Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

docs: consolidate MongoDB documentation improvements (#8097)

Nora Reidyc0eda9f53889
diff --git a/docs/edge/ar/concepts/memory.mdx b/docs/edge/ar/concepts/memory.mdx
index 655b5957d..661c35fa1 100644
--- a/docs/edge/ar/concepts/memory.mdx
+++ b/docs/edge/ar/concepts/memory.mdx
@@ -758,7 +758,7 @@ memory = Memory(
## واجهة التخزين
- **الافتراضي**: LanceDB، مخزّن تحت `./.crewai/memory` (أو `$CREWAI_STORAGE_DIR/memory` إذا تم تعيين متغير البيئة، أو المسار الذي تمرره كـ `storage="path/to/dir"`).
-- **واجهة مخصصة**: نفّذ بروتوكول `StorageBackend` (انظر `crewai.memory.storage.backend`) ومرّر مثيلًا إلى `Memory(storage=your_backend)`.
+- **واجهة مخصصة**: نفّذ بروتوكول `StorageBackend` (انظر `crewai.memory.storage.backend`) ومرّر مثيلًا إلى `Memory(storage=your_backend)`. لعمليات النشر الإنتاجية، يمكنك استخدام `MongoDBStorageBackend` من حزمة `crewai-mongodb-memory`. لمعرفة المزيد، راجع [دليل تطبيق MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/agent-memory/).
## الاستكشاف
diff --git a/docs/edge/ar/concepts/tools.mdx b/docs/edge/ar/concepts/tools.mdx
index 2740f723d..f011fa7f7 100644
--- a/docs/edge/ar/concepts/tools.mdx
+++ b/docs/edge/ar/concepts/tools.mdx
@@ -144,6 +144,7 @@ crew.kickoff()
| **JSONSearchTool** | أداة RAG مصممة للبحث في ملفات JSON، تخدم التعامل مع البيانات المنظمة. |
| **LlamaIndexTool** | تُمكّن استخدام أدوات LlamaIndex. |
| **MDXSearchTool** | أداة RAG مخصصة للبحث في ملفات Markdown (MDX)، مفيدة للوثائق. |
+| **MongoDBVectorSearchTool** | أداة RAG لبحث التشابه المتجهي في مجموعات MongoDB Atlas، مع أدوات مساعدة اختيارية لإنشاء وإدارة فهارس البحث المتجهي. |
| **PDFSearchTool** | أداة RAG للبحث في مستندات PDF، مثالية لمعالجة المستندات الممسوحة ضوئيًا. |
| **PGSearchTool** | أداة RAG محسّنة للبحث في قواعد بيانات PostgreSQL، مناسبة لاستعلامات قواعد البيانات. |
| **Vision Tool** | أداة لإنشاء الصور باستخدام DALL-E API. |
diff --git a/docs/edge/ar/tools/database-data/mongodbvectorsearchtool.mdx b/docs/edge/ar/tools/database-data/mongodbvectorsearchtool.mdx
index cbff43b11..fcd15f3d6 100644
--- a/docs/edge/ar/tools/database-data/mongodbvectorsearchtool.mdx
+++ b/docs/edge/ar/tools/database-data/mongodbvectorsearchtool.mdx
@@ -9,10 +9,14 @@ mode: "wide"
## الوصف
-تنفيذ استعلامات التشابه المتجهي على مجموعات MongoDB Atlas. تدعم أدوات مساعدة لإنشاء الفهارس وإدراج النصوص المضمنة بكميات كبيرة.
+تُمكّن `MongoDBVectorSearchTool` من إجراء استعلامات التشابه المتجهي على مجموعات MongoDB Atlas. يدعم
+MongoDB Atlas البحث المتجهي الأصلي. كما تدعم الأداة أدوات مساعدة لإنشاء الفهارس وإدراج النصوص المضمنة بكميات كبيرة.
-يدعم MongoDB Atlas البحث المتجهي الأصلي. اعرف المزيد:
-https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
+يُعد البحث المتجهي في MongoDB مفيدًا للتطبيقات التي تريد استخدام قاعدة بيانات بحث متجهي للاستعلام عن البيانات
+باستخدام البحث الدلالي، أو تصفية الاستعلامات حسب حقول أخرى في مجموعتك، أو تشغيل تطبيقات الذكاء الاصطناعي
+وأنظمة الوكلاء الخاصة بك من خلال تنفيذ التوليد المعزز بالاسترجاع (RAG).
+
+اعرف المزيد: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
## التثبيت
@@ -28,24 +32,31 @@ pip install crewai-tools[mongodb]
uv add crewai-tools --extra mongodb
```
-## المعاملات
-
-### التهيئة
+## معاملات التهيئة
-- `connection_string` (str, مطلوب)
-- `database_name` (str, مطلوب)
-- `collection_name` (str, مطلوب)
-- `vector_index_name` (str, الافتراضي `vector_index`)
-- `text_key` (str, الافتراضي `text`)
-- `embedding_key` (str, الافتراضي `embedding`)
-- `dimensions` (int, الافتراضي `1536`)
+- `connection_string` (str): مطلوب. بيانات اعتماد سلسلة الاتصال بـ MongoDB Atlas للاتصال بمجموعتك (cluster).
+- `database_name` (str): مطلوب. اسم قاعدة بيانات MongoDB المراد استخدامها.
+- `collection_name` (str): مطلوب. المجموعة ضمن قاعدة البيانات حيث تُخزَّن المستندات والتضمينات (embeddings).
+- `vector_index_name` (str، الافتراضي: `vector_index`): اختياري. اسم فهرس البحث المتجهي في MongoDB المراد
+ الاستعلام عنه (يجب أن يطابق الفهرس الذي تم إنشاؤه في Atlas).
+- `text_key` (str، الافتراضي: `text`): اختياري. اسم حقل المستند الذي يُخزَّن فيه النص الخام.
+- `embedding_key` (str، الافتراضي: `embedding`): اختياري. اسم حقل المستند الذي يُخزَّن فيه التضمين المتجهي.
+- `dimensions` (int، الافتراضي: `1536`): اختياري. عدد أبعاد نموذج التضمين (يجب أن يطابق نموذجك).
+- `query_config` (MongoDBVectorSearchConfig): اختياري. كائن `MongoDBVectorSearchConfig` لإعدادات الاستعلام
+ المتقدمة، مثل `limit` و `oversampling_factor`.
-### معاملات التشغيل
+## طرق MongoDBVectorSearchTool
-- `query` (str, مطلوب): استعلام بلغة طبيعية لتضمينه والبحث عنه.
