docs: add flow plot visualization example to documentation (#2668 )

Co-Authored-By: Joe Moura <joao@crewai.com>
docs: update docs.json with contextual options, SEO, and 404 redirect (#2654 )
2026-04-18 17:02:35 +00:00 · 2025-04-22 19:07:38 +00:00 · 2025-04-22 09:52:27 -07:00 · 2025-04-22 13:09:30 -03:00 · 2025-04-21 19:18:21 -04:00 · 2025-04-18 18:33:04 -07:00
24 changed files with 990 additions and 205 deletions
--- a/docs/changelog.mdx
+++ b/docs/changelog.mdx
@@ -4,6 +4,36 @@ description: View the latest updates and changes to CrewAI
 icon: timeline
 ---

+<Update label="2025-04-07" description="v0.114.0">
+  ## Release Highlights
+  <Frame>
+    <img src="/images/v01140.png" />
+  </Frame>
+
+  **New Features & Enhancements**
+  - Agents as an atomic unit. (`Agent(...).kickoff()`)
+  - Support for [Custom LLM implementations](https://docs.crewai.com/guides/advanced/custom-llm).
+  - Integrated External Memory and [Opik observability](https://docs.crewai.com/how-to/opik-observability).
+  - Enhanced YAML extraction.
+  - Multimodal agent validation.
+  - Added Secure fingerprints for agents and crews.
+
+  **Core Improvements & Fixes**
+  - Improved serialization, agent copying, and Python compatibility.
+  - Added wildcard support to `emit()`
+  - Added support for additional router calls and context window adjustments.
+  - Fixed typing issues, validation, and import statements.
+  - Improved method performance.
+  - Enhanced agent task handling, event emissions, and memory management.
+  - Fixed CLI issues, conditional tasks, cloning behavior, and tool outputs.
+
+  **Documentation & Guides**
+  - Improved documentation structure, theme, and organization.
+  - Added guides for Local NVIDIA NIM with WSL2, W&B Weave, and Arize Phoenix.
+  - Updated tool configuration examples, prompts, and observability docs.
+  - Guide on using singular agents within Flows.
+</Update>
+
 <Update label="2025-03-17" description="v0.108.0">
  **Features**
  - Converted tabs to spaces in `crew.py` template
--- a/docs/concepts/flows.mdx
+++ b/docs/concepts/flows.mdx
@@ -790,6 +790,9 @@ Visualizing your AI workflows can provide valuable insights into the structure a

 Plots in CrewAI are graphical representations of your AI workflows. They display the various tasks, their connections, and the flow of data between them. This visualization helps in understanding the sequence of operations, identifying bottlenecks, and ensuring that the workflow logic aligns with your expectations.

+![Example of a Flow Plot](/images/flow_plot_example.png)
+*An example visualization of a simple flow with start method, sequential steps, and directional execution.*
+
 ### How to Generate a Plot

 CrewAI provides two convenient methods to generate plots of your flows:
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -42,6 +42,16 @@ CrewAI supports various types of knowledge sources out of the box:
 | `collection_name`          | **str**                              | No       | Name of the collection where the knowledge will be stored. Used to identify different sets of knowledge. Defaults to "knowledge" if not provided.     |
 | `storage`                  | **Optional[KnowledgeStorage]**       | No       | Custom storage configuration for managing how the knowledge is stored and retrieved. If not provided, a default storage will be created.              |

+
+<Tip>
+Unlike retrieval from a vector database using a tool, agents preloaded with knowledge will not need a retrieval persona or task.
+Simply add the relevant knowledge sources your agent or crew needs to function.
+
+Knowledge sources can be added at the agent or crew level.
+Crew level knowledge sources will be used by **all agents** in the crew.
+Agent level knowledge sources will be used by the **specific agent** that is preloaded with the knowledge.
+</Tip>
+
 ## Quickstart Example

