Fix import sorting issues in Elasticsearch integration

Co-Authored-By: Joe Moura <joao@crewai.com>

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

docs/concepts/cli.mdx

@@ -179,7 +179,78 @@ def crew(self) -> Crew:
 ```
 </Note>
 
-### 10. API Keys
+### 10. Deploy
+
+Deploy the crew or flow to [CrewAI Enterprise](https://app.crewai.com).
+
+- **Authentication**: You need to be authenticated to deploy to CrewAI Enterprise.
+    ```shell Terminal
+    crewai signup
+    ```
+    If you already have an account, you can login with:
+    ```shell Terminal
+    crewai login
+    ```
+
+- **Create a deployment**: Once you are authenticated, you can create a deployment for your crew or flow from the root of your localproject.
+    ```shell Terminal
+    crewai deploy create
+    ```
+    - Reads your local project configuration.
+    - Prompts you to confirm the environment variables (like `OPENAI_API_KEY`, `SERPER_API_KEY`) found locally. These will be securely stored with the deployment on the Enterprise platform. Ensure your sensitive keys are correctly configured locally (e.g., in a `.env` file) before running this.
+    - Links the deployment to the corresponding remote GitHub repository (it usually detects this automatically).
+
+- **Deploy the Crew**: Once you are authenticated, you can deploy your crew or flow to CrewAI Enterprise.
+    ```shell Terminal
+    crewai deploy push
+    ``` 
+    - Initiates the deployment process on the CrewAI Enterprise platform.
+    - Upon successful initiation, it will output the Deployment created successfully! message along with the Deployment Name and a unique Deployment ID (UUID).
+
+- **Deployment Status**: You can check the status of your deployment with:
+    ```shell Terminal
+    crewai deploy status
+    ```
+    This fetches the latest deployment status of your most recent deployment attempt (e.g., `Building Images for Crew`, `Deploy Enqueued`, `Online`).
+
+- **Deployment Logs**: You can check the logs of your deployment with:
+    ```shell Terminal
+    crewai deploy logs
+    ```
+    This streams the deployment logs to your terminal.
+
+- **List deployments**: You can list all your deployments with:
+    ```shell Terminal
+    crewai deploy list
+    ```
+    This lists all your deployments.
+
+- **Delete a deployment**: You can delete a deployment with:
+    ```shell Terminal
+    crewai deploy remove
+    ```
+    This deletes the deployment from the CrewAI Enterprise platform.
+
+- **Help Command**: You can get help with the CLI with:
+    ```shell Terminal
+    crewai deploy --help
+    ```
+    This shows the help message for the CrewAI Deploy CLI.
+
+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>
+
+### 11. API Keys
 
 When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.
 

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:

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>

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": {

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

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
 ---

docs/how-to/elasticsearch-integration.md

@@ -0,0 +1,117 @@
+# Elasticsearch Integration
+
+CrewAI supports using Elasticsearch as an alternative to ChromaDB for RAG (Retrieval Augmented Generation) storage. This allows you to leverage Elasticsearch's powerful search capabilities and scalability for your AI agents.
+
+## Installation
+
+To use Elasticsearch with CrewAI, you need to install the Elasticsearch Python client:
+
+```bash
+pip install elasticsearch
+```
+
+## Using Elasticsearch for Memory
+
+You can configure your crew to use Elasticsearch for memory storage:
+
+```python
+from crewai import Agent, Crew, Task
+
+# Create agents and tasks
+agent = Agent(
+    role="Researcher",
+    goal="Research a topic",
+    backstory="You are a researcher who loves to find information.",
+)
+
+task = Task(
+    description="Research about AI",
+    expected_output="Information about AI",
+    agent=agent,
+)
+
+# Create a crew with Elasticsearch memory
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    memory_config={
+        "provider": "elasticsearch",
+        "host": "localhost",  # Optional, defaults to localhost
+        "port": 9200,         # Optional, defaults to 9200
+        "username": "user",   # Optional
+        "password": "pass",   # Optional
+    },
+)
+
+# Execute the crew
+result = crew.kickoff()
+```
+
+## Using Elasticsearch for Knowledge
+
+You can also use Elasticsearch for knowledge storage:
+
+```python
+from crewai import Agent, Crew, Task
+from crewai.knowledge import Knowledge
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+# Create knowledge with Elasticsearch storage
+content = "AI is a field of computer science that focuses on creating machines that can perform tasks that typically require human intelligence."
+string_source = StringKnowledgeSource(
+    content=content, metadata={"topic": "AI"}
+)
+
+knowledge = Knowledge(
+    collection_name="test",
+    sources=[string_source],
+    storage_provider="elasticsearch",  # Use Elasticsearch
+    # Optional Elasticsearch configuration
+    host="localhost",
+    port=9200,
+    username="user",
+    password="pass",
+)
+
+# Create an agent with the knowledge
+agent = Agent(
+    role="AI Expert",
+    goal="Explain AI",
+    backstory="You are an AI expert who loves to explain AI concepts.",
+    knowledge=[knowledge],
+)
+
+# Create a task
+task = Task(
+    description="Explain what AI is",
+    expected_output="Explanation of AI",
+    agent=agent,
+)
+
+# Create a crew
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+)
+
+# Execute the crew
+result = crew.kickoff()
+```
+
+## Configuration Options
+
+The Elasticsearch integration supports the following configuration options:
+
+- `host`: Elasticsearch host (default: "localhost")
+- `port`: Elasticsearch port (default: 9200)
+- `username`: Elasticsearch username (optional)
+- `password`: Elasticsearch password (optional)
+- Additional keyword arguments are passed directly to the Elasticsearch client
+
+## Running Tests
+
+To run the Elasticsearch tests, you need to set the `RUN_ELASTICSEARCH_TESTS` environment variable to `true`:
+
+```bash
+RUN_ELASTICSEARCH_TESTS=true pytest tests/memory/elasticsearch_storage_test.py tests/knowledge/elasticsearch_knowledge_storage_test.py tests/integration/elasticsearch_integration_test.py
+```

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:
 

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

docs/tools/langchaintool.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.

