+            if not any(
+                isinstance(handler, TokenCalcHandler) for handler in self.llm.callbacks
+            ):
                 self.llm.callbacks.append(token_handler)
-            else:
-                self.llm.callbacks = [token_handler]
 
         if not self.agent_executor:
             if not self.cache_handler:
@@ -292,7 +307,13 @@ class Agent(BaseModel):
                 "request_within_rpm_limit"
             ] = self._rpm_controller.check_or_wait
 
-        prompt = Prompts(i18n=self.i18n, tools=tools).task_execution()
+        prompt = Prompts(
+            i18n=self.i18n,
+            tools=tools,
+            system_template=self.system_template,
+            prompt_template=self.prompt_template,
+            response_template=self.response_template,
+        ).task_execution()
 
         execution_prompt = prompt.partial(
             goal=self.goal,
@@ -300,7 +321,13 @@ class Agent(BaseModel):
             backstory=self.backstory,
         )
 
-        bind = self.llm.bind(stop=[self.i18n.slice("observation")])
+        stop_words = [self.i18n.slice("observation")]
+        if self.response_template:
+            stop_words.append(
+                self.response_template.split("{{ .Response }}")[1].strip()
+            )
+
+        bind = self.llm.bind(stop=stop_words)
         inner_agent = agent_args | execution_prompt | bind | CrewAgentParser(agent=self)
         self.agent_executor = CrewAgentExecutor(
             agent=RunnableAgent(runnable=inner_agent), **executor_args

src/crewai/agents/executor.py

@@ -40,6 +40,9 @@ class CrewAgentExecutor(AgentExecutor):
     have_forced_answer: bool = False
     force_answer_max_iterations: Optional[int] = None
     step_callback: Optional[Any] = None
+    system_template: Optional[str] = None
+    prompt_template: Optional[str] = None
+    response_template: Optional[str] = None
 
     @root_validator()
     def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
@@ -113,6 +116,7 @@ class CrewAgentExecutor(AgentExecutor):
         # Allowing human input given task setting
         if self.task.human_input:
             self.should_ask_for_human_input = True
+
         # Let's start tracking the number of iterations and time elapsed
         self.iterations = 0
         time_elapsed = 0.0
@@ -128,8 +132,10 @@ class CrewAgentExecutor(AgentExecutor):
                     intermediate_steps,
                     run_manager=run_manager,
                 )
+
                 if self.step_callback:
                     self.step_callback(next_step_output)
+
                 if isinstance(next_step_output, AgentFinish):
                     # Creating long term memory
                     create_long_term_memory = threading.Thread(
@@ -292,7 +298,6 @@ class CrewAgentExecutor(AgentExecutor):
                         tool=tool_calling.tool_name,
                         tools=", ".join([tool.name.casefold() for tool in self.tools]),
                     )
-
             yield AgentStep(action=agent_action, observation=observation)
 
     def _ask_human_input(self, final_answer: dict) -> str:

src/crewai/agents/parser.py

@@ -52,7 +52,6 @@ class CrewAgentParser(ReActSingleInputOutputParser):
             action_input = action_match.group(2)
             tool_input = action_input.strip(" ")
             tool_input = tool_input.strip('"')
-
             return AgentAction(action, tool_input, text)
 
         elif includes_answer:

src/crewai/cli/templates/README.md

@@ -40,7 +40,7 @@ poetry run {{folder_name}}
 
 This command initializes the {{name}} Crew, assembling the agents and assigning them tasks as defined in your configuration.
 
-This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folser
+This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folder.
 
 ## Understanding Your Crew
 
@@ -51,7 +51,7 @@ The {{name}} Crew is composed of multiple AI agents, each with unique roles, goa
 For support, questions, or feedback regarding the {{crew_name}} Crew or crewAI.
 - Visit our [documentation](https://docs.crewai.com)
 - Reach out to us through our [GitHub repository](https://github.com/joaomdmoura/crewai)
-- [Joing our Discord](https://discord.com/invite/X4JWnZnxPb)
-- [Chat wtih our docs](https://chatg.pt/DWjSBZn)
+- [Join our Discord](https://discord.com/invite/X4JWnZnxPb)
+- [Chat with our docs](https://chatg.pt/DWjSBZn)
 
-Let's create wonders together with the power and simplicity of crewAI.
+Let's create wonders together with the power and simplicity of crewAI.