+- `run(query=...)`: يُضمّن استعلامًا وينفّذ بحث تشابه متجهي، ويُعيد المستندات المطابقة. يأخذ معامل
+ `query` (`str`) بلغة طبيعية لتضمينه والبحث عنه.
+- `add_texts(list of strings)`: يأخذ قائمة من النصوص لتضمينها وإدراجها كمستندات في قاعدة بيانات MongoDB Atlas الخاصة بك.
+- `create_vector_search_index(dimensions=...)`: يُنشئ فهرس بحث متجهي في MongoDB بالأبعاد والتشابه الصحيحين.
+ يأخذ معامل `dimensions` (int).
## بداية سريعة
+يوضح المثال التالي كيفية تهيئة الأداة وتنفيذ بحث تشابه متجهي على مجموعة MongoDB Atlas المحددة:
+
```python Code
from crewai_tools import MongoDBVectorSearchTool
@@ -58,31 +69,48 @@ tool = MongoDBVectorSearchTool(
print(tool.run(query="how to create vector index"))
```
-## أدوات مساعدة لإنشاء الفهارس
-
-استخدم `create_vector_search_index(...)` لإنشاء فهرس بحث متجهي في Atlas بالأبعاد والتشابه الصحيحين.
-
## المشكلات الشائعة
- فشل المصادقة: تأكد من أن قائمة الوصول إلى عناوين IP في Atlas تسمح بخادمك وأن سلسلة الاتصال تتضمن بيانات الاعتماد.
- الفهرس غير موجود: أنشئ الفهرس المتجهي أولاً؛ يجب أن يتطابق الاسم مع `vector_index_name`.
- عدم تطابق الأبعاد: قم بمحاذاة أبعاد نموذج التضمين مع `dimensions`.
-## أمثلة إضافية
+## أمثلة
+
+### تحميل قاعدة البيانات مسبقًا وإنشاء الفهرس
-### التهيئة الأساسية
+يوضح المثال التالي كيفية تحميل قاعدة بيانات MongoDB Atlas الخاصة بك مسبقًا بالمستندات
+وإنشاء فهرس بحث متجهي في MongoDB للاستعلام عن مجموعتك:
```python Code
+import os
from crewai_tools import MongoDBVectorSearchTool
tool = MongoDBVectorSearchTool(
database_name="example_database",
collection_name="example_collection",
connection_string="<your_mongodb_connection_string>",
+ dimensions=3072,
)
+
+# Load text content from a local folder and add to your MongoDB collection
+texts = []
+for fname in os.listdir("knowledge"):
+ path = os.path.join("knowledge", fname)
+ if os.path.isfile(path):
+ with open(path, "r", encoding="utf-8") as f:
+ texts.append(f.read())
+
+tool.add_texts(texts)
+
+# Create the MongoDB Vector Search index (e.g., 3072 dims for text-embedding-3-large)
+tool.create_vector_search_index(dimensions=3072)
```
-### تكوين استعلام مخصص
+### تكوين استعلام مخصص وتكامل مع الوكيل
+
+يوضح المثال التالي كيفية توفير تكوين استعلام مخصص لـ `MongoDBVectorSearchTool`
+ودمجها مع وكيل CrewAI:
```python Code
from crewai_tools import MongoDBVectorSearchConfig, MongoDBVectorSearchTool
@@ -105,33 +133,10 @@ rag_agent = Agent(
)
```
-### تحميل قاعدة البيانات مسبقاً وإنشاء الفهرس
+### تشغيل سير عمل CrewAI
-```python Code
-import os
-from crewai_tools import MongoDBVectorSearchTool
-
-tool = MongoDBVectorSearchTool(
- database_name="example_database",
- collection_name="example_collection",
- connection_string="<your_mongodb_connection_string>",
-)
-
-# Load text content from a local folder and add to MongoDB
-texts = []
-for fname in os.listdir("knowledge"):
- path = os.path.join("knowledge", fname)
- if os.path.isfile(path):
- with open(path, "r", encoding="utf-8") as f:
- texts.append(f.read())
-
-tool.add_texts(texts)
-
-# Create the Atlas Vector Search index (e.g., 3072 dims for text-embedding-3-large)
-tool.create_vector_search_index(dimensions=3072)
-```
-
-## مثال
+يوضح المثال التالي كيفية دمج `MongoDBVectorSearchTool` مع Agent و Task و Crew
+لإنشاء وتشغيل سير عمل RAG قائم على الوكلاء في CrewAI:
```python Code
from crewai import Agent, Task, Crew
@@ -165,3 +170,9 @@ crew = Crew(
result = crew.kickoff()
```
+
+## لمعرفة المزيد
+
+لمعرفة المزيد حول تكاملات CrewAI مع MongoDB، راجع أدلة MongoDB التالية:
+- [دمج MongoDB مع CrewAI](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/)
+- [بناء تطبيق RAG قائم على الوكلاء باستخدام CrewAI و MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/build-agents/)
diff --git a/docs/edge/ar/tools/database-data/overview.mdx b/docs/edge/ar/tools/database-data/overview.mdx
index f4824f515..72bd7eb93 100644
--- a/docs/edge/ar/tools/database-data/overview.mdx
+++ b/docs/edge/ar/tools/database-data/overview.mdx
@@ -51,17 +51,22 @@ mode: "wide"
- **التحليلات الفورية**: الوصول إلى البيانات الحية لاتخاذ القرارات
```python
-from crewai_tools import MySQLTool, QdrantVectorSearchTool, NL2SQLTool
+from crewai_tools import MySQLTool, MongoDBVectorSearchTool, QdrantVectorSearchTool, NL2SQLTool
# Create database tools
mysql_db = MySQLTool()
-vector_search = QdrantVectorSearchTool()
+mongodb_vector_search = MongoDBVectorSearchTool(
+ connection_string="<MONGODB_URI>",
+ database_name="<database>",
+ collection_name="<collection>",
+)
+qdrant_vector_search = QdrantVectorSearchTool()
nl_to_sql = NL2SQLTool()
# Add to your agent
agent = Agent(
role="Data Analyst",
- tools=[mysql_db, vector_search, nl_to_sql],
+ tools=[mysql_db, mongodb_vector_search, qdrant_vector_search, nl_to_sql],
goal="Extract insights from various data sources"
)
```
diff --git a/docs/edge/ar/tools/overview.mdx b/docs/edge/ar/tools/overview.mdx
index 0a20c720d..b8e84c618 100644
--- a/docs/edge/ar/tools/overview.mdx
+++ b/docs/edge/ar/tools/overview.mdx
@@ -43,7 +43,7 @@ mode: "wide"
href="/ar/tools/database-data/overview"
color="#8B5CF6"
>
- الاتصال بقواعد بيانات SQL ومخازن المتجهات ومستودعات البيانات. الاستعلام عن MySQL و PostgreSQL و Snowflake و Qdrant و Weaviate.