pyproject.toml

@@ -37,6 +37,7 @@ dependencies = [
     "tomli>=2.0.2",
     "blinker>=1.9.0",
     "json5>=0.10.0",
+    "elasticsearch>=9.0.0",
 ]
 
 [project.urls]

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)

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

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

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"),
         }
 

src/crewai/knowledge/knowledge.py

@@ -1,11 +1,18 @@
 import os
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, cast
 
 from pydantic import BaseModel, ConfigDict, Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 
+try:
+    from crewai.knowledge.storage.elasticsearch_knowledge_storage import (
+        ElasticsearchKnowledgeStorage,
+    )
+except ImportError:
+    ElasticsearchKnowledgeStorage = None
+
 os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
 
 
@@ -30,20 +37,34 @@ class Knowledge(BaseModel):
         sources: List[BaseKnowledgeSource],
         embedder: Optional[Dict[str, Any]] = None,
         storage: Optional[KnowledgeStorage] = None,
+        storage_provider: str = "chromadb",
         **data,
     ):
         super().__init__(**data)
         if storage:
             self.storage = storage
         else:
-            self.storage = KnowledgeStorage(
-                embedder=embedder, collection_name=collection_name
-            )
+            if storage_provider == "elasticsearch":
+                try:
+                    self.storage = cast(KnowledgeStorage, self._create_elasticsearch_storage(
+                        embedder, collection_name
+                    ))
+                except ImportError:
+                    raise ImportError(
+                        "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+                    )
+            else:
+                self.storage = KnowledgeStorage(
+                    embedder=embedder, collection_name=collection_name
+                )
         self.sources = sources
-        self.storage.initialize_knowledge_storage()
+        if self.storage is not None:
+            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 +77,8 @@ class Knowledge(BaseModel):
 
         results = self.storage.search(
             query,
-            limit,
+            limit=results_limit,
+            score_threshold=score_threshold,
         )
         return results
 
@@ -68,6 +90,16 @@ class Knowledge(BaseModel):
         except Exception as e:
             raise e
 
+    def _create_elasticsearch_storage(self, embedder, collection_name):
+        """Create an Elasticsearch storage instance."""
+        if ElasticsearchKnowledgeStorage is None:
+            raise ImportError(
+                "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+            )
+        return ElasticsearchKnowledgeStorage(
+            embedder_config=embedder, collection_name=collection_name
+        )
+
     def reset(self) -> None:
         if self.storage:
             self.storage.reset()

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",
+    )

src/crewai/knowledge/storage/elasticsearch_knowledge_storage.py

@@ -0,0 +1,268 @@
+import contextlib
+import hashlib
+import io
+import logging
+import os
+from typing import Any, Dict, List, Optional, Union, cast
+
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.logger import Logger
+from crewai.utilities.paths import db_storage_path
+
+
+@contextlib.contextmanager
+def suppress_logging(logger_name="elasticsearch", level=logging.ERROR):
+    logger = logging.getLogger(logger_name)
+    original_level = logger.getEffectiveLevel()
+    logger.setLevel(level)
+    with (
+        contextlib.redirect_stdout(io.StringIO()),
+        contextlib.redirect_stderr(io.StringIO()),
+        contextlib.suppress(UserWarning),
+    ):
+        yield
+    logger.setLevel(original_level)
+
+
+class ElasticsearchKnowledgeStorage(BaseKnowledgeStorage):
+    """
+    Extends BaseKnowledgeStorage to use Elasticsearch for storing embeddings
+    and improving search efficiency.