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = {extras = ["tools"], version = "^0.27.0"}
+crewai = {extras = ["tools"], version = "^0.28.8"}
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -25,7 +25,7 @@ from crewai.process import Process
 from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
-from crewai.utilities import I18N, Logger, RPMController, FileHandler
+from crewai.utilities import I18N, FileHandler, Logger, RPMController
 
 
 class Crew(BaseModel):
@@ -36,6 +36,7 @@ class Crew(BaseModel):
         tasks: List of tasks assigned to the crew.
         agents: List of agents part of this crew.
         manager_llm: The language model that will run manager agent.
+        manager_agent: Custom agent that will be used as manager.
         memory: Whether the crew should use memory to store memories of it's execution.
         manager_callbacks: The callback handlers to be executed by the manager agent when hierarchical process is used
         cache: Whether the crew should use a cache to store the results of the tools execution.
@@ -44,6 +45,7 @@ class Crew(BaseModel):
         verbose: Indicates the verbosity level for logging during execution.
         config: Configuration settings for the crew.
         max_rpm: Maximum number of requests per minute for the crew execution to be respected.
+        prompt_file: Path to the prompt json file to be used for the crew.
         id: A unique identifier for the crew instance.
         full_output: Whether the crew should return the full output with all tasks outputs or just the final output.
         task_callback: Callback to be executed after each task for every agents execution.
@@ -86,6 +88,9 @@ class Crew(BaseModel):
     manager_llm: Optional[Any] = Field(
         description="Language model that will run the agent.", default=None
     )
+    manager_agent: Optional[Any] = Field(
+        description="Custom agent that will be used as manager.", default=None
+    )
     manager_callbacks: Optional[List[InstanceOf[BaseCallbackHandler]]] = Field(
         default=None,
         description="A list of callback handlers to be executed by the manager agent when hierarchical process is used",
@@ -108,13 +113,9 @@ class Crew(BaseModel):
         default=None,
         description="Maximum number of requests per minute for the crew execution to be respected.",
     )
-    language: str = Field(
-        default="en",
-        description="Language used for the crew, defaults to English.",
-    )
-    language_file: str = Field(
+    prompt_file: str = Field(
         default=None,
-        description="Path to the language file to be used for the crew.",
+        description="Path to the prompt json file to be used for the crew.",
     )
     output_log_file: Optional[Union[bool, str]] = Field(
         default=False,
@@ -170,12 +171,23 @@ class Crew(BaseModel):
     @model_validator(mode="after")
     def check_manager_llm(self):
         """Validates that the language model is set when using hierarchical process."""
-        if self.process == Process.hierarchical and not self.manager_llm:
-            raise PydanticCustomError(
-                "missing_manager_llm",
-                "Attribute `manager_llm` is required when using hierarchical process.",
-                {},
-            )
+        if self.process == Process.hierarchical:
+            if not self.manager_llm and not self.manager_agent:
+                raise PydanticCustomError(
+                    "missing_manager_llm_or_manager_agent",
+                    "Attribute `manager_llm` or `manager_agent` is required when using hierarchical process.",
+                    {},
+                )
+
+            if (self.manager_agent is not None) and (
+                self.agents.count(self.manager_agent) > 0
+            ):
+                raise PydanticCustomError(
+                    "manager_agent_in_agents",
+                    "Manager agent should not be included in agents list.",
+                    {},
+                )
+
         return self
 
     @model_validator(mode="after")
@@ -233,7 +245,7 @@ class Crew(BaseModel):
         self._interpolate_inputs(inputs)
         self._set_tasks_callbacks()
 
-        i18n = I18N(language=self.language, language_file=self.language_file)
+        i18n = I18N(prompt_file=self.prompt_file)
 
         for agent in self.agents:
             agent.i18n = i18n
@@ -306,15 +318,22 @@ class Crew(BaseModel):
     def _run_hierarchical_process(self) -> str:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
 
-        i18n = I18N(language=self.language, language_file=self.language_file)
-        manager = Agent(
-            role=i18n.retrieve("hierarchical_manager_agent", "role"),
-            goal=i18n.retrieve("hierarchical_manager_agent", "goal"),
-            backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
-            tools=AgentTools(agents=self.agents).tools(),
-            llm=self.manager_llm,
-            verbose=True,
-        )
+        i18n = I18N(prompt_file=self.prompt_file)
+        if self.manager_agent is not None:
+            self.manager_agent.allow_delegation = True
+            manager = self.manager_agent
+            if len(manager.tools) > 0:
+                raise Exception("Manager agent should not have tools")
+            manager.tools = AgentTools(agents=self.agents).tools()
+        else:
+            manager = Agent(
+                role=i18n.retrieve("hierarchical_manager_agent", "role"),
+                goal=i18n.retrieve("hierarchical_manager_agent", "goal"),
+                backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
+                tools=AgentTools(agents=self.agents).tools(),
+                llm=self.manager_llm,
+                verbose=True,
+            )
 
         task_output = ""
         for task in self.tasks:
@@ -343,7 +362,8 @@ class Crew(BaseModel):
     def _set_tasks_callbacks(self) -> str:
         """Sets callback for every task suing task_callback"""
         for task in self.tasks:
-            task.callback = self.task_callback
+            if not task.callback:
+                task.callback = self.task_callback
 
     def _interpolate_inputs(self, inputs: Dict[str, Any]) -> str:
         """Interpolates the inputs in the tasks and agents."""

src/crewai/memory/long_term/long_term_memory.py

@@ -28,5 +28,5 @@ class LongTermMemory(Memory):
             datetime=item.datetime,
         )
 