 <Tip>
@@ -146,6 +156,26 @@ result = crew.kickoff(
 )
 ```

+## Knowledge Configuration
+
+You can configure the knowledge configuration for the crew or agent.
+
+```python Code
+from crewai.knowledge.knowledge_config import KnowledgeConfig
+
+knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)
+
+agent = Agent(
+    ...
+    knowledge_config=knowledge_config
+)
+```
+
+<Tip>
+  `results_limit`: is the number of relevant documents to return. Default is 3.
+  `score_threshold`: is the minimum score for a document to be considered relevant. Default is 0.35.
+</Tip>
+
 ## More Examples

 Here are examples of how to use different types of knowledge sources:
--- a/docs/concepts/llamaindex-tools.mdx
+++ b/docs/concepts/llamaindex-tools.mdx
@@ -1,71 +0,0 @@
---
-title: Using LlamaIndex Tools
-description: Learn how to integrate LlamaIndex tools with CrewAI agents to enhance search-based queries and more.
-icon: toolbox
---
-
-## Using LlamaIndex Tools
-
-<Info>
-    CrewAI seamlessly integrates with LlamaIndex’s comprehensive toolkit for RAG (Retrieval-Augmented Generation) and agentic pipelines, enabling advanced search-based queries and more. 
-</Info>
-
-Here are the available built-in tools offered by LlamaIndex.
-
-```python Code
-from crewai import Agent
-from crewai_tools import LlamaIndexTool
-
-# Example 1: Initialize from FunctionTool
-from llama_index.core.tools import FunctionTool
-
-your_python_function = lambda ...: ...
-og_tool = FunctionTool.from_defaults(
-    your_python_function, 
-    name="<name>", 
-    description='<description>'
-)
-tool = LlamaIndexTool.from_tool(og_tool)
-
-# Example 2: Initialize from LlamaHub Tools
-from llama_index.tools.wolfram_alpha import WolframAlphaToolSpec
-wolfram_spec = WolframAlphaToolSpec(app_id="<app_id>")
-wolfram_tools = wolfram_spec.to_tool_list()
-tools = [LlamaIndexTool.from_tool(t) for t in wolfram_tools]
-
-# Example 3: Initialize Tool from a LlamaIndex Query Engine
-query_engine = index.as_query_engine()
-query_tool = LlamaIndexTool.from_query_engine(
-    query_engine,
-    name="Uber 2019 10K Query Tool",
-    description="Use this tool to lookup the 2019 Uber 10K Annual Report"
-)
-
-# Create and assign the tools to an agent
-agent = Agent(
-    role='Research Analyst',
-    goal='Provide up-to-date market analysis',
-    backstory='An expert analyst with a keen eye for market trends.',
-    tools=[tool, *tools, query_tool]
-)
-
-# rest of the code ...
-```
-
-## Steps to Get Started
-
-To effectively use the LlamaIndexTool, follow these steps:
-
-<Steps>
-    <Step title="Package Installation">
-    Make sure that `crewai[tools]` package is installed in your Python environment:
-    <CodeGroup>
-        ```shell Terminal
-        pip install 'crewai[tools]'
-        ```
-    </CodeGroup>
-    </Step>
-    <Step title="Install and Use LlamaIndex">
-    Follow the LlamaIndex documentation [LlamaIndex Documentation](https://docs.llamaindex.ai/) to set up a RAG/agent pipeline.
-    </Step>
-</Steps>
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -8,25 +8,27 @@
    "dark": "#C94C3C"
  },
  "favicon": "favicon.svg",
+  "contextual": {
+    "options": ["copy", "view", "chatgpt", "claude"]
+  },
  "navigation": {
    "tabs": [
      {
-        "tab": "Get Started",
+        "tab": "Documentation",
        "groups": [
          {
            "group": "Get Started",
            "pages": [
              "introduction",
              "installation",
-              "quickstart",
-              "changelog"
+              "quickstart"
            ]
          },
          {
            "group": "Guides",
            "pages": [
              {
-                "group": "Concepts",
+                "group": "Strategy",
                "pages": [
                  "guides/concepts/evaluating-use-cases"
                ]
@@ -79,41 +81,6 @@
              "concepts/event-listener"
            ]
          },
-          {
-            "group": "How to Guides",
-            "pages": [
-              "how-to/create-custom-tools",
-              "how-to/sequential-process",
-              "how-to/hierarchical-process",
-              "how-to/custom-manager-agent",
-              "how-to/llm-connections",
-              "how-to/customizing-agents",
-              "how-to/multimodal-agents",
-              "how-to/coding-agents",
-              "how-to/force-tool-output-as-result",
-              "how-to/human-input-on-execution",
-              "how-to/kickoff-async",
-              "how-to/kickoff-for-each",
-              "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks",
-              "how-to/langchain-tools",
-              "how-to/llamaindex-tools"
-            ]
-          },
-          {
-            "group": "Agent Monitoring & Observability",
-            "pages": [
-              "how-to/agentops-observability",
-              "how-to/arize-phoenix-observability",
-              "how-to/langfuse-observability",
-              "how-to/langtrace-observability",
-              "how-to/mlflow-observability",
-              "how-to/openlit-observability",
-              "how-to/opik-observability",
-              "how-to/portkey-observability",
-              "how-to/weave-integration"
-            ]
-          },
          {
            "group": "Tools",
            "pages": [
@@ -141,6 +108,7 @@
              "tools/hyperbrowserloadtool",
              "tools/linkupsearchtool",
              "tools/llamaindextool",
+              "tools/langchaintool",
              "tools/serperdevtool",
              "tools/s3readertool",
              "tools/s3writertool",
@@ -170,6 +138,40 @@
              "tools/youtubevideosearchtool"
            ]
          },
+          {
+            "group": "Agent Monitoring & Observability",
+            "pages": [
+              "how-to/agentops-observability",
+              "how-to/arize-phoenix-observability",
+              "how-to/langfuse-observability",
+              "how-to/langtrace-observability",
+              "how-to/mlflow-observability",
+              "how-to/openlit-observability",
+              "how-to/opik-observability",
+              "how-to/portkey-observability",
+              "how-to/weave-integration"
+            ]
+          },
+          {
+            "group": "Learn",
+            "pages": [
+              "how-to/conditional-tasks",
+              "how-to/coding-agents",
+              "how-to/create-custom-tools",
+              "how-to/custom-llm",
+              "how-to/custom-manager-agent",
+              "how-to/customizing-agents",
+              "how-to/force-tool-output-as-result",
+              "how-to/hierarchical-process",
+              "how-to/human-input-on-execution",
+              "how-to/kickoff-async",
+              "how-to/kickoff-for-each",
+              "how-to/llm-connections",
+              "how-to/multimodal-agents",
+              "how-to/replay-tasks-from-latest-crew-kickoff",
+              "how-to/sequential-process"
+            ]
+          },
          {
            "group": "Telemetry",
            "pages": [
@@ -188,19 +190,35 @@
            ]
          }
        ]
+      },
+      {
+        "tab": "Releases",
+        "groups": [
+          {
+            "group": "Releases",
+            "pages": [
+              "changelog"
+            ]
+          }
+        ]
      }
    ],
    "global": {
      "anchors": [
        {
-          "anchor": "Community",
+          "anchor": "Website",
+          "href": "https://crewai.com",
+          "icon": "globe"
+        },
+        {
+          "anchor": "Forum",
          "href": "https://community.crewai.com",
          "icon": "discourse"
        },
        {
-          "anchor": "Tutorials",
-          "href": "https://www.youtube.com/@crewAIInc",
-          "icon": "youtube"
+          "anchor": "Get Help",
+          "href": "mailto:support@crewai.com",
+          "icon": "headset"
        }
      ]
    }
@@ -214,6 +232,12 @@
    "strict": false
  },
  "navbar": {
+    "links": [
+      {
+        "label": "Start Free Trial",
+        "href": "https://app.crewai.com"
+      }
+    ],
    "primary": {
      "type": "github",
      "href": "https://github.com/crewAIInc/crewAI"
@@ -223,7 +247,12 @@
    "prompt": "Search CrewAI docs"
  },
  "seo": {
-    "indexing": "navigable"
+    "indexing": "all"
+  },
+  "errors": {
+    "404": {
+      "redirect": true
+    }
  },
  "footer": {
    "socials": {
--- a/docs/how-to/custom-llm.mdx
+++ b/docs/how-to/custom-llm.mdx
@@ -1,9 +1,13 @@
-# Custom LLM Implementations
+---
+title: Custom LLM Implementation
+description: Learn how to create custom LLM implementations in CrewAI.
+icon: code
+---
+
+## Custom LLM Implementations

 CrewAI now supports custom LLM implementations through the `BaseLLM` abstract base class. This allows you to create your own LLM implementations that don't rely on litellm's authentication mechanism.

-## Using Custom LLM Implementations
-
 To create a custom LLM implementation, you need to:

 1. Inherit from the `BaseLLM` abstract base class
--- a/docs/how-to/custom-manager-agent.mdx
+++ b/docs/how-to/custom-manager-agent.mdx
@@ -1,5 +1,5 @@
 ---
-title: Create Your Own Manager Agent
+title: Custom Manager Agent
 description: Learn how to set a custom agent as the manager in CrewAI, providing more control over task management and coordination.
 icon: user-shield
 ---
--- a/docs/how-to/replay-tasks-from-latest-crew-kickoff.mdx
+++ b/docs/how-to/replay-tasks-from-latest-crew-kickoff.mdx
@@ -20,10 +20,8 @@ Here's an example of how to replay from a task:
 To use the replay feature, follow these steps:

 <Steps>
-   <Step title="Open your terminal or command prompt.">
-   </Step>
-   <Step title="Navigate to the directory where your CrewAI project is located.">
-   </Step>
+   <Step title="Open your terminal or command prompt."></Step>
+   <Step title="Navigate to the directory where your CrewAI project is located."></Step>
   <Step title="Run the following commands:">
      To view the latest kickoff task_ids use:

--- a/docs/images/flow_plot_example.png
+++ b/docs/images/flow_plot_example.png
--- a/docs/images/v01140.png
+++ b/docs/images/v01140.png
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -336,9 +336,22 @@ email_summarizer_task:
      - research_task
 ```

-## Deploying Your Project
+## Deploying Your Crew

-The easiest way to deploy your crew is through [CrewAI Enterprise](http://app.crewai.com), where you can deploy your crew in a few clicks.
+The easiest way to deploy your crew to production is through [CrewAI Enterprise](http://app.crewai.com).
+
+Watch this video tutorial for a step-by-step demonstration of deploying your crew to [CrewAI Enterprise](http://app.crewai.com) using the CLI.
+
+<iframe
+  width="100%"
+  height="400"
+  src="https://www.youtube.com/embed/3EqSV-CYDZA"
+  title="CrewAI Deployment Guide"
+  frameborder="0"
+  style={{ borderRadius: '10px' }}
+  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+  allowfullscreen
+></iframe>

 <CardGroup cols={2}>
  <Card
--- a/docs/concepts/langchain-tools.mdx
+++ b/docs/concepts/langchain-tools.mdx
@@ -1,10 +1,10 @@
 ---
-title: Using LangChain Tools
-description: Learn how to integrate LangChain tools with CrewAI agents to enhance search-based queries and more.
+title: LangChain Tool
+description: The `LangChainTool` is a wrapper for LangChain tools and query engines.
 icon: link
 ---