+    """
+
+    app: Any = None
+    collection_name: Optional[str] = "knowledge"
+
+    def __init__(
+        self,
+        embedder_config: Optional[Dict[str, Any]] = None,
+        collection_name: Optional[str] = None,
+        host: str = "localhost",
+        port: int = 9200,
+        username: Optional[str] = None,
+        password: Optional[str] = None,
+        **kwargs: Any
+    ):
+        self.collection_name = collection_name
+        self._set_embedder_config(embedder_config)
+        
+        self.host = host
+        self.port = port
+        self.username = username
+        self.password = password
+        self.index_name = f"crewai_knowledge_{collection_name if collection_name else 'default'}".lower()
+        self.additional_config = kwargs
+
+    def search(
+        self,
+        query: List[str],
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Dict[str, Any]]:
+        if not self.app:
+            self.initialize_knowledge_storage()
+            
+        try:
+            embedding = self._get_embedding_for_text(query[0])
+            
+            search_query: Dict[str, Any] = {
+                "size": limit,
+                "query": {
+                    "script_score": {
+                        "query": {"match_all": {}},
+                        "script": {
+                            "source": "cosineSimilarity(params.query_vector, 'embedding') + 1.0",
+                            "params": {"query_vector": embedding}
+                        }
+                    }
+                }
+            }
+            
+            if filter:
+                query_obj = search_query.get("query", {})
+                if isinstance(query_obj, dict):
+                    script_score_obj = query_obj.get("script_score", {})
+                    if isinstance(script_score_obj, dict):
+                        query_part = script_score_obj.get("query", {})
+                        if isinstance(query_part, dict):
+                            for key, value in filter.items():
+                                new_query = {
+                                    "bool": {
+                                        "must": [
+                                            query_part,
+                                            {"match": {f"metadata.{key}": value}}
+                                        ]
+                                    }
+                                }
+                                if isinstance(script_score_obj, dict):
+                                    script_score_obj["query"] = new_query
+            
+            with suppress_logging():
+                if self.app is not None and hasattr(self.app, "search") and callable(getattr(self.app, "search")):
+                    response = self.app.search(
+                        index=self.index_name,
+                        body=search_query
+                    )
+                
+                    results = []
+                    for hit in response["hits"]["hits"]:
+                        adjusted_score = (hit["_score"] - 1.0)
+                        
+                        if adjusted_score >= score_threshold:
+                            results.append({
+                                "id": hit["_id"],
+                                "metadata": hit["_source"]["metadata"],
+                                "context": hit["_source"]["text"],
+                                "score": adjusted_score,
+                            })
+                        
+                    return results
+                else:
+                    Logger(verbose=True).log("error", "Elasticsearch client is not initialized", "red")
+                    return []
+        except Exception as e:
+            Logger(verbose=True).log("error", f"Search error: {e}", "red")
+            raise Exception(f"Error during knowledge search: {str(e)}")
+
+    def initialize_knowledge_storage(self):
+        try:
+            from elasticsearch import Elasticsearch
+            
+            es_auth = {}
+            if self.username and self.password:
+                es_auth = {"basic_auth": (self.username, self.password)}
+                
+            self.app = Elasticsearch(
+                [f"http://{self.host}:{self.port}"], 
+                **es_auth,
+                **self.additional_config
+            )
+            
+            if not self.app.indices.exists(index=self.index_name):
+                self.app.indices.create(
+                    index=self.index_name,
+                    body={
+                        "mappings": {
+                            "properties": {
+                                "text": {"type": "text"},
+                                "embedding": {
+                                    "type": "dense_vector",
+                                    "dims": 1536,  # Default for OpenAI embeddings
+                                    "index": True,
+                                    "similarity": "cosine"
+                                },
+                                "metadata": {"type": "object"}
+                            }
+                        }
+                    }
+                )
+                
+        except ImportError:
+            raise ImportError(
+                "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+            )
+        except Exception as e:
+            Logger(verbose=True).log(
+                "error", 
+                f"Error initializing Elasticsearch: {str(e)}", 
+                "red"
+            )
+            raise Exception(f"Error initializing Elasticsearch: {str(e)}")
+
+    def reset(self) -> None:
+        try:
+            if self.app is not None:
+                if self.app.indices.exists(index=self.index_name):
+                    self.app.indices.delete(index=self.index_name)
+                
+                self.initialize_knowledge_storage()
+        except Exception as e:
+            raise Exception(
+                f"An error occurred while resetting the knowledge storage: {e}"
+            )
+               
+    def save(
+        self,
+        documents: List[str],
+        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
+    ) -> None:
+        if not self.app:
+            self.initialize_knowledge_storage()
+
+        try:
+            unique_docs = {}
+
+            for idx, doc in enumerate(documents):
+                doc_id = hashlib.sha256(doc.encode("utf-8")).hexdigest()
+                doc_metadata = None
+                if metadata is not None:
+                    if isinstance(metadata, list):
+                        doc_metadata = metadata[idx]
+                    else:
+                        doc_metadata = metadata
+                unique_docs[doc_id] = (doc, doc_metadata)
+
+            for doc_id, (doc, meta) in unique_docs.items():
+                embedding = self._get_embedding_for_text(doc)
+                
+                doc_body = {
+                    "text": doc,
+                    "embedding": embedding,
+                    "metadata": meta or {},
+                }
+                
+                if self.app is not None and hasattr(self.app, "index") and callable(getattr(self.app, "index")):
+                    index_func = getattr(self.app, "index")
+                    index_func(
+                        index=self.index_name,
+                        id=doc_id,
+                        document=doc_body,
+                        refresh=True  # Make the document immediately available for search
+                    )
+                else:
+                    Logger(verbose=True).log("error", "Elasticsearch client is not initialized", "red")
+                
+        except Exception as e:
+            Logger(verbose=True).log("error", f"Save error: {e}", "red")
+            raise Exception(f"Error during knowledge save: {str(e)}")
+
+    def _get_embedding_for_text(self, text: str) -> List[float]:
+        """Get embedding for text using the configured embedder."""
+        if self.embedder_config is None:
+            raise ValueError("Embedder configuration is not set")
+            
+        embedder = self.embedder_config
+        if hasattr(embedder, "embed_documents") and callable(getattr(embedder, "embed_documents")):
+            embed_func = getattr(embedder, "embed_documents")
+            return embed_func([text])[0]
+        elif hasattr(embedder, "embed") and callable(getattr(embedder, "embed")):
+            embed_func = getattr(embedder, "embed")
+            return embed_func(text)
+        else:
+            raise ValueError("Invalid embedding function configuration")
+
+    def _create_default_embedding_function(self):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+        )
+
+    def _set_embedder_config(
+        self, embedder: Optional[Dict[str, Any]] = None
+    ) -> None:
+        """Set the embedding configuration for the knowledge storage.