-    def search(self, task: str, latest_n: int) -> Dict[str, Any]:
+    def search(self, task: str, latest_n: int = 3) -> Dict[str, Any]:
         return self.storage.load(task, latest_n)

src/crewai/project/annotations.py

@@ -1,14 +1,28 @@
 tasks_order = []
 
 
+def memoize(func):
+    cache = {}
+
+    def memoized_func(*args, **kwargs):
+        key = (args, tuple(kwargs.items()))
+        if key not in cache:
+            cache[key] = func(*args, **kwargs)
+        return cache[key]
+
+    return memoized_func
+
+
 def task(func):
     func.is_task = True
     tasks_order.append(func.__name__)
+    func = memoize(func)
     return func
 
 
 def agent(func):
     func.is_agent = True
+    func = memoize(func)
     return func
 
 

src/crewai/task.py

@@ -1,6 +1,8 @@
+import re
 import threading
 import uuid
 from typing import Any, Dict, List, Optional, Type
+import os
 
 from langchain_openai import ChatOpenAI
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
@@ -245,7 +247,16 @@ class Task(BaseModel):
                     return exported_result.model_dump()
                 return exported_result
             except Exception:
-                pass
+              # sometimes the response contains valid JSON in the middle of text
+              match = re.search(r"({.*})", result, re.DOTALL)
+              if match:
+                  try:
+                      exported_result = model.model_validate_json(match.group(0))
+                      if self.output_json:
+                          return exported_result.model_dump()
+                      return exported_result
+                  except Exception:
+                      pass
 
             llm = self.agent.function_calling_llm or self.agent.llm
 
@@ -281,6 +292,11 @@ class Task(BaseModel):
         return isinstance(llm, ChatOpenAI) and llm.openai_api_base == None
 
     def _save_file(self, result: Any) -> None:
+        directory = os.path.dirname(self.output_file)
+
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+
         with open(self.output_file, "w") as file:
             file.write(result)
         return None

src/crewai/telemetry/telemetry.py

@@ -88,7 +88,9 @@ class Telemetry:
                 self._add_attribute(span, "python_version", platform.python_version())
                 self._add_attribute(span, "crew_id", str(crew.id))
                 self._add_attribute(span, "crew_process", crew.process)
-                self._add_attribute(span, "crew_language", crew.language)
+                self._add_attribute(
+                    span, "crew_language", crew.prompt_file if crew.i18n else "None"
+                )
                 self._add_attribute(span, "crew_memory", crew.memory)
                 self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
                 self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
@@ -103,7 +105,7 @@ class Telemetry:
                                 "verbose?": agent.verbose,
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
-                                "i18n": agent.i18n.language,
+                                "i18n": agent.i18n.prompt_file,
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
@@ -232,7 +234,7 @@ class Telemetry:
                                 "verbose?": agent.verbose,
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
-                                "i18n": agent.i18n.language,
+                                "i18n": agent.i18n.prompt_file,
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [

src/crewai/tools/agent_tools.py

@@ -34,11 +34,11 @@ class AgentTools(BaseModel):
         return tools
 
     def delegate_work(self, coworker: str, task: str, context: str):
-        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
+        """Useful to delegate a specific task to a co-worker passing all necessary context and names."""
         return self._execute(coworker, task, context)
 
     def ask_question(self, coworker: str, question: str, context: str):
-        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
+        """Useful to ask a question, opinion or take from a co-worker passing all necessary context and names."""
         return self._execute(coworker, question, context)
 
     def _execute(self, agent, task, context):
@@ -67,6 +67,6 @@ class AgentTools(BaseModel):
         task = Task(
             description=task,
             agent=agent,
-            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
+            expected_output="Your best answer to your co-worker asking you this, accounting for the context shared.",
         )
         return agent.execute_task(task, context)

src/crewai/tools/tool_usage.py

@@ -1,4 +1,5 @@
 import ast
+from difflib import SequenceMatcher
 from textwrap import dedent
 from typing import Any, List, Union
 
@@ -26,13 +27,13 @@ class ToolUsage:
     Class that represents the usage of a tool by an agent.
 
     Attributes:
-        task: Task being executed.
-        tools_handler: Tools handler that will manage the tool usage.
-        tools: List of tools available for the agent.
-        original_tools: Original tools available for the agent before being converted to BaseTool.
-        tools_description: Description of the tools available for the agent.
-        tools_names: Names of the tools available for the agent.
-        function_calling_llm: Language model to be used for the tool usage.
+      task: Task being executed.
+      tools_handler: Tools handler that will manage the tool usage.
+      tools: List of tools available for the agent.
+      original_tools: Original tools available for the agent before being converted to BaseTool.
+      tools_description: Description of the tools available for the agent.
+      tools_names: Names of the tools available for the agent.
+      function_calling_llm: Language model to be used for the tool usage.
     """
 
     def __init__(
@@ -215,12 +216,18 @@ class ToolUsage:
 