+ الاتصال بقواعد البيانات ومخازن المتجهات ومستودعات البيانات. الاستعلام عن MySQL و PostgreSQL و MongoDB و Snowflake و Qdrant و Weaviate.
</Card>
<Card
@@ -87,7 +87,7 @@ mode: "wide"
هل تحتاج إلى أداة محددة؟ إليك بعض الخيارات الشائعة:
-<CardGroup cols={3}>
+<CardGroup cols={2}>
<Card title="أداة RAG" icon="image" href="/ar/tools/ai-ml/ragtool">
تنفيذ الاسترجاع المعزز بالتوليد
</Card>
@@ -97,6 +97,9 @@ mode: "wide"
<Card title="قراءة الملفات" icon="file" href="/ar/tools/file-document/filereadtool">
قراءة أي نوع ملف
</Card>
+ <Card title="قراءة الأدلة" icon="folder-open" href="/ar/tools/file-document/directoryreadtool">
+ سرد وقراءة محتويات الأدلة
+ </Card>
<Card title="استخراج الموقع" icon="globe" href="/ar/tools/web-scraping/scrapewebsitetool">
استخراج محتوى الويب
</Card>
@@ -106,6 +109,9 @@ mode: "wide"
<Card title="قارئ S3" icon="cloud" href="/ar/tools/cloud-storage/s3readertool">
الوصول إلى ملفات AWS S3
</Card>
+ <Card title="بحث متجهي MongoDB" icon="database" href="/ar/tools/database-data/mongodbvectorsearchtool">
+ إجراء استعلامات بحث تشابه متجهي على MongoDB
+ </Card>
</CardGroup>
## **البدء**
diff --git a/docs/edge/en/concepts/memory.mdx b/docs/edge/en/concepts/memory.mdx
index d23b47842..8ec4d11c6 100644
--- a/docs/edge/en/concepts/memory.mdx
+++ b/docs/edge/en/concepts/memory.mdx
@@ -762,7 +762,7 @@ memory = Memory(
## Storage Backend
- **Default**: LanceDB, stored under `./.crewai/memory` (or `$CREWAI_STORAGE_DIR/memory` if the env var is set, or the path you pass as `storage="path/to/dir"`).
-- **Custom backend**: Implement the `StorageBackend` protocol (see `crewai.memory.storage.backend`) and pass an instance to `Memory(storage=your_backend)`.
+- **Custom backend**: Implement the `StorageBackend` protocol (see `crewai.memory.storage.backend`) and pass an instance to `Memory(storage=your_backend)`. For production deployments, you can use `MongoDBStorageBackend` from the `crewai-mongodb-memory` package. To learn more, see the [MongoDB implementation tutorial](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/agent-memory/).
## Discovery
diff --git a/docs/edge/en/concepts/tools.mdx b/docs/edge/en/concepts/tools.mdx
index e78c4aa44..30e327fa5 100644
--- a/docs/edge/en/concepts/tools.mdx
+++ b/docs/edge/en/concepts/tools.mdx
@@ -145,6 +145,7 @@ Here is a list of the available tools and their descriptions:
| **JSONSearchTool** | A RAG tool designed for searching within JSON files, catering to structured data handling. |
| **LlamaIndexTool** | Enables the use of LlamaIndex tools. |
| **MDXSearchTool** | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation. |
+| **MongoDBVectorSearchTool** | A RAG tool for vector similarity search on MongoDB Atlas collections, with optional helpers to create and manage vector search indexes. |
| **PDFSearchTool** | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents. |
| **PGSearchTool** | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
| **Vision Tool** | A tool for generating images using the DALL-E API. |
diff --git a/docs/edge/en/tools/database-data/mongodbvectorsearchtool.mdx b/docs/edge/en/tools/database-data/mongodbvectorsearchtool.mdx
index 09c5ee518..fbf4b2a3e 100644
--- a/docs/edge/en/tools/database-data/mongodbvectorsearchtool.mdx
+++ b/docs/edge/en/tools/database-data/mongodbvectorsearchtool.mdx
@@ -9,10 +9,14 @@ mode: "wide"
## Description
-Perform vector similarity queries on MongoDB Atlas collections. Supports index creation helpers and bulk insert of embedded texts.
+The `MongoDBVectorSearchTool` enables vector similarity queries on MongoDB Atlas collections. MongoDB Atlas
+supports native vector search. The tool also supports index creation helpers and bulk insert of embedded texts.
-MongoDB Atlas supports native vector search. Learn more:
-https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
+MongoDB Vector Search is useful for applications that want to use a vector search database to query data
+with semantic search, filter queries on other fields in your collection, or power your
+AI applications and agentic systems by implementing retrieval-augmented generation (RAG).
+
+Learn more: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
## Installation
@@ -28,24 +32,31 @@ or
uv add crewai-tools --extra mongodb
```
-## Parameters
-
-### Initialization
+## Initialization Parameters
-- `connection_string` (str, required)
-- `database_name` (str, required)
-- `collection_name` (str, required)
-- `vector_index_name` (str, default `vector_index`)
-- `text_key` (str, default `text`)
-- `embedding_key` (str, default `embedding`)
-- `dimensions` (int, default `1536`)
+- `connection_string` (str): Required. MongoDB Atlas connection string credentials to connect to your cluster.
+- `database_name` (str): Required. The name of the MongoDB database to use.
+- `collection_name` (str): Required. The collection within the database where documents and embeddings are stored.
+- `vector_index_name` (str, default: `vector_index`): Optional. The name of the MongoDB Vector Search index to query (must match the index
+ created in Atlas).
+- `text_key` (str, default: `text`): Optional. The document field name where raw text is stored.
+- `embedding_key` (str, default: `embedding`): Optional. The document field name where the vector embedding is stored.
+- `dimensions` (int, default: `1536`): Optional. The number of dimensions for the embedding model (must match your model).
+- `query_config` (MongoDBVectorSearchConfig): Optional. A `MongoDBVectorSearchConfig` object for advanced query settings, like `limit` and `oversampling_factor`.
-### Run Parameters
+## MongoDBVectorSearchTool Methods
-- `query` (str, required): Natural language query to embed and search.
+- `run(query=...)`: Embeds a query and performs vector similarity search, returning matching documents.