+
+        Args:
+            embedder (Optional[Dict[str, Any]]): Configuration dictionary for the embedder.
+                If None or empty, defaults to the default embedding function.
+        """
+        self.embedder_config = (
+            EmbeddingConfigurator().configure_embedder(embedder)
+            if embedder
+            else self._create_default_embedding_function()
+        )

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

src/crewai/memory/entity/entity_memory.py

@@ -22,7 +22,9 @@ class EntityMemory(Memory):
         else:
             memory_provider = None
 
-        if memory_provider == "mem0":
+        if storage:
+            pass
+        elif memory_provider == "mem0":
             try:
                 from crewai.memory.storage.mem0_storage import Mem0Storage
             except ImportError:
@@ -30,17 +32,26 @@ class EntityMemory(Memory):
                     "Mem0 is not installed. Please install it with `pip install mem0ai`."
                 )
             storage = Mem0Storage(type="entities", crew=crew)
-        else:
-            storage = (
-                storage
-                if storage
-                else RAGStorage(
+        elif memory_provider == "elasticsearch":
+            try:
+                storage = self._create_elasticsearch_storage(
                     type="entities",
                     allow_reset=True,
                     embedder_config=embedder_config,
                     crew=crew,
                     path=path,
                 )
+            except ImportError:
+                raise ImportError(
+                    "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+                )
+        else:
+            storage = RAGStorage(
+                type="entities",
+                allow_reset=True,
+                embedder_config=embedder_config,
+                crew=crew,
+                path=path,
             )
 
         super().__init__(storage=storage)
@@ -59,6 +70,11 @@ class EntityMemory(Memory):
             data = f"{item.name}({item.type}): {item.description}"
         super().save(data, item.metadata)
 
+    def _create_elasticsearch_storage(self, **kwargs):
+        """Create an Elasticsearch storage instance."""
+        from crewai.memory.storage.elasticsearch_storage import ElasticsearchStorage
+        return ElasticsearchStorage(**kwargs)
+
     def reset(self) -> None:
         try:
             self.storage.reset()

src/crewai/memory/short_term/short_term_memory.py

@@ -24,7 +24,9 @@ class ShortTermMemory(Memory):
         else:
             memory_provider = None
 
-        if memory_provider == "mem0":
+        if storage:
+            pass
+        elif memory_provider == "mem0":
             try:
                 from crewai.memory.storage.mem0_storage import Mem0Storage
             except ImportError:
@@ -32,16 +34,24 @@ class ShortTermMemory(Memory):
                     "Mem0 is not installed. Please install it with `pip install mem0ai`."
                 )
             storage = Mem0Storage(type="short_term", crew=crew)
-        else:
-            storage = (
-                storage
-                if storage
-                else RAGStorage(
+        elif memory_provider == "elasticsearch":
+            try:
+                storage = self._create_elasticsearch_storage(
                     type="short_term",
                     embedder_config=embedder_config,
                     crew=crew,
                     path=path,
                 )
+            except ImportError:
+                raise ImportError(
+                    "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+                )
+        else:
+            storage = RAGStorage(
+                type="short_term",
+                embedder_config=embedder_config,
+                crew=crew,
+                path=path,
             )
         super().__init__(storage=storage)
         self._memory_provider = memory_provider
@@ -68,6 +78,11 @@ class ShortTermMemory(Memory):
             query=query, limit=limit, score_threshold=score_threshold
         )  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
 
+    def _create_elasticsearch_storage(self, **kwargs):
+        """Create an Elasticsearch storage instance."""
+        from crewai.memory.storage.elasticsearch_storage import ElasticsearchStorage
+        return ElasticsearchStorage(**kwargs)
+
     def reset(self) -> None:
         try:
             self.storage.reset()

src/crewai/memory/storage/elasticsearch_storage.py

@@ -0,0 +1,275 @@
+import contextlib
+import io
+import logging
+import os
+import uuid
+from typing import Any, Dict, List, Optional, cast
+
+from crewai.memory.storage.base_rag_storage import BaseRAGStorage
+from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.constants import MAX_FILE_NAME_LENGTH
+from crewai.utilities.logger import Logger
+from crewai.utilities.paths import db_storage_path
+
+
+@contextlib.contextmanager
+def suppress_logging(logger_name="elasticsearch", level=logging.ERROR):
+    logger = logging.getLogger(logger_name)
+    original_level = logger.getEffectiveLevel()
+    logger.setLevel(level)
+    with (
+        contextlib.redirect_stdout(io.StringIO()),
+        contextlib.redirect_stderr(io.StringIO()),
+        contextlib.suppress(UserWarning),
+    ):
+        yield
+    logger.setLevel(original_level)
+
+
+class ElasticsearchStorage(BaseRAGStorage):
+    """
+    Extends BaseRAGStorage to use Elasticsearch for storing embeddings
+    and improving search efficiency.