     def _select_tool(self, tool_name: str) -> BaseTool:
         for tool in self.tools:
-            if tool.name.lower().strip() == tool_name.lower().strip():
+            if (
+                tool.name.lower().strip() == tool_name.lower().strip()
+                or SequenceMatcher(
+                    None, tool.name.lower().strip(), tool_name.lower().strip()
+                ).ratio()
+                > 0.9
+            ):
                 return tool
         self.task.increment_tools_errors()
         if tool_name and tool_name != "":
             raise Exception(
-                f"Action '{tool_name}' don't exist, these are the only available Actions: {self.tools_description}"
+                f"Action '{tool_name}' don't exist, these are the only available Actions:\n {self.tools_description}"
             )
         else:
             raise Exception(
@@ -260,17 +267,17 @@ class ToolUsage:
                     else ToolCalling
                 )
                 converter = Converter(
-                    text=f"Only tools available:\n###\n{self._render()}\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid ouput schema:\n\n{tool_string}```",
+                    text=f"Only tools available:\n###\n{self._render()}\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid output schema:\n\n{tool_string}```",
                     llm=self.function_calling_llm,
                     model=model,
                     instructions=dedent(
                         """\
-                            The schema should have the following structure, only two keys:
-                            - tool_name: str
-                            - arguments: dict (with all arguments being passed)
+              The schema should have the following structure, only two keys:
+              - tool_name: str
+              - arguments: dict (with all arguments being passed)
 
-                            Example:
-                            {"tool_name": "tool name", "arguments": {"arg_name1": "value", "arg_name2": 2}}""",
+              Example:
+              {"tool_name": "tool name", "arguments": {"arg_name1": "value", "arg_name2": 2}}""",
                     ),
                     max_attemps=1,
                 )
@@ -282,7 +289,8 @@ class ToolUsage:
                 tool_name = self.action.tool
                 tool = self._select_tool(tool_name)
                 try:
-                    arguments = ast.literal_eval(self.action.tool_input)
+                    tool_input = self._validate_tool_input(self.action.tool_input)
+                    arguments = ast.literal_eval(tool_input)
                 except Exception:
                     return ToolUsageErrorException(
                         f'{self._i18n.errors("tool_arguments_error")}'
@@ -308,3 +316,54 @@ class ToolUsage:
             return self._tool_calling(tool_string)
 
         return calling
+
+    def _validate_tool_input(self, tool_input: str) -> str:
+        try:
+            ast.literal_eval(tool_input)
+            return tool_input
+        except Exception:
+            # Clean and ensure the string is properly enclosed in braces
+            tool_input = tool_input.strip()
+            if not tool_input.startswith("{"):
+                tool_input = "{" + tool_input
+            if not tool_input.endswith("}"):
+                tool_input += "}"
+
+            # Manually split the input into key-value pairs
+            entries = tool_input.strip("{} ").split(",")
+            formatted_entries = []
+
+            for entry in entries:
+                if ":" not in entry:
+                    continue  # Skip malformed entries
+                key, value = entry.split(":", 1)
+
+                # Remove extraneous white spaces and quotes, replace single quotes
+                key = key.strip().strip('"').replace("'", '"')
+                value = value.strip()
+
+                # Handle replacement of single quotes at the start and end of the value string
+                if value.startswith("'") and value.endswith("'"):
+                    value = value[1:-1]  # Remove single quotes
+                    value = (
+                        '"' + value.replace('"', '\\"') + '"'
+                    )  # Re-encapsulate with double quotes
+                elif value.isdigit():  # Check if value is a digit, hence integer
+                    formatted_value = value
+                elif value.lower() in [
+                    "true",
+                    "false",
+                    "null",
+                ]:  # Check for boolean and null values
+                    formatted_value = value.lower()
+                else:
+                    # Assume the value is a string and needs quotes
+                    formatted_value = '"' + value.replace('"', '\\"') + '"'
+
+                # Rebuild the entry with proper quoting
+                formatted_entry = f'"{key}": {formatted_value}'
+                formatted_entries.append(formatted_entry)
+
+            # Reconstruct the JSON string
+            new_json_string = "{" + ", ".join(formatted_entries) + "}"
+            return new_json_string