-## Using LangChain Tools
+## `LangChainTool`

 <Info>
    CrewAI seamlessly integrates with LangChain's comprehensive [list of tools](https://python.langchain.com/docs/integrations/tools/), all of which can be used with CrewAI.
--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -114,6 +114,14 @@ class Agent(BaseAgent):
        default=None,
        description="Embedder configuration for the agent.",
    )
+    agent_knowledge_context: Optional[str] = Field(
+        default=None,
+        description="Knowledge context for the agent.",
+    )
+    crew_knowledge_context: Optional[str] = Field(
+        default=None,
+        description="Knowledge context for the crew.",
+    )

    @model_validator(mode="after")
    def post_init_setup(self):
@@ -234,22 +242,30 @@ class Agent(BaseAgent):
            memory = contextual_memory.build_context_for_task(task, context)
            if memory.strip() != "":
                task_prompt += self.i18n.slice("memory").format(memory=memory)
-
+        knowledge_config = (
+            self.knowledge_config.model_dump() if self.knowledge_config else {}
+        )
        if self.knowledge:
-            agent_knowledge_snippets = self.knowledge.query([task.prompt()])
+            agent_knowledge_snippets = self.knowledge.query(
+                [task.prompt()], **knowledge_config
+            )
            if agent_knowledge_snippets:
-                agent_knowledge_context = extract_knowledge_context(
+                self.agent_knowledge_context = extract_knowledge_context(
                    agent_knowledge_snippets
                )
-                if agent_knowledge_context:
-                    task_prompt += agent_knowledge_context
+                if self.agent_knowledge_context:
+                    task_prompt += self.agent_knowledge_context

        if self.crew:
-            knowledge_snippets = self.crew.query_knowledge([task.prompt()])
+            knowledge_snippets = self.crew.query_knowledge(
+                [task.prompt()], **knowledge_config
+            )
            if knowledge_snippets:
-                crew_knowledge_context = extract_knowledge_context(knowledge_snippets)
-                if crew_knowledge_context:
-                    task_prompt += crew_knowledge_context
+                self.crew_knowledge_context = extract_knowledge_context(
+                    knowledge_snippets
+                )
+                if self.crew_knowledge_context:
+                    task_prompt += self.crew_knowledge_context

        tools = tools or self.tools or []
        self.create_agent_executor(tools=tools, task=task)
--- a/src/crewai/agents/agent_builder/base_agent.py
+++ b/src/crewai/agents/agent_builder/base_agent.py
@@ -19,6 +19,7 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.security.security_config import SecurityConfig
 from crewai.tools.base_tool import BaseTool, Tool
@@ -155,6 +156,10 @@ class BaseAgent(ABC, BaseModel):
    adapted_agent: bool = Field(
        default=False, description="Whether the agent is adapted"
    )
+    knowledge_config: Optional[KnowledgeConfig] = Field(
+        default=None,
+        description="Knowledge configuration for the agent such as limits and threshold",
+    )

    @model_validator(mode="before")
    @classmethod
--- a/src/crewai/cli/tools/main.py
+++ b/src/crewai/cli/tools/main.py
@@ -117,7 +117,9 @@ class ToolCommand(BaseCommand, PlusAPIMixin):

        published_handle = publish_response.json()["handle"]
        console.print(
-            f"Successfully published {published_handle} ({project_version}).\nInstall it in other projects with crewai tool install {published_handle}",
+            f"Successfully published `{published_handle}` ({project_version}).\n\n"
+            + "⚠️ Security checks are running in the background. Your tool will be available once these are complete.\n"
+            + f"You can monitor the status or access your tool here:\nhttps://app.crewai.com/crewai_plus/tools/{published_handle}",
            style="bold green",
        )

@@ -153,8 +155,12 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        login_response_json = login_response.json()

        settings = Settings()
-        settings.tool_repository_username = login_response_json["credential"]["username"]
-        settings.tool_repository_password = login_response_json["credential"]["password"]
+        settings.tool_repository_username = login_response_json["credential"][
+            "username"
+        ]
+        settings.tool_repository_password = login_response_json["credential"][
+            "password"
+        ]
        settings.dump()

        console.print(
@@ -179,7 +185,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
            capture_output=False,
            env=self._build_env_with_credentials(repository_handle),
            text=True,
-            check=True
+            check=True,
        )

        if add_package_result.stderr:
@@ -204,7 +210,11 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        settings = Settings()

        env = os.environ.copy()
-        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(settings.tool_repository_username or "")
-        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(settings.tool_repository_password or "")
+        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(
+            settings.tool_repository_username or ""
+        )
+        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(
+            settings.tool_repository_password or ""
+        )

        return env
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -304,9 +304,7 @@ class Crew(BaseModel):
        """Initialize private memory attributes."""
        self._external_memory = (
            # External memory doesn’t support a default value since it was designed to be managed entirely externally
-            self.external_memory.set_crew(self)
-            if self.external_memory
-            else None
+            self.external_memory.set_crew(self) if self.external_memory else None
        )

        self._long_term_memory = self.long_term_memory
@@ -1136,9 +1134,13 @@ class Crew(BaseModel):
        result = self._execute_tasks(self.tasks, start_index, True)
        return result

-    def query_knowledge(self, query: List[str]) -> Union[List[Dict[str, Any]], None]:
+    def query_knowledge(
+        self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
+    ) -> Union[List[Dict[str, Any]], None]:
        if self.knowledge:
-            return self.knowledge.query(query)
+            return self.knowledge.query(
+                query, results_limit=results_limit, score_threshold=score_threshold
+            )
        return None

    def fetch_inputs(self) -> Set[str]:
@@ -1220,9 +1222,13 @@ class Crew(BaseModel):
        copied_data = self.model_dump(exclude=exclude)
        copied_data = {k: v for k, v in copied_data.items() if v is not None}
        if self.short_term_memory:
-            copied_data["short_term_memory"] = self.short_term_memory.model_copy(deep=True)
+            copied_data["short_term_memory"] = self.short_term_memory.model_copy(
+                deep=True
+            )
        if self.long_term_memory:
-            copied_data["long_term_memory"] = self.long_term_memory.model_copy(deep=True)
+            copied_data["long_term_memory"] = self.long_term_memory.model_copy(
+                deep=True
+            )
        if self.entity_memory:
            copied_data["entity_memory"] = self.entity_memory.model_copy(deep=True)
        if self.external_memory:
@@ -1230,7 +1236,6 @@ class Crew(BaseModel):
        if self.user_memory:
            copied_data["user_memory"] = self.user_memory.model_copy(deep=True)

-
        copied_data.pop("agents", None)
        copied_data.pop("tasks", None)

@@ -1403,7 +1408,10 @@ class Crew(BaseModel):
            "short": (getattr(self, "_short_term_memory", None), "short term"),
            "entity": (getattr(self, "_entity_memory", None), "entity"),
            "knowledge": (getattr(self, "knowledge", None), "knowledge"),
-            "kickoff_outputs": (getattr(self, "_task_output_handler", None), "task output"),
+            "kickoff_outputs": (
+                getattr(self, "_task_output_handler", None),
+                "task output",
+            ),
            "external": (getattr(self, "_external_memory", None), "external"),
        }

--- a/src/crewai/knowledge/knowledge.py
+++ b/src/crewai/knowledge/knowledge.py
@@ -43,7 +43,9 @@ class Knowledge(BaseModel):
        self.storage.initialize_knowledge_storage()
        self._add_sources()