+    """
+
+    app: Any = None
+
+    def __init__(
+        self, 
+        type: str, 
+        allow_reset: bool = True, 
+        embedder_config: Any = None, 
+        crew: Any = None, 
+        path: Optional[str] = None,
+        host: str = "localhost",
+        port: int = 9200,
+        username: Optional[str] = None,
+        password: Optional[str] = None,
+        **kwargs: Any
+    ):
+        super().__init__(type, allow_reset, embedder_config, crew)
+        agents = crew.agents if crew else []
+        agents = [self._sanitize_role(agent.role) for agent in agents]
+        agents = "_".join(agents)
+        self.agents = agents
+        self.storage_file_name = self._build_storage_file_name(type, agents)
+        
+        self.type = type
+        self.allow_reset = allow_reset
+        self.path = path
+        
+        self.host = host
+        self.port = port
+        self.username = username
+        self.password = password
+        self.index_name = f"crewai_{type}".lower()
+        self.additional_config = kwargs
+        
+        self._initialize_app()
+
+    def _sanitize_role(self, role: str) -> str:
+        """
+        Sanitizes agent roles to ensure valid directory and index names.
+        """
+        return role.replace("\n", "").replace(" ", "_").replace("/", "_")
+
+    def _build_storage_file_name(self, type: str, file_name: str) -> str:
+        """
+        Ensures file name does not exceed max allowed by OS
+        """
+        base_path = f"{db_storage_path()}/{type}"
+
+        if len(file_name) > MAX_FILE_NAME_LENGTH:
+            logging.warning(
+                f"Trimming file name from {len(file_name)} to {MAX_FILE_NAME_LENGTH} characters."
+            )
+            file_name = file_name[:MAX_FILE_NAME_LENGTH]
+
+        return f"{base_path}/{file_name}"
+
+    def _set_embedder_config(self):
+        configurator = EmbeddingConfigurator()
+        self.embedder_config = configurator.configure_embedder(self.embedder_config)
+
+    def _initialize_app(self):
+        try:
+            from elasticsearch import Elasticsearch
+            
+            self._set_embedder_config()
+            
+            es_auth = {}
+            if self.username and self.password:
+                es_auth = {"basic_auth": (self.username, self.password)}
+                
+            self.app = Elasticsearch(
+                [f"http://{self.host}:{self.port}"], 
+                **es_auth,
+                **self.additional_config
+            )
+            
+            if not self.app.indices.exists(index=self.index_name):
+                self.app.indices.create(
+                    index=self.index_name,
+                    body={
+                        "mappings": {
+                            "properties": {
+                                "text": {"type": "text"},
+                                "embedding": {
+                                    "type": "dense_vector",
+                                    "dims": 1536,  # Default for OpenAI embeddings
+                                    "index": True,
+                                    "similarity": "cosine"
+                                },
+                                "metadata": {"type": "object"}
+                            }
+                        }
+                    }
+                )
+                
+        except ImportError:
+            raise ImportError(
+                "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+            )
+        except Exception as e:
+            Logger(verbose=True).log(
+                "error", 
+                f"Error initializing Elasticsearch: {str(e)}", 
+                "red"
+            )
+            raise Exception(f"Error initializing Elasticsearch: {str(e)}")
+
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
+        if not hasattr(self, "app"):
+            self._initialize_app()
+            
+        try:
+            self._generate_embedding(value, metadata)
+        except Exception as e:
+            logging.error(f"Error during {self.type} save: {str(e)}")
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        if not hasattr(self, "app") or self.app is None:
+            self._initialize_app()
+
+        try:
+            embedding = self._get_embedding_for_text(query)
+            
+            search_query: Dict[str, Any] = {
+                "size": limit,
+                "query": {
+                    "script_score": {
+                        "query": {"match_all": {}},
+                        "script": {
+                            "source": "cosineSimilarity(params.query_vector, 'embedding') + 1.0",
+                            "params": {"query_vector": embedding}
+                        }
+                    }
+                }
+            }
+            
+            if filter:
+                query_obj = search_query.get("query", {})
+                if isinstance(query_obj, dict):
+                    script_score_obj = query_obj.get("script_score", {})
+                    if isinstance(script_score_obj, dict):
+                        query_part = script_score_obj.get("query", {})
+                        if isinstance(query_part, dict):
+                            for key, value in filter.items():
+                                new_query = {
+                                    "bool": {
+                                        "must": [
+                                            query_part,
+                                            {"match": {f"metadata.{key}": value}}
+                                        ]
+                                    }
+                                }
+                                if isinstance(script_score_obj, dict):
+                                    script_score_obj["query"] = new_query
+            
+            with suppress_logging():
+                if self.app is not None and hasattr(self.app, "search") and callable(getattr(self.app, "search")):
+                    search_func = getattr(self.app, "search")
+                    response = search_func(
+                        index=self.index_name,
+                        body=search_query
+                    )
+                    
+                    results = []
+                    for hit in response["hits"]["hits"]:
+                        adjusted_score = (hit["_score"] - 1.0)
+                        
+                        if adjusted_score >= score_threshold:
+                            results.append({
+                                "id": hit["_id"],
+                                "metadata": hit["_source"]["metadata"],
+                                "context": hit["_source"]["text"],
+                                "score": adjusted_score,
+                            })
+                        
+                    return results
+                else:
+                    logging.error("Elasticsearch client is not initialized")
+                    return []
+        except Exception as e:
+            logging.error(f"Error during {self.type} search: {str(e)}")
+            return []
+
+    def _get_embedding_for_text(self, text: str) -> List[float]:
+        """Get embedding for text using the configured embedder."""