src/crewai/translations/en.json

@@ -6,12 +6,12 @@
   },
   "slices": {
     "observation": "\nObservation",
-    "task": "\nCurrent Task: {input}\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: ",
+    "task": "\nCurrent Task: {input}\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:",
     "memory": "\n\n# Useful context: \n{memory}",
     "role_playing": "You are {role}. {backstory}\nYour personal goal is: {goal}",
-    "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple a python dictionary using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n",
+    "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple a python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n",
     "no_tools": "To 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!",
-    "format": "I MUST either use a tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n ",
+    "format": "I MUST either use a tool (use one at time) OR give my best final answer. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n ",
     "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfy the expect criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
     "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n",
     "task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
@@ -20,7 +20,6 @@
     "getting_input": "This is the agent final answer: {final_answer}\nPlease provide a feedback: "
   },
   "errors": {
-    "unexpected_format": "\nSorry, I didn't use the expected format, I MUST either use a tool (use one at time) OR give my best final answer.\n",
     "force_final_answer": "Tool won't be use because it's time to give your final answer. Don't use tools and just your absolute BEST Final answer.",
     "agent_tool_unexsiting_coworker": "\nError executing tool. Co-worker mentioned not found, it must to be one of the following options:\n{coworkers}\n",
     "task_repeated_usage": "I tried reusing the same input, I must stop using this action input. I'll try something else instead.\n\n",
@@ -30,7 +29,7 @@
     "tool_usage_exception": "I encountered an error while trying to use the tool. This was the error: {error}.\n Tool {tool} accepts these inputs: {tool_inputs}"
   },
   "tools": {
-    "delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to exectue the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
-    "ask_question": "Ask a specific question to one of the following co-workers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
+    "delegate_work": "Delegate a specific task to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, the task you want them to do, and ALL necessary context to exectue the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
+    "ask_question": "Ask a specific question to one of the following co-workers: {coworkers}\nThe input to this tool should be the co-worker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them."
   }
 }

src/crewai/utilities/i18n.py

@@ -2,44 +2,36 @@ import json
 import os
 from typing import Dict, Optional
 
-from pydantic import BaseModel, Field, PrivateAttr, ValidationError, model_validator
+from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
 
 class I18N(BaseModel):
-    _translations: Dict[str, Dict[str, str]] = PrivateAttr()
-    language_file: Optional[str] = Field(
+    _prompts: Dict[str, Dict[str, str]] = PrivateAttr()
+    prompt_file: Optional[str] = Field(
         default=None,
-        description="Path to the translation file to load",
-    )
-    language: Optional[str] = Field(
-        default="en",
-        description="Language used to load translations",
+        description="Path to the prompt_file file to load",
     )
 
     @model_validator(mode="after")
-    def load_translation(self) -> "I18N":
-        """Load translations from a JSON file based on the specified language."""
+    def load_prompts(self) -> "I18N":
+        """Load prompts from a JSON file."""
         try:
-            if self.language_file:
-                with open(self.language_file, "r") as f:
-                    self._translations = json.load(f)
+            if self.prompt_file:
+                with open(self.prompt_file, "r") as f:
+                    self._prompts = json.load(f)
             else:
                 dir_path = os.path.dirname(os.path.realpath(__file__))
-                prompts_path = os.path.join(
-                    dir_path, f"../translations/{self.language}.json"
-                )
+                prompts_path = os.path.join(dir_path, f"../translations/en.json")
 
                 with open(prompts_path, "r") as f:
-                    self._translations = json.load(f)
+                    self._prompts = json.load(f)
         except FileNotFoundError:
-            raise ValidationError(
-                f"Translation file for language '{self.language}' not found."
-            )
+            raise Exception(f"Prompt file '{self.prompt_file}' not found.")
         except json.JSONDecodeError:
-            raise ValidationError(f"Error decoding JSON from the prompts file.")
+            raise Exception(f"Error decoding JSON from the prompts file.")
 
-        if not self._translations:
-            self._translations = {}
+        if not self._prompts:
+            self._prompts = {}
 
         return self
 
@@ -54,6 +46,6 @@ class I18N(BaseModel):
 
     def retrieve(self, kind, key) -> str:
         try:
-            return self._translations[kind][key]
+            return self._prompts[kind][key]
         except:
-            raise ValidationError(f"Translation for '{kind}':'{key}'  not found.")
+            raise Exception(f"Prompt for '{kind}':'{key}'  not found.")

src/crewai/utilities/paths.py

@@ -1,3 +1,4 @@
+import os
 from pathlib import Path
 
 import appdirs
@@ -13,6 +14,11 @@ def db_storage_path():
 
 
 def get_project_directory_name():
-    cwd = Path.cwd()
-    project_directory_name = cwd.name
-    return project_directory_name
+    project_directory_name = os.environ.get("CREWAI_STORAGE_DIR")
+
+    if project_directory_name:
+        return project_directory_name
+    else:
+        cwd = Path.cwd()
+        project_directory_name = cwd.name
+        return project_directory_name

src/crewai/utilities/prompts.py

@@ -1,4 +1,4 @@
-from typing import Any, ClassVar
+from typing import Any, ClassVar, Optional
 
 from langchain.prompts import BasePromptTemplate, PromptTemplate
 from pydantic import BaseModel, Field
@@ -7,16 +7,15 @@ from crewai.utilities import I18N
 
 
 class Prompts(BaseModel):
-    """Manages and generates prompts for a generic agent with support for different languages."""
+    """Manages and generates prompts for a generic agent."""
 
     i18n: I18N = Field(default=I18N())
     tools: list[Any] = Field(default=[])
+    system_template: Optional[str] = None
+    prompt_template: Optional[str] = None
+    response_template: Optional[str] = None
     SCRATCHPAD_SLICE: ClassVar[str] = "\n{agent_scratchpad}"
 