-    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
+    def query(
+        self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
+    ) -> List[Dict[str, Any]]:
        """
        Query across all knowledge sources to find the most relevant information.
        Returns the top_k most relevant chunks.
@@ -56,7 +58,8 @@ class Knowledge(BaseModel):

        results = self.storage.search(
            query,
-            limit,
+            limit=results_limit,
+            score_threshold=score_threshold,
        )
        return results

--- a/src/crewai/knowledge/knowledge_config.py
+++ b/src/crewai/knowledge/knowledge_config.py
@@ -0,0 +1,16 @@
+from pydantic import BaseModel, Field
+
+
+class KnowledgeConfig(BaseModel):
+    """Configuration for knowledge retrieval.
+
+    Args:
+        results_limit (int): The number of relevant documents to return.
+        score_threshold (float): The minimum score for a document to be considered relevant.
+    """
+
+    results_limit: int = Field(default=3, description="The number of results to return")
+    score_threshold: float = Field(
+        default=0.35,
+        description="The minimum score for a result to be considered relevant",
+    )
--- a/src/crewai/knowledge/storage/knowledge_storage.py
+++ b/src/crewai/knowledge/storage/knowledge_storage.py
@@ -4,7 +4,7 @@ import io
 import logging
 import os
 import shutil
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Optional, Union

 import chromadb
 import chromadb.errors
--- a/src/crewai/utilities/events/third_party/agentops_listener.py
+++ b/src/crewai/utilities/events/third_party/agentops_listener.py
@@ -1,4 +1,3 @@
-import os
 from typing import Optional

 from crewai.utilities.events import (
@@ -26,7 +25,7 @@ class AgentOpsListener(BaseEventListener):
        super().__init__()

    def setup_listeners(self, crewai_event_bus):
-        if not AGENTOPS_INSTALLED or not os.getenv("AGENTOPS_API_KEY"):
+        if not AGENTOPS_INSTALLED:
            return

        @crewai_event_bus.on(CrewKickoffStartedEvent)
--- a/tests/agent_test.py
+++ b/tests/agent_test.py
@@ -10,6 +10,8 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import AgentFinish, CrewAgentExecutor
 from crewai.agents.parser import CrewAgentParser, OutputParserException
+from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
@@ -259,7 +261,9 @@ def test_cache_hitting():
    def handle_tool_end(source, event):
        received_events.append(event)

-    with (patch.object(CacheHandler, "read") as read,):
+    with (
+        patch.object(CacheHandler, "read") as read,
+    ):
        read.return_value = "0"
        task = Task(
            description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -1611,6 +1615,78 @@ def test_agent_with_knowledge_sources():
        assert "red" in result.raw.lower()