+        if self.embedder_config is None:
+            raise ValueError("Embedder configuration is not set")
+            
+        embedder = self.embedder_config
+        if hasattr(embedder, "embed_documents") and callable(getattr(embedder, "embed_documents")):
+            embed_func = getattr(embedder, "embed_documents")
+            return embed_func([text])[0]
+        elif hasattr(embedder, "embed") and callable(getattr(embedder, "embed")):
+            embed_func = getattr(embedder, "embed")
+            return embed_func(text)
+        else:
+            raise ValueError("Invalid embedding function configuration")
+
+    def _generate_embedding(self, text: str, metadata: Optional[Dict[str, Any]] = None) -> Any:
+        """Generate embedding for text and save to Elasticsearch.
+        
+        This method overrides the BaseRAGStorage method to use Elasticsearch.
+        """
+        if not hasattr(self, "app") or self.app is None:
+            self._initialize_app()
+
+        embedding = self._get_embedding_for_text(text)
+        
+        doc = {
+            "text": text,
+            "embedding": embedding,
+            "metadata": metadata or {},
+        }
+        
+        if self.app is not None and hasattr(self.app, "index") and callable(getattr(self.app, "index")):
+            index_func = getattr(self.app, "index")
+            result = index_func(
+                index=self.index_name,
+                id=str(uuid.uuid4()),
+                document=doc,
+                refresh=True  # Make the document immediately available for search
+            )
+            return result
+        return None
+
+    def reset(self) -> None:
+        try:
+            if self.app is not None:
+                if self.app.indices.exists(index=self.index_name):
+                    self.app.indices.delete(index=self.index_name)
+                
+                self._initialize_app()
+        except Exception as e:
+            raise Exception(
+                f"An error occurred while resetting the {self.type} memory: {e}"
+            )

src/crewai/memory/storage/storage_factory.py

@@ -0,0 +1,81 @@
+from typing import Any, Dict, Optional, Type, cast
+
+from crewai.memory.storage.base_rag_storage import BaseRAGStorage
+from crewai.memory.storage.rag_storage import RAGStorage
+from crewai.utilities.logger import Logger
+
+try:
+    from crewai.memory.storage.elasticsearch_storage import ElasticsearchStorage
+except ImportError:
+    ElasticsearchStorage = None
+
+try:
+    from crewai.memory.storage.mem0_storage import Mem0Storage
+except ImportError:
+    Mem0Storage = None
+
+
+class StorageFactory:
+    """Factory for creating storage instances based on provider type."""
+
+    @classmethod
+    def create_storage(
+        cls,
+        provider: str,
+        type: str,
+        allow_reset: bool = True,
+        embedder_config: Optional[Any] = None,
+        crew: Any = None,
+        path: Optional[str] = None,
+        **kwargs,
+    ) -> BaseRAGStorage:
+        """Create a storage instance based on the provider type.
+
+        Args:
+            provider: Type of storage provider ("chromadb", "elasticsearch", "mem0").
+            type: Type of memory storage (e.g., "short_term", "entity").
+            allow_reset: Whether to allow resetting the storage.
+            embedder_config: Configuration for the embedder.
+            crew: Crew instance.
+            path: Path to the storage.
+            **kwargs: Additional arguments.
+
+        Returns:
+            Storage instance.
+        """
+        if provider == "elasticsearch":
+            if ElasticsearchStorage is None:
+                Logger(verbose=True).log(
+                    "error",
+                    "Elasticsearch is not installed. Please install it with `pip install elasticsearch`.",
+                    "red",
+                )
+                raise ImportError(
+                    "Elasticsearch is not installed. Please install it with `pip install elasticsearch`."
+                )
+            return ElasticsearchStorage(
+                type=type,
+                allow_reset=allow_reset,
+                embedder_config=embedder_config,
+                crew=crew,
+                path=path,
+                **kwargs,
+            )
+        elif provider == "mem0":
+            if Mem0Storage is None:
+                Logger(verbose=True).log(
+                    "error",
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`.",
+                    "red",
+                )
+                raise ImportError(
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`."
+                )
+            return cast(BaseRAGStorage, Mem0Storage(type=type, crew=crew))
+        return RAGStorage(
+            type=type,
+            allow_reset=allow_reset,
+            embedder_config=embedder_config,
+            crew=crew,
+            path=path,
+        )

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."

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

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

tests/integration/elasticsearch_integration_test.py

@@ -0,0 +1,90 @@
+"""Integration test for Elasticsearch with CrewAI."""
+
+import os
+import unittest
+
+import pytest
+
+from crewai import Agent, Crew, Task
+from crewai.knowledge import Knowledge
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+
+@pytest.mark.skipif(
+    os.environ.get("RUN_ELASTICSEARCH_TESTS") != "true",
+    reason="Elasticsearch tests require RUN_ELASTICSEARCH_TESTS=true"
+)
+class TestElasticsearchIntegration(unittest.TestCase):
+    """Integration test for Elasticsearch with CrewAI."""
+
+    def test_crew_with_elasticsearch_memory(self):
+        """Test a crew with Elasticsearch memory."""
+        researcher = Agent(
+            role="Researcher",
+            goal="Research a topic",
+            backstory="You are a researcher who loves to find information.",
+        )
+        
+        writer = Agent(
+            role="Writer",
+            goal="Write about a topic",
+            backstory="You are a writer who loves to write about topics.",
+        )
+        
+        research_task = Task(
+            description="Research about AI",
+            expected_output="Information about AI",
+            agent=researcher,
+        )
+        
+        write_task = Task(
+            description="Write about AI",
+            expected_output="Article about AI",
+            agent=writer,
+            context=[research_task],
+        )
+        
+        crew = Crew(
+            agents=[researcher, writer],
+            tasks=[research_task, write_task],
+            memory_config={"provider": "elasticsearch"},
+        )
+        
+        result = crew.kickoff()
+        
+        self.assertIsNotNone(result)
+        
+    def test_crew_with_elasticsearch_knowledge(self):
+        """Test a crew with Elasticsearch knowledge."""