-    def task_execution_without_tools(self) -> BasePromptTemplate:
-        """Generate a prompt for task execution without tools components."""
-        return self._build_prompt(["role_playing", "task"])
-
     def task_execution(self) -> BasePromptTemplate:
         """Generate a standard prompt for task execution."""
         slices = ["role_playing"]
@@ -24,12 +23,42 @@ class Prompts(BaseModel):
             slices.append("tools")
         else:
             slices.append("no_tools")
-        slices.append("task")
-        return self._build_prompt(slices)
 
-    def _build_prompt(self, components: list[str]) -> BasePromptTemplate:
+        slices.append("task")
+
+        if not self.system_template and not self.prompt_template:
+            return self._build_prompt(slices)
+        else:
+            return self._build_prompt(
+                slices,
+                self.system_template,
+                self.prompt_template,
+                self.response_template,
+            )
+
+    def _build_prompt(
+        self,
+        components: list[str],
+        system_template=None,
+        prompt_template=None,
+        response_template=None,
+    ) -> BasePromptTemplate:
         """Constructs a prompt string from specified components."""
-        prompt_parts = [self.i18n.slice(component) for component in components]
-        prompt_parts.append(self.SCRATCHPAD_SLICE)
-        prompt = PromptTemplate.from_template("".join(prompt_parts))
+        if not system_template and not prompt_template:
+            prompt_parts = [self.i18n.slice(component) for component in components]
+            prompt_parts.append(self.SCRATCHPAD_SLICE)
+            prompt = PromptTemplate.from_template("".join(prompt_parts))
+        else:
+            prompt_parts = [
+                self.i18n.slice(component)
+                for component in components
+                if component != "task"
+            ]
+            system = system_template.replace("{{ .System }}", "".join(prompt_parts))
+            prompt = prompt_template.replace(
+                "{{ .Prompt }}",
+                "".join([self.i18n.slice("task"), self.SCRATCHPAD_SLICE]),
+            )
+            response = response_template.split("{{ .Response }}")[0]
+            prompt = PromptTemplate.from_template(f"{system}\n{prompt}\n{response}")
         return prompt

tests/agent_test.py

@@ -754,6 +754,7 @@ def test_agent_definition_based_on_dict():
     assert agent.verbose == True
     assert agent.tools == []
 
+
 # test for human input
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_human_input():
@@ -780,6 +781,7 @@ def test_agent_human_input():
         mock_human_input.assert_called_once()
         assert output == "Hello"
 
+
 def test_interpolate_inputs():
     agent = Agent(
         role="{topic} specialist",
@@ -797,3 +799,46 @@ def test_interpolate_inputs():
     assert agent.goal == "Figure stuff out"
     assert agent.backstory == "I am the master of nothing"
 
+
+def test_system_and_prompt_template():
+    agent = Agent(
+        role="{topic} specialist",
+        goal="Figure {goal} out",
+        backstory="I am the master of {role}",
+        system_template="""<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>""",
+        prompt_template="""<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>""",
+        response_template="""<|start_header_id|>assistant<|end_header_id|>
+
+{{ .Response }}<|eot_id|>""",
+    )
+
+    template = agent.agent_executor.agent.dict()["runnable"]["middle"][0]["template"]
+    assert (
+        template
+        == """<|start_header_id|>system<|end_header_id|>
+
+You are {role}. {backstory}
+Your personal goal is: {goal}To give my best complete final answer to the task use the exact following format:
+
+Thought: I now can give a great answer
+Final Answer: my best complete final answer to the task.
+Your final answer must be the great and the most complete as possible, it must be outcome described.
+
+I MUST use these formats, my job depends on it!<|eot_id|>
+<|start_header_id|>user<|end_header_id|>
+
+
+Current Task: {input}
+
+Begin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!
+
+Thought:
+{agent_scratchpad}<|eot_id|>
+<|start_header_id|>assistant<|end_header_id|>
+
+"""
+    )