+ Takes a natural language `query` (`str`) parameter to embed and search.
+- `add_texts(list of strings)`: Takes a list of strings to embed and insert as documents into your MongoDB Atlas database.
+- `create_vector_search_index(dimensions=...)`: Provisions a MongoDB Vector Search index with the correct dimensions
+ and similarity. Takes a `dimensions` (int) parameter.
## Quick start
+The following example demonstrates how to initialize the tool and execute a vector similarity search against the
+specified MongoDB Atlas collection:
+
```python Code
from crewai_tools import MongoDBVectorSearchTool
@@ -58,31 +69,48 @@ tool = MongoDBVectorSearchTool(
print(tool.run(query="how to create vector index"))
```
-## Index creation helpers
-
-Use `create_vector_search_index(...)` to provision an Atlas Vector Search index with the correct dimensions and similarity.
-
## Common issues
- Authentication failures: ensure your Atlas IP Access List allows your runner and the connection string includes credentials.
- Index not found: create the vector index first; name must match `vector_index_name`.
- Dimensions mismatch: align embedding model dimensions with `dimensions`.
-## More examples
+## Examples
+
+### Preload the database and create the index
-### Basic initialization
+The following example demonstrates how to preload your MongoDB Atlas database with documents
+and create a MongoDB Vector Search index to query your collection:
```python Code
+import os
from crewai_tools import MongoDBVectorSearchTool
tool = MongoDBVectorSearchTool(
database_name="example_database",
collection_name="example_collection",
connection_string="<your_mongodb_connection_string>",
+ dimensions=3072,
)
+
+# Load text content from a local folder and add to your MongoDB collection
+texts = []
+for fname in os.listdir("knowledge"):
+ path = os.path.join("knowledge", fname)
+ if os.path.isfile(path):
+ with open(path, "r", encoding="utf-8") as f:
+ texts.append(f.read())
+
+tool.add_texts(texts)
+
+# Create the MongoDB Vector Search index (e.g., 3072 dims for text-embedding-3-large)
+tool.create_vector_search_index(dimensions=3072)
```
-### Custom query configuration
+### Custom query configuration and agent configuration
+
+The following example demonstrates how to provide a custom query configuration to the `MongoDBVectorSearchTool`
+and integrate with a CrewAI agent:
```python Code
from crewai_tools import MongoDBVectorSearchConfig, MongoDBVectorSearchTool
@@ -105,33 +133,10 @@ rag_agent = Agent(
)
```
-### Preloading the database and creating the index
-
-```python Code
-import os
-from crewai_tools import MongoDBVectorSearchTool
-
-tool = MongoDBVectorSearchTool(
- database_name="example_database",
- collection_name="example_collection",
- connection_string="<your_mongodb_connection_string>",
-)
-
-# Load text content from a local folder and add to MongoDB
-texts = []
-for fname in os.listdir("knowledge"):
- path = os.path.join("knowledge", fname)
- if os.path.isfile(path):
- with open(path, "r", encoding="utf-8") as f:
- texts.append(f.read())
-
-tool.add_texts(texts)
-
-# Create the Atlas Vector Search index (e.g., 3072 dims for text-embedding-3-large)
-tool.create_vector_search_index(dimensions=3072)
-```
+### Run a CrewAI workflow
-## Example
+The following example demonstrates how to integrate your `MongoDBVectorSearchTool` with an Agent, Task, and
+Crew to create and run a CrewAI agentic RAG workflow:
```python Code
from crewai import Agent, Task, Crew
@@ -166,4 +171,8 @@ crew = Crew(
result = crew.kickoff()
```
+## Learn More
+To learn more about CrewAI integrations with MongoDB, see the following MongoDB guides:
+- [Integrate MongoDB with CrewAI](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/)
+- [Build an Agentic RAG Application with CrewAI and MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/build-agents/)
diff --git a/docs/edge/en/tools/database-data/overview.mdx b/docs/edge/en/tools/database-data/overview.mdx
index 19c14ed3c..fddcb8fde 100644
--- a/docs/edge/en/tools/database-data/overview.mdx
+++ b/docs/edge/en/tools/database-data/overview.mdx
@@ -51,16 +51,21 @@ These tools enable your agents to interact with various database systems, from t
- **Real-time Analytics**: Access live data for decision making
```python
-from crewai_tools import MySQLTool, QdrantVectorSearchTool, NL2SQLTool
+from crewai_tools import MySQLTool, MongoDBVectorSearchTool, QdrantVectorSearchTool, NL2SQLTool
# Create database tools
mysql_db = MySQLTool()
-vector_search = QdrantVectorSearchTool()
+mongodb_vector_search = MongoDBVectorSearchTool(
+ connection_string="<MONGODB_URI>",
+ database_name="<database>",
+ collection_name="<collection>",
+)
+qdrant_vector_search = QdrantVectorSearchTool()
nl_to_sql = NL2SQLTool()
# Add to your agent
agent = Agent(
role="Data Analyst",
- tools=[mysql_db, vector_search, nl_to_sql],
+ tools=[mysql_db, mongodb_vector_search, qdrant_vector_search, nl_to_sql],
goal="Extract insights from various data sources"
)
diff --git a/docs/edge/en/tools/overview.mdx b/docs/edge/en/tools/overview.mdx
index fb9926f0b..77e3090b0 100644
--- a/docs/edge/en/tools/overview.mdx
+++ b/docs/edge/en/tools/overview.mdx
@@ -43,7 +43,7 @@ CrewAI provides an extensive library of pre-built tools to enhance your agents'
href="/en/tools/database-data/overview"
color="#8B5CF6"
>
- Connect to SQL databases, vector stores, and data warehouses. Query MySQL, PostgreSQL, Snowflake, Qdrant, and Weaviate.
+ Connect to databases, vector stores, and data warehouses. Query MySQL, PostgreSQL, MongoDB, Snowflake, Qdrant, and Weaviate.