+        content = "AI is a field of computer science that focuses on creating machines that can perform tasks that typically require human intelligence."
+        string_source = StringKnowledgeSource(
+            content=content, metadata={"topic": "AI"}
+        )
+        
+        knowledge = Knowledge(
+            collection_name="test",
+            sources=[string_source],
+            storage_provider="elasticsearch",
+        )
+        
+        agent = Agent(
+            role="AI Expert",
+            goal="Explain AI",
+            backstory="You are an AI expert who loves to explain AI concepts.",
+            knowledge=[knowledge],
+        )
+        
+        task = Task(
+            description="Explain what AI is",
+            expected_output="Explanation of AI",
+            agent=agent,
+        )
+        
+        crew = Crew(
+            agents=[agent],
+            tasks=[task],
+        )
+        
+        result = crew.kickoff()
+        
+        self.assertIsNotNone(result)

tests/knowledge/elasticsearch_knowledge_storage_test.py

@@ -0,0 +1,94 @@
+"""Test Elasticsearch knowledge storage functionality."""
+
+import os
+import unittest
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.knowledge.storage.elasticsearch_knowledge_storage import (
+    ElasticsearchKnowledgeStorage,
+)
+
+
+@pytest.mark.skipif(
+    os.environ.get("RUN_ELASTICSEARCH_TESTS") != "true",
+    reason="Elasticsearch tests require RUN_ELASTICSEARCH_TESTS=true"
+)
+class TestElasticsearchKnowledgeStorage(unittest.TestCase):
+    """Test Elasticsearch knowledge storage functionality."""
+
+    def setUp(self):
+        """Set up test fixtures."""
+        self.es_mock = MagicMock()
+        self.es_mock.indices.exists.return_value = False
+        
+        self.embedder_mock = MagicMock()
+        self.embedder_mock.embed_documents.return_value = [[0.1, 0.2, 0.3]]
+        
+        self.es_patcher = patch(
+            "crewai.knowledge.storage.elasticsearch_knowledge_storage.Elasticsearch",
+            return_value=self.es_mock
+        )
+        self.es_class_mock = self.es_patcher.start()
+        
+        self.storage = ElasticsearchKnowledgeStorage(
+            embedder_config=self.embedder_mock,
+            collection_name="test"
+        )
+        self.storage.initialize_knowledge_storage()
+        
+    def tearDown(self):
+        """Tear down test fixtures."""
+        self.es_patcher.stop()
+        
+    def test_initialization(self):
+        """Test initialization of Elasticsearch knowledge storage."""
+        self.es_class_mock.assert_called_once()
+        
+        self.es_mock.indices.create.assert_called_once()
+        
+    def test_save(self):
+        """Test saving to Elasticsearch knowledge storage."""
+        self.storage.save(["Test document 1", "Test document 2"], {"source": "test"})
+        
+        self.assertEqual(self.es_mock.index.call_count, 2)
+        
+        self.assertEqual(self.embedder_mock.embed_documents.call_count, 2)
+        
+    def test_search(self):
+        """Test searching in Elasticsearch knowledge storage."""
+        self.es_mock.search.return_value = {
+            "hits": {
+                "hits": [
+                    {
+                        "_id": "test_id",
+                        "_score": 1.5,  # Score between 1-2 (Elasticsearch range)
+                        "_source": {
+                            "text": "Test document",
+                            "metadata": {"source": "test"},
+                        }
+                    }
+                ]
+            }
+        }
+        
+        results = self.storage.search(["test query"])
+        
+        self.es_mock.search.assert_called_once()
+        
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]["id"], "test_id")
+        self.assertEqual(results[0]["context"], "Test document")
+        self.assertEqual(results[0]["metadata"], {"source": "test"})
+        self.assertEqual(results[0]["score"], 0.5)  # Adjusted to 0-1 range
+        
+    def test_reset(self):
+        """Test resetting Elasticsearch knowledge storage."""
+        self.es_mock.indices.exists.return_value = True
+        
+        self.storage.reset()
+        
+        self.es_mock.indices.delete.assert_called_once()
+        
+        self.assertEqual(self.es_mock.indices.create.call_count, 2)

tests/memory/elasticsearch_storage_test.py

@@ -0,0 +1,91 @@
+"""Test Elasticsearch storage functionality."""
+
+import os
+import unittest
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.memory.storage.elasticsearch_storage import ElasticsearchStorage
+
+
+@pytest.mark.skipif(
+    os.environ.get("RUN_ELASTICSEARCH_TESTS") != "true",
+    reason="Elasticsearch tests require RUN_ELASTICSEARCH_TESTS=true"
+)
+class TestElasticsearchStorage(unittest.TestCase):
+    """Test Elasticsearch storage functionality."""
+
+    def setUp(self):
+        """Set up test fixtures."""