tests/cassettes/test_crew_function_calling_llm.yaml

@@ -324,7 +324,7 @@ interactions:
       Name: learn_about_ai\nTool Description: learn_about_AI(topic) -> float - Useful
       for when you need to learn about AI to write an paragraph about it.\nTool Arguments:
       {''topic'': {}}\n\nReturn a valid schema for the tool, the tool name must be
-      exactly equal one of the options, use this text to inform the valid ouput schema:\n\nThought:
+      exactly equal one of the options, use this text to inform the valid output schema:\n\nThought:
       Before I can write an amazing article about AI, I need to understand the basics
       of AI, its applications, and ethical considerations to ensure that the content
       is well-rounded and informative.\n\nAction: learn_about_AI\nAction Input: {\"topic\":
@@ -854,7 +854,7 @@ interactions:
       Name: learn_about_ai\nTool Description: learn_about_AI(topic) -> float - Useful
       for when you need to learn about AI to write an paragraph about it.\nTool Arguments:
       {''topic'': {}}\n\nReturn a valid schema for the tool, the tool name must be
-      exactly equal one of the options, use this text to inform the valid ouput schema:\n\nThought:
+      exactly equal one of the options, use this text to inform the valid output schema:\n\nThought:
       Now that I know AI is a broad field, I should learn specifically about its applications
       to provide concrete examples in my article.\n\nAction: learn_about_AI\nAction
       Input: {\"topic\": \"applications of AI\"}```"}, {"role": "system", "content":
@@ -1325,7 +1325,7 @@ interactions:
       Name: learn_about_ai\nTool Description: learn_about_AI(topic) -> float - Useful
       for when you need to learn about AI to write an paragraph about it.\nTool Arguments:
       {''topic'': {}}\n\nReturn a valid schema for the tool, the tool name must be
-      exactly equal one of the options, use this text to inform the valid ouput schema:\n\nThought:
+      exactly equal one of the options, use this text to inform the valid output schema:\n\nThought:
       It seems there was an error with the action input. I need to correct the format
       to ensure the tool works properly for gathering information on the applications
       of AI.\n\nAction: learn_about_AI\nAction Input: {\"topic\": \"applications of
@@ -1807,7 +1807,7 @@ interactions:
       Name: learn_about_ai\nTool Description: learn_about_AI(topic) -> float - Useful
       for when you need to learn about AI to write an paragraph about it.\nTool Arguments:
       {''topic'': {}}\n\nReturn a valid schema for the tool, the tool name must be
-      exactly equal one of the options, use this text to inform the valid ouput schema:\n\nThought:
+      exactly equal one of the options, use this text to inform the valid output schema:\n\nThought:
       Having understood that AI is a broad field, and after the corrected attempt
       to learn about its applications, I realize I need more detailed insights into
       ethical considerations around AI to make sure the article covers a balanced

tests/crew_test.py

@@ -648,10 +648,10 @@ def test_agent_usage_metrics_are_captured_for_sequential_process():
     result = crew.kickoff()
     assert result == "Howdy!"
     assert crew.usage_metrics == {
-        "completion_tokens": 51,
-        "prompt_tokens": 483,
-        "successful_requests": 3,
-        "total_tokens": 534,
+        "completion_tokens": 17,
+        "prompt_tokens": 160,
+        "successful_requests": 1,
+        "total_tokens": 177,
     }
 
 
@@ -678,10 +678,10 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     result = crew.kickoff()
     assert result == '"Howdy!"'
     assert crew.usage_metrics == {
-        "total_tokens": 2592,
-        "prompt_tokens": 2048,
-        "completion_tokens": 544,
-        "successful_requests": 6,
+        "total_tokens": 1650,
+        "prompt_tokens": 1367,
+        "completion_tokens": 283,
+        "successful_requests": 3,
     }
 
 
@@ -912,3 +912,82 @@ def test_crew_log_file_output(tmp_path):
     crew = Crew(agents=[researcher], tasks=tasks, output_log_file=str(test_file))
     crew.kickoff()
     assert test_file.exists()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_manager_agent():
+    from unittest.mock import patch
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    manager = Agent(
+        role="Manager",
+        goal="Manage the crew and ensure the tasks are completed efficiently.",
+        backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
+        allow_delegation=False,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.hierarchical,
+        manager_agent=manager,
+        tasks=[task],
+    )
+
+    with patch.object(Task, "execute") as execute:
+        crew.kickoff()
+        assert manager.allow_delegation == True
+        execute.assert_called()
+
+
+def test_manager_agent_in_agents_raises_exception():
+    pass
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    manager = Agent(
+        role="Manager",
+        goal="Manage the crew and ensure the tasks are completed efficiently.",
+        backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
+        allow_delegation=False,
+    )
+
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError):
+        crew = Crew(
+            agents=[researcher, writer, manager],
+            process=Process.hierarchical,
+            manager_agent=manager,
+            tasks=[task],
+        )
+
+
+def test_manager_agent_with_tools_raises_exception():
+    pass
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    manager = Agent(
+        role="Manager",
+        goal="Manage the crew and ensure the tasks are completed efficiently.",
+        backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
+        allow_delegation=False,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.hierarchical,
+        manager_agent=manager,
+        tasks=[task],
+    )
+
+    with pytest.raises(Exception):
+        crew.kickoff()

tests/memory/long_term_memory_test.py

@@ -20,7 +20,7 @@ def test_save_and_search(long_term_memory):
         metadata={"task": "test_task", "quality": 0.5},
     )
     long_term_memory.save(memory)
-    find = long_term_memory.search("test_task")[0]
+    find = long_term_memory.search("test_task", latest_n=5)[0]
     assert find["score"] == 0.5
     assert find["datetime"] == "test_datetime"
     assert find["metadata"]["agent"] == "test_agent"