</Card>
<Card
@@ -87,7 +87,7 @@ CrewAI provides an extensive library of pre-built tools to enhance your agents'
Need a specific tool? Here are some popular choices:
-<CardGroup cols={3}>
+<CardGroup cols={2}>
<Card title="RAG Tool" icon="image" href="/en/tools/ai-ml/ragtool">
Implement Retrieval-Augmented Generation
</Card>
@@ -97,6 +97,9 @@ Need a specific tool? Here are some popular choices:
<Card title="File Read" icon="file" href="/en/tools/file-document/filereadtool">
Read any file type
</Card>
+ <Card title="Directory Read" icon="folder-open" href="/en/tools/file-document/directoryreadtool">
+ List and read directory contents
+ </Card>
<Card title="Scrape Website" icon="globe" href="/en/tools/web-scraping/scrapewebsitetool">
Extract web content
</Card>
@@ -106,6 +109,9 @@ Need a specific tool? Here are some popular choices:
<Card title="S3 Reader" icon="cloud" href="/en/tools/cloud-storage/s3readertool">
Access AWS S3 files
</Card>
+ <Card title="MongoDB Vector Search" icon="database" href="/en/tools/database-data/mongodbvectorsearchtool">
+ Run vector similarity queries on MongoDB
+ </Card>
</CardGroup>
## **Getting Started**
diff --git a/docs/edge/ko/concepts/memory.mdx b/docs/edge/ko/concepts/memory.mdx
index d6b3d5f61..e9ca192ce 100644
--- a/docs/edge/ko/concepts/memory.mdx
+++ b/docs/edge/ko/concepts/memory.mdx
@@ -758,7 +758,7 @@ memory = Memory(
## 스토리지 백엔드
- **기본값**: LanceDB, `./.crewai/memory` 아래에 저장 (또는 환경 변수가 설정된 경우 `$CREWAI_STORAGE_DIR/memory`, 또는 `storage="path/to/dir"`로 전달한 경로).
-- **사용자 정의 백엔드**: `StorageBackend` 프로토콜을 구현하고(`crewai.memory.storage.backend` 참조) `Memory(storage=your_backend)`에 인스턴스를 전달합니다.
+- **사용자 정의 백엔드**: `StorageBackend` 프로토콜을 구현하고(`crewai.memory.storage.backend` 참조) `Memory(storage=your_backend)`에 인스턴스를 전달합니다. 프로덕션 배포의 경우 `crewai-mongodb-memory` 패키지의 `MongoDBStorageBackend`를 사용할 수 있습니다. 자세한 내용은 [MongoDB 구현 튜토리얼](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/agent-memory/)을 참고하세요.
## 탐색(Discovery)
diff --git a/docs/edge/ko/concepts/tools.mdx b/docs/edge/ko/concepts/tools.mdx
index cd0e96173..4395056c4 100644
--- a/docs/edge/ko/concepts/tools.mdx
+++ b/docs/edge/ko/concepts/tools.mdx
@@ -143,6 +143,7 @@ crew.kickoff()
| **JSONSearchTool** | JSON 파일 내에서 검색하도록 설계된 RAG 도구로, 구조화된 데이터 처리에 적합합니다. |
| **LlamaIndexTool** | LlamaIndex 도구의 사용을 가능하게 합니다. |
| **MDXSearchTool** | 마크다운(MDX) 파일 내에서 검색하도록 맞춤화된 RAG 도구로, 문서화에 유용합니다. |
+| **MongoDBVectorSearchTool** | MongoDB Atlas 컬렉션에서 벡터 유사도 검색을 수행하는 RAG 도구로, 벡터 검색 인덱스를 생성하고 관리하는 선택적 헬퍼를 제공합니다. |
| **PDFSearchTool** | PDF 문서 내에서 검색하는 RAG 도구로, 스캔된 문서를 처리하기에 이상적입니다. |
| **PGSearchTool** | PostgreSQL 데이터베이스 내에서 검색하는 데 최적화된 RAG 도구로, 데이터베이스 쿼리에 적합합니다. |
| **Vision Tool** | DALL-E API를 사용해 이미지를 생성하는 도구입니다. |
diff --git a/docs/edge/ko/tools/database-data/mongodbvectorsearchtool.mdx b/docs/edge/ko/tools/database-data/mongodbvectorsearchtool.mdx
index d979ddc7b..2ddc0242a 100644
--- a/docs/edge/ko/tools/database-data/mongodbvectorsearchtool.mdx
+++ b/docs/edge/ko/tools/database-data/mongodbvectorsearchtool.mdx
@@ -9,10 +9,14 @@ mode: "wide"
## 설명
-MongoDB Atlas 컬렉션에서 벡터 유사성 쿼리를 수행합니다. 인덱스 생성 도우미 및 임베디드 텍스트의 일괄 삽입을 지원합니다.
+`MongoDBVectorSearchTool`은 MongoDB Atlas 컬렉션에서 벡터 유사도 쿼리를 수행할 수 있게 해줍니다. MongoDB Atlas는
+네이티브 벡터 검색을 지원합니다. 이 도구는 또한 인덱스 생성 도우미와 임베딩된 텍스트의 일괄 삽입을 지원합니다.
-MongoDB Atlas는 네이티브 벡터 검색을 지원합니다. 자세히 알아보기:
-https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
+MongoDB Vector Search는 시맨틱 검색으로 데이터를 쿼리하거나, 컬렉션 내 다른 필드에 대한 필터 쿼리를 수행하거나,
+검색 증강 생성(retrieval-augmented generation, RAG)을 구현하여 AI 애플리케이션과 에이전트 시스템을 강화하려는
+애플리케이션에 유용합니다.
+
+더 알아보기: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
## 설치
@@ -28,24 +32,31 @@ pip install crewai-tools[mongodb]
uv add crewai-tools --extra mongodb
```
-## 파라미터
-
-### 초기화
+## 초기화 매개변수
-- `connection_string` (str, 필수)
-- `database_name` (str, 필수)
-- `collection_name` (str, 필수)
-- `vector_index_name` (str, 기본값 `vector_index`)
-- `text_key` (str, 기본값 `text`)
-- `embedding_key` (str, 기본값 `embedding`)
-- `dimensions` (int, 기본값 `1536`)
+- `connection_string` (str): 필수. 클러스터에 연결하기 위한 MongoDB Atlas 연결 문자열 자격 증명입니다.
+- `database_name` (str): 필수. 사용할 MongoDB 데이터베이스의 이름입니다.
+- `collection_name` (str): 필수. 문서와 임베딩이 저장되는 데이터베이스 내 컬렉션입니다.
+- `vector_index_name` (str, 기본값: `vector_index`): 선택. 쿼리할 MongoDB Vector Search 인덱스의 이름입니다(Atlas에서
+ 생성한 인덱스와 일치해야 합니다).
+- `text_key` (str, 기본값: `text`): 선택. 원본 텍스트가 저장되는 문서 필드명입니다.
+- `embedding_key` (str, 기본값: `embedding`): 선택. 벡터 임베딩이 저장되는 문서 필드명입니다.
+- `dimensions` (int, 기본값: `1536`): 선택. 임베딩 모델의 차원 수입니다(사용하는 모델과 일치해야 합니다).