+        self.es_mock = MagicMock()
+        self.es_mock.indices.exists.return_value = False
+        
+        self.embedder_mock = MagicMock()
+        self.embedder_mock.embed_documents.return_value = [[0.1, 0.2, 0.3]]
+        
+        self.es_patcher = patch(
+            "crewai.memory.storage.elasticsearch_storage.Elasticsearch",
+            return_value=self.es_mock
+        )
+        self.es_class_mock = self.es_patcher.start()
+        
+        self.storage = ElasticsearchStorage(
+            type="test",
+            embedder_config=self.embedder_mock
+        )
+        
+    def tearDown(self):
+        """Tear down test fixtures."""
+        self.es_patcher.stop()
+        
+    def test_initialization(self):
+        """Test initialization of Elasticsearch storage."""
+        self.es_class_mock.assert_called_once()
+        
+        self.es_mock.indices.create.assert_called_once()
+        
+    def test_save(self):
+        """Test saving to Elasticsearch storage."""
+        self.storage.save("Test document", {"source": "test"})
+        
+        self.es_mock.index.assert_called_once()
+        
+        self.embedder_mock.embed_documents.assert_called_once_with(["Test document"])
+        
+    def test_search(self):
+        """Test searching in Elasticsearch storage."""
+        self.es_mock.search.return_value = {
+            "hits": {
+                "hits": [
+                    {
+                        "_id": "test_id",
+                        "_score": 1.5,  # Score between 1-2 (Elasticsearch range)
+                        "_source": {
+                            "text": "Test document",
+                            "metadata": {"source": "test"},
+                        }
+                    }
+                ]
+            }
+        }
+        
+        results = self.storage.search("test query")
+        
+        self.es_mock.search.assert_called_once()
+        
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]["id"], "test_id")
+        self.assertEqual(results[0]["context"], "Test document")
+        self.assertEqual(results[0]["metadata"], {"source": "test"})
+        self.assertEqual(results[0]["score"], 0.5)  # Adjusted to 0-1 range
+        
+    def test_reset(self):
+        """Test resetting Elasticsearch storage."""
+        self.es_mock.indices.exists.return_value = True
+        
+        self.storage.reset()
+        
+        self.es_mock.indices.delete.assert_called_once()
+        
+        self.assertEqual(self.es_mock.indices.create.call_count, 2)

uv.lock

@@ -1,5 +1,4 @@
 version = 1
-revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
@@ -628,6 +627,7 @@ dependencies = [
     { name = "blinker" },
     { name = "chromadb" },
     { name = "click" },
+    { name = "elasticsearch" },
     { name = "instructor" },
     { name = "json-repair" },
     { name = "json5" },
@@ -710,6 +710,7 @@ requires-dist = [
     { name = "click", specifier = ">=8.1.7" },
     { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.40.1" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
+    { name = "elasticsearch", specifier = ">=9.0.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
@@ -735,7 +736,6 @@ requires-dist = [
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
 ]
-provides-extras = ["tools", "embeddings", "agentops", "fastembed", "pdfplumber", "pandas", "openpyxl", "mem0", "docling", "aisuite"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -1097,6 +1097,33 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/bb/84/4a2cab0e6adde6a85e7ba543862e5fc0250c51f3ac721a078a55cdcff250/easyocr-1.7.2-py3-none-any.whl", hash = "sha256:5be12f9b0e595d443c9c3d10b0542074b50f0ec2d98b141a109cd961fd1c177c", size = 2870178 },
 ]
 
+[[package]]
+name = "elastic-transport"
+version = "8.17.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6a/54/d498a766ac8fa475f931da85a154666cc81a70f8eb4a780bc8e4e934e9ac/elastic_transport-8.17.1.tar.gz", hash = "sha256:5edef32ac864dca8e2f0a613ef63491ee8d6b8cfb52881fa7313ba9290cac6d2", size = 73425 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cf/cd/b71d5bc74cde7fc6fd9b2ff9389890f45d9762cbbbf81dc5e51fd7588c4a/elastic_transport-8.17.1-py3-none-any.whl", hash = "sha256:192718f498f1d10c5e9aa8b9cf32aed405e469a7f0e9d6a8923431dbb2c59fb8", size = 64969 },
+]
+
+[[package]]
+name = "elasticsearch"
+version = "9.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "elastic-transport" },
+    { name = "python-dateutil" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/26/ad/d76e88811e68d7bdd976c0ff6027e7c3b544a949c8d3de052adc5765e1a6/elasticsearch-9.0.0.tar.gz", hash = "sha256:c075ccdc7d5697e2a842a88418efdb6cf6732d7a62c77a25d60184db23fd1464", size = 823636 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4b/b7/e85bdb8bed719dbf92780264d6c381186ced8eb7acc88bbe37a996f87b03/elasticsearch-9.0.0-py3-none-any.whl", hash = "sha256:295425172043e5db723d55cb3a5e28622696ca7739b466b812ab12ac938b6249", size = 895793 },
+]
+
 [[package]]
 name = "embedchain"
 version = "0.1.125"
@@ -2988,6 +3015,7 @@ name = "nvidia-nccl-cu12"
 version = "2.20.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/bb/d09dda47c881f9ff504afd6f9ca4f502ded6d8fc2f572cacc5e39da91c28/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01", size = 176238458 },
     { url = "https://files.pythonhosted.org/packages/4b/2a/0a131f572aa09f741c30ccd45a8e56316e8be8dfc7bc19bf0ab7cfef7b19/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56", size = 176249402 },
 ]
 
@@ -2997,6 +3025,7 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971 },
+    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338 },
 ]
 
 [[package]]