+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            agent = Agent(
+                role="Information Agent",
+                goal="Provide information based on knowledge sources",
+                backstory="You have access to specific knowledge sources.",
+                llm=LLM(model="gpt-4o-mini"),
+                knowledge_sources=[string_source],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default():
+    content = "Brandon's favorite color is red and he likes Mexican food."
+    string_source = StringKnowledgeSource(content=content)
+    knowledge_config = KnowledgeConfig()
+    with patch(
+        "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
+    ) as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{"content": content}]
+        with patch.object(Knowledge, "query") as mock_knowledge_query:
+            string_source = StringKnowledgeSource(content=content)
+            knowledge_config = KnowledgeConfig()
+            agent = Agent(
+                role="Information Agent",
+                goal="Provide information based on knowledge sources",
+                backstory="You have access to specific knowledge sources.",
+                llm=LLM(model="gpt-4o-mini"),
+                knowledge_sources=[string_source],
+                knowledge_config=knowledge_config,
+            )
+            task = Task(
+                description="What is Brandon's favorite color?",
+                expected_output="Brandon's favorite color.",
+                agent=agent,
+            )
+            crew = Crew(agents=[agent], tasks=[task])
+            crew.kickoff()
+
+            assert agent.knowledge is not None
+            mock_knowledge_query.assert_called_once_with(
+                [task.prompt()],
+                **knowledge_config.model_dump(),
+            )
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_with_knowledge_sources_extensive_role():
    content = "Brandon's favorite color is red and he likes Mexican food."
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml
@@ -0,0 +1,330 @@
+interactions:
+- request:
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '137'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fcf607c16eb34-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=CncSMPCav.9EJL3emmM0sTqugx5GN6_Oy8JPFBssVho-1744933673-1.0.1.1-Q1XMvHbQdrfEWkkCYeeNHwFdZ1NpjAGJ_0jOUYIk_APelFe7nCanjW_xlOj12b3JQql9.iWQDiHvCeYJDTWkdxnNiMQOEiFMYHX5YZXUuJs;
+        path=/; expires=Fri, 18-Apr-25 00:17:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=unfPTYCpF5COtm5PuZDuaJqlhefP0iibfjsXHc9lKq0-1744933673515-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '75'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-8687b6cbdb-4qpmr
+      x-envoy-upstream-service-time:
+      - '46'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999986'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b8c884a7fe2bd4732903ecbdc632576d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou 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:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jJNNi9swEIbv+RWDLr0ki/NBvm5NYUsplFK29NAuZiKNnWlkjVaSk02X
+        /PdiJxtn2y30YrCeecfvvCM/9QAUG7UEpTeYdOXtYPXp7vbLw7evm4ePmObvt/jrsVgVn9/5dbhj
+        1W8Usv5JOj2rbrRU3lJicSesA2GiputwNpksxuPpbNyCSgzZRlb6NJjIoGLHg1E2mgyy2WA4P6s3
+        wpqiWsL3HgDAU/tsfDpDj2oJWf/5pKIYsSS1vBQBqCC2OVEYI8eELql+B7W4RK61/gGc7EGjg5J3
+        BAhlYxvQxT0FgB/ulh1aeNu+L2EV0BlxbyIUuJPAiUCLlQAcwUkCX68ta3sAI7quyCUywA72bMge
+        AHfIFteWYOtkb8mUBFHqoCneXPsLVNQRm4xcbe0VQOckYZNxm8z9mRwvWVgpfZB1/EOqCnYcN3kg
+        jOKauWMSr1p67AHct5nXL2JUPkjlU55kS+3nhtP5qZ/qVt3R0fQMkyS0V6rFpP9Kv9xQQrbxamtK
+        o96Q6aTdirE2LFegdzX1325e632anF35P+07oDX5RCb3gQzrlxN3ZYGaP+FfZZeUW8MqUtixpjwx
+        hWYThgqs7el+qniIiaq8YFdS8IFPl7TweTZejOajUbbIVO/Y+w0AAP//AwA4a1/QsgMAAA==
+    headers:
+      CF-RAY:
+      - 931fcf649bdbed40-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:54 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=8vySwO0xqpm0u93_1_rXQwTeEIWa2ei3_CD5sAdoo3o-1744933674-1.0.1.1-iqZDpH5poOUp4Rcnhfrb0N2Z0c2662RBiPEcx_gefNW.m3tBA3qyFa8tmFv7PitH8u9vyYK7jxUwy4lPiSi830QWNbTMgCMTbrJ7iaUV7hY;
+        path=/; expires=Fri, 18-Apr-25 00:17:54 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=IXAyT8eWpFERM53ngcYNmaqhocfGbOHWSoe7SFNdoGI-1744933674288-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '489'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999801'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_151f9d0b786f2022f249ee20ea108b43
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
+++ b/tests/cassettes/test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml
@@ -0,0 +1,330 @@
+interactions:
+- request:
+    body: '{"input": ["Brandon''s favorite color is red and he likes Mexican food."],
+      "model": "text-embedding-3-small", "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '137'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+yPtfmz59Pced/yrwR2bV9zhAQ2UkRFHEymYAiOxHZtEDfvN99ovdkNicm
+        YiNpu1bXdf1W//Nff/7802V1fp/++feff17VOP3z377PHumU/vPvP//9X3/+/Pnzn7/P/29k3mb5
+        41G9i9/w34/V+5Ev//z7D/9/nvzfQf/+889JZZQeb+UOCJHjaQqtRQfv1mXUaf0OTfTuHjx+CvAU
+        CWC/KEik3pNeZScAwr5Zzkgne4Gqd6jX2+oDW3BxGx8nMkfrxaq0GM2PNaV5G6QZM0P1joRJl32W
+        BVuXtTPPo02jZhRX8gjWdj7MgDz2D+wRexhoUHsaTN9P0RfLw5itFrmbCgzCHVFOdx/wQte1qJvK
+        FxH556YeT0pqoJ0RTNhqPwiskhTe0T7qIpzrwS4arGS24D4uc6y90d4VpMq+wy7hntS8mG297p2B
+        QNrwZ5pV1p4RZ6vPEHEPDtuWVA0L/w451CylgPUZBhFvXaQWWqXwwKobdNmavrcCyvDk4aRDezby
+        2c5Hym33obtXgLKlioYGKUfZovrOBtkSu6cOQbHw6POcJoyE+vmMxtegUst+HNh2ZImhpFTNsJ4V
+        73p1XlWO8NsSscGvH7asThqCqtoe6anKt+6SsI0K91Ef0UtGS5dIB8DD3QV2vtwaybB8lksCj5K7
+        pTjWccSrU5igG+hfVOuSRl+4sPGhtJ4Qtfr4w4g0EQcaRfCgnrKxXVFD8hnSZ6jTk5PN9ax4JxU5