+- `query_config` (MongoDBVectorSearchConfig): 선택. `limit`, `oversampling_factor` 등 고급 쿼리 설정을 위한
+ `MongoDBVectorSearchConfig` 객체입니다.
-### 실행 매개변수
+## MongoDBVectorSearchTool 메서드
-- `query` (str, 필수): 임베드 및 검색할 자연어 쿼리.
+- `run(query=...)`: 쿼리를 임베딩하고 벡터 유사도 검색을 수행하여 일치하는 문서를 반환합니다.
+ 임베딩하고 검색할 자연어 `query` (`str`) 매개변수를 받습니다.
+- `add_texts(list of strings)`: 임베딩하여 MongoDB Atlas 데이터베이스에 문서로 삽입할 문자열 목록을 받습니다.
+- `create_vector_search_index(dimensions=...)`: 올바른 차원과 유사도를 가진 MongoDB Vector Search 인덱스를
+ 프로비저닝합니다. `dimensions` (int) 매개변수를 받습니다.
## 빠른 시작
+다음 예시는 도구를 초기화하고 지정된 MongoDB Atlas 컬렉션에 대해 벡터 유사도 검색을 실행하는 방법을 보여줍니다:
+
```python Code
from crewai_tools import MongoDBVectorSearchTool
@@ -58,31 +69,48 @@ tool = MongoDBVectorSearchTool(
print(tool.run(query="how to create vector index"))
```
-## 인덱스 생성 도우미
-
-`create_vector_search_index(...)`를 사용하여 올바른 차원과 유사성을 가진 Atlas Vector Search 인덱스를 프로비저닝하세요.
-
## 일반적인 문제
- 인증 실패: Atlas IP 액세스 목록에 러너가 허용되어 있는지 확인하고, 연결 문자열에 자격 증명이 포함되어 있는지 확인하세요.
- 인덱스를 찾을 수 없음: 벡터 인덱스를 먼저 생성하세요; 이름이 `vector_index_name`과 일치해야 합니다.
- 차원 불일치: 임베딩 모델의 차원을 `dimensions`와 일치시켜야 합니다.
-## 추가 예시
+## 예시
+
+### 데이터베이스 미리 로드 및 인덱스 생성
-### 기본 초기화
+다음 예시는 MongoDB Atlas 데이터베이스에 문서를 미리 로드하고 컬렉션을 쿼리하기 위한 MongoDB Vector Search
+인덱스를 생성하는 방법을 보여줍니다:
```python Code
+import os
from crewai_tools import MongoDBVectorSearchTool
tool = MongoDBVectorSearchTool(
database_name="example_database",
collection_name="example_collection",
connection_string="<your_mongodb_connection_string>",
+ dimensions=3072,
)
+
+# Load text content from a local folder and add to your MongoDB collection
+texts = []
+for fname in os.listdir("knowledge"):
+ path = os.path.join("knowledge", fname)
+ if os.path.isfile(path):
+ with open(path, "r", encoding="utf-8") as f:
+ texts.append(f.read())
+
+tool.add_texts(texts)
+
+# Create the MongoDB Vector Search index (e.g., 3072 dims for text-embedding-3-large)
+tool.create_vector_search_index(dimensions=3072)
```
-### 사용자 지정 쿼리 구성
+### 사용자 지정 쿼리 구성 및 에이전트 구성
+
+다음 예시는 `MongoDBVectorSearchTool`에 사용자 지정 쿼리 구성을 제공하고 CrewAI 에이전트와 통합하는 방법을
+보여줍니다:
```python Code
from crewai_tools import MongoDBVectorSearchConfig, MongoDBVectorSearchTool
@@ -105,33 +133,10 @@ rag_agent = Agent(
)
```
-### 데이터베이스 미리 로드 및 인덱스 생성
+### CrewAI 워크플로우 실행
-```python Code
-import os
-from crewai_tools import MongoDBVectorSearchTool
-
-tool = MongoDBVectorSearchTool(
- database_name="example_database",
- collection_name="example_collection",
- connection_string="<your_mongodb_connection_string>",
-)
-
-# Load text content from a local folder and add to MongoDB
-texts = []
-for fname in os.listdir("knowledge"):
- path = os.path.join("knowledge", fname)
- if os.path.isfile(path):
- with open(path, "r", encoding="utf-8") as f:
- texts.append(f.read())
-
-tool.add_texts(texts)
-
-# Create the Atlas Vector Search index (e.g., 3072 dims for text-embedding-3-large)
-tool.create_vector_search_index(dimensions=3072)
-```
-
-## 예시
+다음 예시는 `MongoDBVectorSearchTool`을 Agent, Task, Crew와 통합하여 CrewAI 에이전틱 RAG 워크플로우를
+생성하고 실행하는 방법을 보여줍니다:
```python Code
from crewai import Agent, Task, Crew
@@ -158,10 +163,16 @@ task = Task(
)
crew = Crew(
- agents=[agent],
+ agents=[agent],
tasks=[task],
verbose=True,
)
result = crew.kickoff()
```
+
+## 더 알아보기
+
+CrewAI와 MongoDB 통합에 대해 더 알아보려면 다음 MongoDB 가이드를 참고하세요:
+- [MongoDB와 CrewAI 통합하기](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/)
+- [CrewAI와 MongoDB로 에이전틱 RAG 애플리케이션 구축하기](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/build-agents/)
diff --git a/docs/edge/ko/tools/database-data/overview.mdx b/docs/edge/ko/tools/database-data/overview.mdx
index 6c4fbb5a5..2e850d67a 100644
--- a/docs/edge/ko/tools/database-data/overview.mdx
+++ b/docs/edge/ko/tools/database-data/overview.mdx
@@ -51,17 +51,22 @@ mode: "wide"
- **실시간 분석**: 의사 결정에 필요한 실시간 데이터 접근
```python
-from crewai_tools import MySQLTool, QdrantVectorSearchTool, NL2SQLTool
+from crewai_tools import MySQLTool, MongoDBVectorSearchTool, QdrantVectorSearchTool, NL2SQLTool
# Create database tools
mysql_db = MySQLTool()
-vector_search = QdrantVectorSearchTool()
+mongodb_vector_search = MongoDBVectorSearchTool(
+ connection_string="<MONGODB_URI>",
+ database_name="<database>",
+ collection_name="<collection>",
+)
+qdrant_vector_search = QdrantVectorSearchTool()
nl_to_sql = NL2SQLTool()
# Add to your agent
agent = Agent(
role="Data Analyst",
- tools=[mysql_db, vector_search, nl_to_sql],
+ tools=[mysql_db, mongodb_vector_search, qdrant_vector_search, nl_to_sql],
goal="Extract insights from various data sources"
)
```
\ No newline at end of file
diff --git a/docs/edge/ko/tools/overview.mdx b/docs/edge/ko/tools/overview.mdx
index f4f11e98d..ed1755a17 100644
--- a/docs/edge/ko/tools/overview.mdx
+++ b/docs/edge/ko/tools/overview.mdx
@@ -43,7 +43,7 @@ CrewAI는 에이전트의 기능을 향상시키기 위한 다양한 사전 구
href="/ko/tools/database-data/overview"
color="#8B5CF6"
>
- SQL 데이터베이스, 벡터 스토어, 데이터 웨어하우스에 연결합니다. MySQL, PostgreSQL, Snowflake, Qdrant, Weaviate를 쿼리할 수 있습니다.