tests/project_test.py

@@ -0,0 +1,35 @@
+from crewai.agent import Agent
+from crewai.project import agent, task
+from crewai.task import Task
+
+
+class SimpleCrew:
+    @agent
+    def simple_agent(self):
+        return Agent(
+            role="Simple Agent", goal="Simple Goal", backstory="Simple Backstory"
+        )
+
+    @task
+    def simple_task(self):
+        return Task(description="Simple Description", expected_output="Simple Output")
+
+
+def test_agent_memoization():
+    crew = SimpleCrew()
+    first_call_result = crew.simple_agent()
+    second_call_result = crew.simple_agent()
+
+    assert (
+        first_call_result is second_call_result
+    ), "Agent memoization is not working as expected"
+
+
+def test_task_memoization():
+    crew = SimpleCrew()
+    first_call_result = crew.simple_task()
+    second_call_result = crew.simple_task()
+
+    assert (
+        first_call_result is second_call_result
+    ), "Task memoization is not working as expected"

tests/utilities/prompts.json

@@ -0,0 +1,40 @@
+{
+  "hierarchical_manager_agent": {
+    "role": "Lorem ipsum dolor sit amet",
+    "goal": "Lorem ipsum dolor sit amet",
+    "backstory": "Lorem ipsum dolor sit amet."
+  },
+  "planning_manager_agent": {
+    "role": "Lorem ipsum dolor sit amet",
+    "goal": "Lorem ipsum dolor sit amet",
+    "backstory": "Lorem ipsum dolor sit amet."
+  },
+  "slices": {
+    "observation": "Lorem ipsum dolor sit amet",
+    "task": "Lorem ipsum dolor sit amet",
+    "memory": "Lorem ipsum dolor sit amet",
+    "role_playing": "Lorem ipsum dolor sit amet",
+    "tools": "Lorem ipsum dolor sit amet",
+    "no_tools": "Lorem ipsum dolor sit amet",
+    "format": "Lorem ipsum dolor sit amet",
+    "final_answer_format": "Lorem ipsum dolor sit amet",
+    "format_without_tools": "Lorem ipsum dolor sit amet",
+    "task_with_context": "Lorem ipsum dolor sit amet",
+    "expected_output": "Lorem ipsum dolor sit amet",
+    "human_feedback": "Lorem ipsum dolor sit amet",
+    "getting_input": "Lorem ipsum dolor sit amet "
+  },
+  "errors": {
+    "force_final_answer": "Lorem ipsum dolor sit amet",
+    "agent_tool_unexsiting_coworker": "Lorem ipsum dolor sit amet",
+    "task_repeated_usage": "Lorem ipsum dolor sit amet",
+    "tool_usage_error": "Lorem ipsum dolor sit amet",
+    "tool_arguments_error": "Lorem ipsum dolor sit amet",
+    "wrong_tool_name": "Lorem ipsum dolor sit amet",
+    "tool_usage_exception": "Lorem ipsum dolor sit amet"
+  },
+  "tools": {
+    "delegate_work": "Lorem ipsum dolor sit amet",
+    "ask_question": "Lorem ipsum dolor sit amet"
+  }
+}

tests/utilities/test_i18n.py

@@ -3,38 +3,42 @@ import pytest
 from crewai.utilities.i18n import I18N
 
 
-def test_load_translation():
-    i18n = I18N(language="en")
-    i18n.load_translation()
-    assert i18n._translations is not None
+def test_load_prompts():
+    i18n = I18N()
+    i18n.load_prompts()
+    assert i18n._prompts is not None
 
 
 def test_slice():
-    i18n = I18N(language="en")
-    i18n.load_translation()
+    i18n = I18N()
+    i18n.load_prompts()
     assert isinstance(i18n.slice("role_playing"), str)
 
 
-def test_errors():
-    i18n = I18N(language="en")
-    i18n.load_translation()
-    assert isinstance(i18n.errors("unexpected_format"), str)
-
-
 def test_tools():
-    i18n = I18N(language="en")
-    i18n.load_translation()
+    i18n = I18N()
+    i18n.load_prompts()
     assert isinstance(i18n.tools("ask_question"), str)
 
 
 def test_retrieve():
-    i18n = I18N(language="en")
-    i18n.load_translation()
+    i18n = I18N()
+    i18n.load_prompts()
     assert isinstance(i18n.retrieve("slices", "role_playing"), str)
 
 
 def test_retrieve_not_found():
-    i18n = I18N(language="en")
-    i18n.load_translation()
+    i18n = I18N()
+    i18n.load_prompts()
     with pytest.raises(Exception):
         i18n.retrieve("nonexistent_kind", "nonexistent_key")
+
+
+def test_prompt_file():
+    import os
+
+    path = os.path.join(os.path.dirname(__file__), "prompts.json")
+    i18n = I18N(prompt_file=path)
+    i18n.load_prompts()
+    assert isinstance(i18n.retrieve("slices", "role_playing"), str)
+    assert i18n.retrieve("slices", "role_playing") == "Lorem ipsum dolor sit amet"