+        T/5MsnTwskU6ARNOHnCJYHpsoPbgFfDzsRYaLe9dPbfLoiDTls800h+6vjruXYDSGiGs3fJFXw5Z
+        2APLfh+ok3y2YDvrfQvLm3/x5fPervlV0QUUF5c33aFAzQRua0JwHeCKb5/FGITQVzsgc1KIg6vA
+        Mmo+Xg5CiY/80LSf2UqSFwdOKDHoMVyBvk6jq0DzTRTs1uUHLFui9ciAyYGq8fHOhDqzzoCpgkE9
+        Ta/q9aW/VnRO/IR6zaVjs8DvQ9Q/byvOji+YzUV7ztGHji4+b4t7LZqHuwO9+NRR9aZ0YFFWKQF8
+        oXu+5D2rgfee2RlmG3/CO+mFXbq0SgJ35cGm+JxKjEnnY6vsjlOI9+aSsPUqdSNMj3FBD3qdMHHA
+        UgCXpjj46xaeI6GBnAZtrfZJOLMKLKg6VrDCz5jaF6K6/LjWGpwt36FHS430JTwlHtrvYIL3q03d
+        JUkWDWVaEtKLvglq9sj4HiRDHtFo3yjuyGe2D/nPY8ER4xwmtq/AQtvoptF7rdiAX9jdgRtn7+Bn
+        tJEZJc2GgD4yNZz3YBjWu3ziAaFrhXenYwImk8wNpOrj/M13t+Y7wz/D3/57Lz0b2K1kHixsVceP
+        ztUy8VYyH90e/AbvXU+sGZ8aDnKhc6LWu9nVPJp3CYqztfBbYCn6DDf9CG16+VBf9VswK6seI7h7
+        nqirt5POrDOr4LC/ExoMssgmx6EzlCfv+s2fnS5e3vIM9VeX0YDfaUxs04EHhXb/4KPzJoC1ac2j
+        jeltac5xgc5gd++B3PYI22Bmw1g9KgFZx+cdGynQMv7ilz7yDuFKkP351LMfTiYsJQCpLhIpWguN
+        76FsiVd6cLRJX4LU5qEFOUQdt3OBGCfJHX7PD/x7H+9L1xThHJQYF+HiUrWYe6DvogzvTlKvM6OP
+        EijuT5i01wcF7Pg6QvgK4pZ6vlzo82dzCmBAD4zuU7MfFvypHbRLREZku91ma5+PBfjGjz8e7mbN
+        sFByKDkcInrs5Iv+oVDhoTppJTYI17LVHD4qvBBo4NB9lmyRDuYMt0bqkQWbJZteYsaBUpZNvFf7
+        Su+cVQ5gr6YI+7u3A0Sev83KJowLXyzuwGV7N5jR68Zc6iWPoB71O63gwiqEtU9sR3wq2yG0nPZE
+        ja7fuKuzmQ10PnUctriPysROHCtogQ3D+JPs3O1a1AGULo+SauHJ0XlpX8ZI350yeqCtmjFn4T0w
+        SHyDz/xqg+2xnU3UZWJP7VURXHaDlgBHg8P00NhvfTy2rgqPRM1pvKIjmPwodNDU8neq2ydTZ2O7
+        C1F5qFKKX8PFHRZvXGFV81eaBMou4wcOjzLwbk/qpxe1/uyMoEAmCc4Yl4GQrZzstsgq+Qe9D4cZ
+        LFkbJCg6NjG9Wy8pWzj/3cBY7VSaymuf0eK2jnBXmRE+bZkJlqdp+NAf6gFbh9saPQ/d7Q6siTtg
+        HG1ubDtLnA8/1fuK/TpfXVbO7gijGR7pQ3e2EVPA2qJ170v+FosWWEPf6iBRgI6dku7Z0ianM2Jl
+        scWq4R/Z9qkd2l98YU3isD7z7UuBtw4V9Hbef+pZu2wEEE/3DCdFdXDF6j7NMOmftg99uXDFME1T
+        MCX6SA/OvAGTcm4tlJ1uFoHzsdQZvxHu8BQ+eurtkiXrcuobMLzW2Tf+TCZka+8or+FpYqypDhBU
+        5eahY3a54ftLBzULDTuF0f3t4X2N7+4QGrsUifHG8We0fdXzbCoOQHjzJlwbKFk/umYDMQsqmunt
+        0RUDj2ko+/QP6ofSW19xoDVQUHHuw289YJf3MiM+vwQ+f5Xf9Xw3OwIT3eNwcu59sDruWUBjOQ/f
+        /FPd+V0FDZKlWPrG71Nf1UJvYOyh2R+rUxQxL88D0KnUoeq8sfTV3+cBME6Pid5uPnDXZBOk6Fyf
+        ZRxe02wQd6LdweOknzHu4zYj42WV0P5QddSbjzv3qydMEMutia3sHgOmk0CDnZ5gjO1HEwm9kUsg
+        7R47cu6j7bBWwVlDfsy9sNHXls5jXV+R6sYt3hdSyJZQdAo4dvGeWtHJGeYUpzEUkpzhg3UT6l5c
+        +hVAw4rxJeUfmejpQYAe7+6CdUM4ZGPt2wW4RvRBTtK2rCdD9yE8lUGK3fdJjNa++ljoKDsbsnkN
+        F53pZyeF72U806h3OnfVpwqiOx8+fbEH2F1lv65QNhUrPp6FYGChsUuQ44QG+XyWpu72qOHhmi4W
+        tqSLrI8lfOXwu/4EWcF+WPwK3OHNF2y8++UP90gq6LuCgdXyqkXisl5N+DS3D38cDjOb2LrpQYap
+        R+1XvGckOz8lKB7gGVtNyA9MLeYO1uSe/I1/sm/kM4Q0FPAh4LfR3JwXH+7ulYbNfa6yZdqPBZyK
+        k0b4Q5zrM4hUAscBB/7mUXRgtsU2hJvLcaDhV691b0uDCJ2G2lcS2YqEX/1Q93NMFi0wIuZTJYQf
+        73yhd1Tm7Lee8Fffn2G0YyR5OTMEiiz81cNzNXkWKOjJwLio9IHXmm6Gh06JCVceLPbyo9BCttTY
+        9EGHhz562zGGhnn1iOQLA1jj65BCw5NaelNnkTGzLGcknMDNp+c0ASztKgWN+mZPeLtvXbYTdx0q
+        J5Zh4/OqgNhc5xWl92tMHca9I4L7xEPcqzDopdvfwGLnxxGQ15nhOMWSPj60xoROc8uwNRhwWC9Z
+        pwFXwzufhMctYKdJilFrhyN1JbQOS+ExCV5KMaA4JUUtkkYkcHekId1J23KYPlc8Q6F+nbHpiAYT
+        /H0cgqbY7nF2/SzDeidTAcXus6exvKsznvVVBWzcaVitLu+azP2OQ3nQ3vFR35rDSuswAN/zi6bc
+        0XZnTnvwEOXrlSyXThyW4v7wIS5eDwJvAj98/VGOXpVWUvVkDBnLrZhAr4MTTQ63NXv1JTThZz8D
+        ejZOlc7sgFNgs9SCr4xwBMOK3AQw8bDHTnhQ3fmcOxVQRVvyW+cdZrNw23RQTsuQXvdvEnXCTezg
+        V/9jXyyFYU7eUwC+649x0A/Z2F6bEH52UovvrviKmGQ0AZQjJPn0W8+WROs0eNPGJ/7uV0ZO4baH
+        7MnLOEorLZtruvGgbGw0uie3sl5W89Er6fFc0KvCDpHYEHuGj6zoaWC/FzDSOMqha60ZvcX3ldEw
+        TRN48Z83ImSSP7ztfeijDzftyLwXm2hpa0GFtVFb1Lrtp3q2XC+AN5+38a1Gu2HN1spCfpC5fu1F
+        Klubq05A9zIdvFPfE2P35xIgpQptvAOew8b+Up1RoEUJWVq31L/+xwKdOjk+SIcxG7/+BT6FmMM7
+        3f/UyzbaqlAe8RG7toOG1RtTC87BpyXKc5gzej51K5DTOiTrz3+MrtlC7Xzf0MygOViFneEgTWMG
+        EU/PdqDQxyr4xruvnP2rK1YCSGDPVkbk1dOjNS83IXynuUV2TjYPrBJYgooP4b/1XAbjwB0IspIX
+        wvjrJxfjcW+g/RjI3/zeEsG1ABUqTNAeopppx5CgQx2bRA53Z33xo9SCX/9CQ6fh9NkQtg5U+qnx
+        pcVadfbYvVV4lOwtdV3dHOayuvLwr5442DAah3uoAilsYuqm2Y0xv0g4aDTWilWeXob+5yerbRHS
+        3OMXtvRjl8DoNu588P0/oVlOZyTprMWHT5jUc1xsW8QB80z3NYb6Kk2tBQzz4vmgrZuaeGNooe/+
+        4Hs7hvo69zsICkuT8eGCz7qwSS0Ic1F442P08CIWJ0n+mx/OT3iumXB8KNAk4Zna25HLuqYJKyV/
+        uRXWb29uIHxnqYg7jDmOv/p5xYHTgs/HWbB52PYubV2nAr1xCjEOoxIsFSYQds1B9cEwCvqH65Cn
+        tLkAqblbeMZW2ZxBe3R3hKvzVV/VxvLh6SjVON9fpYg8thcffuOF7le+yJazUUL4He+DMDjWq9AK
+        Ofz6bep/kBmtgfoJwM+P//QSAcPowcpUF2oNZ6zz2+nSwmePI+p847G/eKIJvzzG59zsOKzFsYOQ
+        K7dbrOW2Fq3skRH48rueujh/RYufcwJMQ2nxV0n9AJ7TLgI8vh8G9oZr/eUxZwOs9v74t77MQWMb
+        cFrhAf/4AlnDdwJrkifY9rpZnwu1smBwMix6KRxVF+JFVmFgCasv3MpXtBYPJ4Bf/uR/84P1nlZ7
+        sDrZIba//n972BYB7ByXYrtGZT13ecYB4zNp1N33VT3xaOBgkjCf2l//skRPysHPTmmpcxzLaN4e
+        hgA+5DjA9qrE7rLDyAdAgwrWpdsH9N94Adc0EPGVxRMYXwKRBN1PMVXdwIrGSpzv6PIIbGorh4e+
+        3MP1DrlPevOVIi7ZOp24EH6su4rdp+nqc7o1eoBs74AzdXPK1s/q3OGzmAm9G45c08tbXuGrkUey
+        kblRX81LoMIg2kRkMa4gm8N+nuFq+hrWw/RabzNPWxEHjDPeqWKRfeshgXypxv6WB9eMNRFvIWJ0
+        2pff2GB94EpBT7uoaGRvJDAE6NSDn5/An6TUZ/JZUmgZqkj9n59Mt0YHvTeqMW5QFTFOnnv0KE3g
+        S9JFdsku6EOIL3dINet4ZswwPsbPj1Kz6gX2V/898tsWm5F20lnwVjsISTQS5uAh+/kLkBi+hfeL
+        a4P1Jdkqsh8f8ounaO2yJYeeax+wh5ZTti2ESoDILDVqA61gLdjLCrw/1AjnXaNFQmqqFpJkofzq
+        rXMtPLJDAwf7qpNNGJVs1Squh0shSr5eTWRgnZYoP/5Hf/V9eegnBzk93JJlSSx3+3EH86/+TJxs
+        0sePw2k/v4F97TW7rDrZBuTX8UT98HgBf+P9wlcXapy2a0Q9PQhhnM0FtnxhYKstqykiUS8RepR0
+        ff6ej+jnv9WrEGWdwB9D+OODNnu9o+X1MM8wf9kVVu3rJluaUuNQuz1wVP2spfv14xU0p8ih2lfv
+        j/1pGuH7cYmw7WIXTOZ+10FWVlsif/VmZa3JqHz1IE6Q2mdTzXcK+PmPmzpfmdjbaovW07mmh1sf
+        slwB+wKi+pLjQ35p3JHgYYXvQr3R5+x8shliwwBBWkzU6U6gZkpshYB1Jv7LE8lbEO+wjo869SWv
+        05dVkRQYO+aLajei12xrEg+ixEM07tddLcZJkENjy084v6V3MJfVk4dKTxu6S/U4E19GKoDlnYXY
+        GODodibRq59/95tOWQZi9887hMcW+BsBnrKuv1Qxep42nE8bpGX0OSUdsvqT9NX7N3196dMK3jGT