+ 데이터베이스, 벡터 스토어, 데이터 웨어하우스에 연결합니다. MySQL, PostgreSQL, MongoDB, Snowflake, Qdrant, Weaviate를 쿼리할 수 있습니다.
</Card>
<Card
@@ -87,7 +87,7 @@ CrewAI는 에이전트의 기능을 향상시키기 위한 다양한 사전 구
특정 도구가 필요하신가요? 인기 있는 옵션들을 소개합니다:
-<CardGroup cols={3}>
+<CardGroup cols={2}>
<Card title="RAG Tool" icon="image" href="/ko/tools/ai-ml/ragtool">
검색 기반 생성(Retrieval-Augmented Generation) 구현
</Card>
@@ -97,6 +97,9 @@ CrewAI는 에이전트의 기능을 향상시키기 위한 다양한 사전 구
<Card title="File Read" icon="file" href="/ko/tools/file-document/filereadtool">
모든 파일 유형 읽기
</Card>
+ <Card title="Directory Read" icon="folder-open" href="/ko/tools/file-document/directoryreadtool">
+ 디렉터리 내용 목록 조회 및 읽기
+ </Card>
<Card title="Scrape Website" icon="globe" href="/ko/tools/web-scraping/scrapewebsitetool">
웹 콘텐츠 추출
</Card>
@@ -106,6 +109,9 @@ CrewAI는 에이전트의 기능을 향상시키기 위한 다양한 사전 구
<Card title="S3 Reader" icon="cloud" href="/ko/tools/cloud-storage/s3readertool">
AWS S3 파일 액세스
</Card>
+ <Card title="MongoDB Vector Search" icon="database" href="/ko/tools/database-data/mongodbvectorsearchtool">
+ MongoDB에서 벡터 유사도 쿼리 실행
+ </Card>
</CardGroup>
## **시작하기**
diff --git a/docs/edge/pt-BR/concepts/memory.mdx b/docs/edge/pt-BR/concepts/memory.mdx
index 6d57ce130..acccff07c 100644
--- a/docs/edge/pt-BR/concepts/memory.mdx
+++ b/docs/edge/pt-BR/concepts/memory.mdx
@@ -758,7 +758,7 @@ memory = Memory(
## Backend de Armazenamento
- **Padrão**: LanceDB, armazenado em `./.crewai/memory` (ou `$CREWAI_STORAGE_DIR/memory` se a variável de ambiente estiver definida, ou o caminho que você passar como `storage="path/to/dir"`).
-- **Backend customizado**: Implemente o protocolo `StorageBackend` (veja `crewai.memory.storage.backend`) e passe uma instância para `Memory(storage=your_backend)`.
+- **Backend customizado**: Implemente o protocolo `StorageBackend` (veja `crewai.memory.storage.backend`) e passe uma instância para `Memory(storage=your_backend)`. Para implantações em produção, você pode usar o `MongoDBStorageBackend` do pacote `crewai-mongodb-memory`. Para saber mais, veja o [tutorial de implementação do MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/agent-memory/).
## Descoberta
diff --git a/docs/edge/pt-BR/concepts/tools.mdx b/docs/edge/pt-BR/concepts/tools.mdx
index da7e6f24a..7a331d644 100644
--- a/docs/edge/pt-BR/concepts/tools.mdx
+++ b/docs/edge/pt-BR/concepts/tools.mdx
@@ -144,6 +144,7 @@ Aqui está uma lista das ferramentas disponíveis e suas descrições:
| **JSONSearchTool** | Ferramenta RAG para busca em arquivos JSON, voltada ao manuseio de dados estruturados. |
| **LlamaIndexTool** | Permite o uso das ferramentas LlamaIndex. |
| **MDXSearchTool** | Ferramenta RAG para busca em arquivos Markdown (MDX), útil para documentação. |
+| **MongoDBVectorSearchTool** | Ferramenta RAG para busca por similaridade vetorial em coleções do MongoDB Atlas, com auxiliares opcionais para criar e gerenciar índices de vector search. |
| **PDFSearchTool** | Ferramenta RAG para busca em documentos PDF, ideal para processar documentos digitalizados. |
| **PGSearchTool** | Ferramenta RAG otimizada para busca em bancos de dados PostgreSQL, adequada para consultas. |
| **Vision Tool** | Ferramenta para gerar imagens utilizando a API do DALL-E. |
diff --git a/docs/edge/pt-BR/tools/database-data/mongodbvectorsearchtool.mdx b/docs/edge/pt-BR/tools/database-data/mongodbvectorsearchtool.mdx
index 15ebcde88..9aa592027 100644
--- a/docs/edge/pt-BR/tools/database-data/mongodbvectorsearchtool.mdx
+++ b/docs/edge/pt-BR/tools/database-data/mongodbvectorsearchtool.mdx
@@ -9,10 +9,14 @@ mode: "wide"
## Description
-Perform vector similarity queries on MongoDB Atlas collections. Supports index creation helpers and bulk insert of embedded texts.
+A `MongoDBVectorSearchTool` permite consultas de similaridade vetorial em coleções do MongoDB Atlas. O MongoDB Atlas
+oferece suporte nativo a vector search. A ferramenta também oferece auxiliares para criação de índices e inserção em massa de textos com embeddings.
-MongoDB Atlas supports native vector search. Learn more:
-https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
+O MongoDB Vector Search é útil para aplicações que desejam usar um banco de dados vetorial para consultar dados
+com busca semântica, filtrar consultas em outros campos da sua coleção, ou potencializar suas
+aplicações de IA e sistemas agentic implementando retrieval-augmented generation (RAG).