+        8Y8v0vvF4+DcKcDnC/rK2NVYC9gmUYXNuW3qsTnLPuT4QvnL36gZWjkgVnHF8VDw0ZJ06Rn89OXh
+        y5/nYotm8KwH2R+Ss66z80hWeLZvnb9aj0O09pJigVbYW2TzfG/qL//t4fvVfDCWudFlfc8F4Fuv
+        /RmUj+FvfP/48zGTXH3eo0aA3SFofHFNunruPlao6PcbwCY7qpFgrQGBJ0f18cXakujzOy/uZPTp
+        MVVeTOQbKf/xJh8Yu1GfnFtC/uphR65EMCpVpaLwg2O6D8I3G7n7cIfh5xhT9cu/tk2pwb/n704o
+        5ZrlUOb++m9POIvscxpzD/C6N/scM69s9kdlhPFbcrGfjL07J+uphfkwQiIAS3HZrAQxOoXPHtuq
+        ttdZ6ZxS2NCtgs3XfaOz1H+EEE/jiUZZsNX71wOkcHFaAWP+1X39b5LA5elCbHCtNyyf10xgfUQT
+        tsL2FgkuYHf441Xu+3TNVuUSeSDMjS3+zg9M9ypa4Tk71PjohoW7dNtUhd4hWKm1nwFgr7zI4U9f
+        eN/6Roqu5cBV0yvy+vLHJXx/PAhvpMV6L6VsNHZlBcUYOfiIPM9d3pakKi+xWagfd+eBedIgKXUV
+        E+zue60WY1LeUX1fH4Trmiqa72OmAtDGM7WGjZqtvixX8DQQ++cHojZLzhWyLmSlh52oAvLVI1Ai
+        RPXnznZqwQTOGZJBOn737wAYy9UZXomI/K6Sg4wqh2sMPvsV+Eyyxay5pHsJSmEb00MPqD5yZnqH
+        h13n+gVYAp0gq+GQ8nzr2KrkOXsqr7KFocZdsEfXSm+8/XGEsekH2NIClQnNoUrhV/9hz8nL7Dt/
+        Dfn87OIo0P1sCuaUh6Of8Pi51FM04scpgYdOinE4LZa7ts1gQOsyrth5C3B4r9E5h29gyT48qaK+
+        wh0KfvoIm6P7AsupWCowjKNMjU451bM1cw388lYfda4W8T//8tO3qL40NZ3C4QzltkMkXa5DvV7e
+        xgjD7WVHrbCVo/Vz5Xl4dYMdPnz546/fBNVrfiLsNDZsLTTY/+XBzlu418365DyABK32pQDPOuOC
+        HUGPdRWwffOBvn75E7D3fuRvP2TOft+V3/ltPOOdvrinZw7H10elKh7e+qwr8vyXJ+jLuxx+fAea
+        B9X20bc/Jy7r0wT1W+KoSUI4rHC3DWBQrTr2PmQEM51LE3KPgFDHPmn1ll7VCpW9EhDu64f7Je16
+        CPJDSv/y09/+QXIa8U14V+53fh3gdq5B/Uxn2boeNPJ3v3+8aL7HjgbsVvH9zVqGNVPNWkWFC3yM
+        maeDWZ3SBB57y8YPN1RdsT4ad3iuY5kweZ3YlHnajMjj8PDrxlwZKVgWKN/8JLydsmGcH64FvvyG
+        2l7yqIXJPDXw16+5uJ445C03E7Sl1egPYVHojNJGQy3sK7LVYkVfvL0yg/FWX+h+cT9gDo6z+ePZ
+        1PsQD/A7fbgrWtH09FLWjT7LmRKD24frCT9fB33clpICnVug4PjC37J5rG0Cw3MXUHVBU0buZKqg
+        9pAbIn/95dZpUAKNIvz2x6gwEJl/8Art04akzwyB1VkOFij8JvKRKZbRXDMmwFLv9vj2kMdo2Vyu
+        IXwKZw5rEoEDO5eage7lOyVojsmwGn53/ulzwmXRC3Q/fbbi7o3d8fqu57MUWCiWGxMb57cyrPHE
+        J3Cjdi+q7kUjEz+N3/x4Az7qzjZjiHox9Iz3RL/nq1v20tGAuXUx8SGWnJpwsttA8VE1VK0uh0E0
+        9WsFke0fiJArn+jbLwgB7qwdVvFwcLfpLr//rV93NfV0QZ96CF3zEGMHZCoQxtkq4MtZL1g7GLo7
+        f/UUcJos80EkGy7jnrWKmizkCbt4G7AU94uHCpBSAvNyD2axGTiYB82dgAFag6iatQY3jZZh/Cgs
+        9u0H8gicu+2X56g1PxmbHF6r4ogvQjOBbhaDFZqmusEnutHB+uuH3o2Vo4ar9+58wKqCEsOzsMtX
+        jM03q+pQrfYMHxVniZaW0zuknfPNr75m7CxGBrSLM4+vn2pwl3Qrj8BiRYKdahrc6ZhgCwqaUmNL
+        /zRg+PYf//qLxxBw0fzrXzqiUdCQShyjXz+tpM6QUe/L9+kkXToI1nuGL1qc6uu9VgVk1G6HHRO/
+        f/mz/vgNdpX247L+eWrR1WogVpOyAV9+3EKBozw2/L0BmKy+O0iiTsJJHL0yui0YD6XLsyTAdh71
+        Mj9mH/7zuxXwX//68+d//G4YtN0jf30vBkz5Mv3H/7kq8B/if4xt+nr9vYZAxrTI//n3/76B8M9n
+        6NrP9D+nrsnf4z///rMV/t41+GfqpvT1/z7/1/dV//Wv/wUAAP//AwBcfFVx4CAAAA==
+    headers:
+      CF-RAY:
+      - 931fceef786ded38-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fj4RMXSXRDQjE2CFC6CGC3dVcJ8cl2Cbu8alijwMHA8-1744933655-1.0.1.1-M3c3AI4XQa.0GJoanNACuOm2aEL4xjqHR1grxIP3olFvq3e0eFHwQTvCF20YwR_OLiMJUH87eNUwgziawMccsxjR9OVZyDr5._5Wts6CrqA;
+        path=/; expires=Fri, 18-Apr-25 00:17:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=MSkpJsQZtdyIGvrl2mIwy0a_We8H6CIrS7etFgRBl2Y-1744933655703-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-origin:
+      - '*'
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-model:
+      - text-embedding-3-small
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '140'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      via:
+      - envoy-router-84959bbcd5-rzqvq
+      x-envoy-upstream-service-time:
+      - '110'
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999986'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_dd3ef61c4765b46ed7db80ddfe261f41
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task respond using the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "\nCurrent Task:
+      What is Brandon''s favorite color?\n\nThis is the expected criteria for your
+      final answer: Brandon''s favorite color.\nyou 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:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '926'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFLBbtswDL37KwhdeokLx0mbOLd2WIAC63YZdthWGIpMO9xkUZDkpEWR
+        fx/kpLG7dUAvBszHR733yOcEQFAlViDUVgbVWp3efv66LvKPRd7Q/f57vtaf7m6ePjze774sv23E
+        JDJ48wtVeGFdKm6txkBsjrByKAPGqdPFfF7MZtdXVz3QcoU60hob0jmnLRlK8yyfp9kinS5P7C2T
+        Qi9W8CMBAHjuv1GnqfBRrCCbvFRa9F42KFbnJgDhWMeKkN6TD9IEMRlAxSag6aXfgeE9KGmgoR2C
+        hCbKBmn8Hh3AT7MmIzXc9P8ruHXSVGwuPNRyx44CgmLNDsjDRnd4OX7GYd15Ga2aTusRII3hIGNU
+        vcGHE3I4W9LcWMcb/xdV1GTIb0uH0rOJ8n1gK3r0kAA89NF1r9IQ1nFrQxn4N/bPTa+Xx3li2NgI
+        LU5g4CD1qL5cTN6YV1YYJGk/Cl8oqbZYDdRhU7KriEdAMnL9r5q3Zh+dk2neM34AlEIbsCqtw4rU
+        a8dDm8N40P9rO6fcCxYe3Y4UloHQxU1UWMtOH89M+CcfsC1rMg066+h4a7Uts1mRL/M8KzKRHJI/
+        AAAA//8DALRhJdF5AwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 931fcef51a67f947-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 17 Apr 2025 23:47:36 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=7agwu5JV1OJvEFNhvfvqdgWf.HoMyIni9D85soRl3WE-1744933656-1.0.1.1-dKUwAZnjjuuiswFKWGsxpwHNBJUpjhYlZvfZpyNQIejxEJrXMCppgPvtQ9wa4SKezLmKqftvn_H.bAx_AEFJD2EWm5V6R_uK8.odneErR6A;
+        path=/; expires=Fri, 18-Apr-25 00:17:36 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=LdTrzwZYrB6ZyQLY7NdaaHVpDVFvIjYm3arSpNy87wU-1744933656504-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '540'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999802'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8837be6510731522fd5ac4b75c11d486
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/tests/crew_test.py
+++ b/tests/crew_test.py
@@ -3,17 +3,17 @@
 import hashlib
 import json
 import os
-import sys
 import tempfile
 from concurrent.futures import Future
 from unittest import mock
-from unittest.mock import MagicMock, Mock, patch
+from unittest.mock import MagicMock, patch

 import pydantic_core
 import pytest

 from crewai.agent import Agent
 from crewai.agents import CacheHandler
+from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
@@ -2153,6 +2153,7 @@ def test_tools_with_custom_caching():
    with patch.object(
        CacheHandler, "add", wraps=crew._cache_handler.add
    ) as add_to_cache:
+
        result = crew.kickoff()

        # Check that add_to_cache was called exactly twice
@@ -4338,48 +4339,3 @@ def test_crew_copy_with_memory():
            raise e  # Re-raise other validation errors
    except Exception as e:
        pytest.fail(f"Copying crew raised an unexpected exception: {e}")
-
-
-@patch.dict(os.environ, {}, clear=True)  # Ensure AGENTOPS_API_KEY is not set
-@patch("sys.modules")
-def test_crew_kickoff_with_agentops_installed_no_key(mock_sys_modules):
-    """
-    Test that crew kickoff does not raise an error if agentops is installed
-    but the AGENTOPS_API_KEY environment variable is not set.
-    This simulates the scenario described in issue #2601.
-    """
-    mock_agentops = MagicMock()
-    mock_sys_modules["agentops"] = mock_agentops
-
-    listener_module_name = "crewai.utilities.events.third_party.agentops_listener"
-    if listener_module_name in sys.modules:
-        del sys.modules[listener_module_name]
-
-    import importlib
-
-    agentops_listener_module = importlib.import_module(listener_module_name)  # noqa: F841 - Used for side effects (registration)
-
-    mock_llm = Mock(spec=LLM)
-    mock_llm.invoke = Mock(return_value="Task completed.")
-    mock_llm.tokens_usage = []  # Mock token usage tracking if needed
-
-    test_agent = Agent(role="tester", goal="test", backstory="testing", llm=mock_llm)
-    test_task = Task(
-        description="test task", expected_output="tested", agent=test_agent
-    )
-
-    # Create the crew
-    crew = Crew(agents=[test_agent], tasks=[test_task])
-
-    try:
-        crew.kickoff()
-    except Exception as e:
-        if "agentops" in str(type(e)).lower() or "api key" in str(e).lower():
-            pytest.fail(f"Crew kickoff raised an unexpected AgentOps exception: {e}")
-
-    mock_agentops.init.assert_not_called()
-
-    if "agentops" in sys.modules:
-        del sys.modules["agentops"]
-    if listener_module_name in sys.modules:
-        del sys.modules[listener_module_name]
Author	SHA1	Message	Date
Devin AI	5320960f3f	docs: add flow plot visualization example to documentation (#2668 ) Co-Authored-By: Joe Moura <joao@crewai.com>	2025-04-22 19:07:38 +00:00
Tony Kipkemboi	16eb4df556	docs: update docs.json with contextual options, SEO, and 404 redirect (#2654 ) * docs: 0.114.0 release notes, navigation restructure, new guides, deploy video, and cleanup - Add v0.114.0 release notes with highlights image and doc links - Restructure docs navigation (Strategy group, Releases tab, navbar links) - Update quickstart with deployment video and clearer instructions - Add/rename guides (Custom Manager Agent, Custom LLM) - Remove legacy concept/tool docs - Add new images and tool docs - Minor formatting and content improvements throughout * docs: update docs.json with contextual options, SEO indexing, and 404 redirect settings	2025-04-22 09:52:27 -07:00
Vini Brasil	3d9000495c	Change CLI tool publish message (#2662 )	2025-04-22 13:09:30 -03:00
Tony Kipkemboi	6d0039b117	docs: 0.114.0 release notes, navigation restructure, new guides, deploy video, and cleanup (#2653 ) Some checks are pending Notify Downstream / notify-downstream (push) Waiting to run Details - Add v0.114.0 release notes with highlights image and doc links - Restructure docs navigation (Strategy group, Releases tab, navbar links) - Update quickstart with deployment video and clearer instructions - Add/rename guides (Custom Manager Agent, Custom LLM) - Remove legacy concept/tool docs - Add new images and tool docs - Minor formatting and content improvements throughout	2025-04-21 19:18:21 -04:00
Lorenze Jay	311a078ca6	Enhance knowledge management in CrewAI (#2637 ) Some checks failed Notify Downstream / notify-downstream (push) Has been cancelled Details * Enhance knowledge management in CrewAI - Added `KnowledgeConfig` class to configure knowledge retrieval parameters such as `limit` and `score_threshold`. - Updated `Agent` and `Crew` classes to utilize the new knowledge configuration for querying knowledge sources. - Enhanced documentation to clarify the addition of knowledge sources at both agent and crew levels. - Introduced new tips in documentation to guide users on knowledge source management and configuration. * Refactor knowledge configuration parameters in CrewAI - Renamed `limit` to `results_limit` in `KnowledgeConfig`, `query_knowledge`, and `query` methods for consistency and clarity. - Updated related documentation to reflect the new parameter name, ensuring users understand the configuration options for knowledge retrieval. * Refactor agent tests to utilize mock knowledge storage - Updated test cases in `agent_test.py` to use `KnowledgeStorage` for mocking knowledge sources, enhancing test reliability and clarity. - Renamed `limit` to `results_limit` in `KnowledgeConfig` for consistency with recent changes. - Ensured that knowledge queries are properly mocked to return expected results during tests. * Add VCR support for agent tests with query limits and score thresholds - Introduced `@pytest.mark.vcr` decorator in `agent_test.py` for tests involving knowledge sources, ensuring consistent recording of HTTP interactions. - Added new YAML cassette files for `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold` and `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default`, capturing the expected API responses for these tests. - Enhanced test reliability by utilizing VCR to manage external API calls during testing. * Update documentation to format parameter names in code style - Changed the formatting of `results_limit` and `score_threshold` in the documentation to use code style for better clarity and emphasis. - Ensured consistency in documentation presentation to enhance user understanding of configuration options. * Enhance KnowledgeConfig with field descriptions - Updated `results_limit` and `score_threshold` in `KnowledgeConfig` to use Pydantic's `Field` for improved documentation and clarity. - Added descriptions to both parameters to provide better context for their usage in knowledge retrieval configuration. * docstrings added	2025-04-18 18:33:04 -07:00