+
+Saiba mais: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
## Installation
@@ -28,24 +32,31 @@ or
uv add crewai-tools --extra mongodb
```
-## Parameters
-
-### Initialization
+## Initialization Parameters
-- `connection_string` (str, required)
-- `database_name` (str, required)
-- `collection_name` (str, required)
-- `vector_index_name` (str, default `vector_index`)
-- `text_key` (str, default `text`)
-- `embedding_key` (str, default `embedding`)
-- `dimensions` (int, default `1536`)
+- `connection_string` (str): Obrigatório. String de conexão do MongoDB Atlas com as credenciais para se conectar ao seu cluster.
+- `database_name` (str): Obrigatório. O nome do banco de dados MongoDB a ser utilizado.
+- `collection_name` (str): Obrigatório. A coleção dentro do banco de dados onde documentos e embeddings são armazenados.
+- `vector_index_name` (str, default: `vector_index`): Opcional. O nome do índice de MongoDB Vector Search a ser consultado (deve corresponder ao índice
+ criado no Atlas).
+- `text_key` (str, default: `text`): Opcional. O nome do campo do documento onde o texto bruto é armazenado.
+- `embedding_key` (str, default: `embedding`): Opcional. O nome do campo do documento onde o embedding vetorial é armazenado.
+- `dimensions` (int, default: `1536`): Opcional. O número de dimensões do modelo de embedding (deve corresponder ao seu modelo).
+- `query_config` (MongoDBVectorSearchConfig): Opcional. Um objeto `MongoDBVectorSearchConfig` para configurações avançadas de consulta, como `limit` e `oversampling_factor`.
-### Run Parameters
+## MongoDBVectorSearchTool Methods
-- `query` (str, required): Natural language query to embed and search.
+- `run(query=...)`: Gera o embedding de uma consulta e realiza uma busca por similaridade vetorial, retornando os documentos correspondentes.
+ Recebe um parâmetro `query` (`str`) em linguagem natural para gerar o embedding e realizar a busca.
+- `add_texts(list of strings)`: Recebe uma lista de strings para gerar embeddings e inserir como documentos no seu banco de dados do MongoDB Atlas.
+- `create_vector_search_index(dimensions=...)`: Provisiona um índice de MongoDB Vector Search com as dimensões
+ e a similaridade corretas. Recebe um parâmetro `dimensions` (int).
## Quick start
+O exemplo a seguir demonstra como inicializar a ferramenta e executar uma busca por similaridade vetorial na
+coleção especificada do MongoDB Atlas:
+
```python Code
from crewai_tools import MongoDBVectorSearchTool
@@ -58,31 +69,48 @@ tool = MongoDBVectorSearchTool(
print(tool.run(query="how to create vector index"))
```
-## Index creation helpers
-
-Use `create_vector_search_index(...)` to provision an Atlas Vector Search index with the correct dimensions and similarity.
-
## Common issues
- Authentication failures: ensure your Atlas IP Access List allows your runner and the connection string includes credentials.
- Index not found: create the vector index first; name must match `vector_index_name`.
- Dimensions mismatch: align embedding model dimensions with `dimensions`.
-## More examples
+## Examples
+
+### Preload the database and create the index
-### Basic initialization
+O exemplo a seguir demonstra como pré-carregar seu banco de dados do MongoDB Atlas com documentos
+e criar um índice de MongoDB Vector Search para consultar sua coleção:
```python Code
+import os
from crewai_tools import MongoDBVectorSearchTool
tool = MongoDBVectorSearchTool(
database_name="example_database",
collection_name="example_collection",
connection_string="<your_mongodb_connection_string>",
+ dimensions=3072,
)
+
+# Load text content from a local folder and add to your MongoDB collection
+texts = []
+for fname in os.listdir("knowledge"):
+ path = os.path.join("knowledge", fname)
+ if os.path.isfile(path):
+ with open(path, "r", encoding="utf-8") as f:
+ texts.append(f.read())
+
+tool.add_texts(texts)
+
+# Create the MongoDB Vector Search index (e.g., 3072 dims for text-embedding-3-large)
+tool.create_vector_search_index(dimensions=3072)
```
-### Custom query configuration
+### Custom query configuration and agent configuration
+
+O exemplo a seguir demonstra como fornecer uma configuração de consulta customizada para a `MongoDBVectorSearchTool`
+e integrá-la com um agente do CrewAI:
```python Code
from crewai_tools import MongoDBVectorSearchConfig, MongoDBVectorSearchTool
@@ -105,33 +133,10 @@ rag_agent = Agent(
)
```
-### Preloading the database and creating the index
+### Run a CrewAI workflow
-```python Code
-import os
-from crewai_tools import MongoDBVectorSearchTool
-
-tool = MongoDBVectorSearchTool(
- database_name="example_database",
- collection_name="example_collection",
- connection_string="<your_mongodb_connection_string>",
-)
-
-# Load text content from a local folder and add to MongoDB
-texts = []
-for fname in os.listdir("knowledge"):
- path = os.path.join("knowledge", fname)
- if os.path.isfile(path):
- with open(path, "r", encoding="utf-8") as f:
- texts.append(f.read())
-
-tool.add_texts(texts)
-
-# Create the Atlas Vector Search index (e.g., 3072 dims for text-embedding-3-large)
-tool.create_vector_search_index(dimensions=3072)
-```
-
-## Example
+O exemplo a seguir demonstra como integrar sua `MongoDBVectorSearchTool` com um Agent, Task e
+Crew para criar e executar um fluxo de trabalho agentic de RAG no CrewAI:
```python Code
from crewai import Agent, Task, Crew
@@ -165,3 +170,9 @@ crew = Crew(
result = crew.kickoff()
```
+
+## Learn More
+
+Para saber mais sobre as integrações do CrewAI com o MongoDB, veja os seguintes guias do MongoDB:
+- [Integrate MongoDB with CrewAI](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/)
+- [Build an Agentic RAG Application with CrewAI and MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/crewai/build-agents/)
diff --git a/docs/edge/pt-BR/tools/database-data/overview.mdx b/docs/edge/pt-BR/tools/database-data/overview.mdx
index f762950be..84e5ef49d 100644
--- a/docs/edge/pt-BR/tools/database-data/overview.mdx
+++ b/docs/edge/pt-BR/tools/database-data/overview.mdx
@@ -43,17 +43,22 @@ Essas ferramentas permitem que seus agentes interajam com diversos sistemas de b
- **Análise em Tempo Real**: Acesse dados ao vivo para tomada de decisões
```python
-from crewai_tools import MySQLTool, QdrantVectorSearchTool, NL2SQLTool
+from crewai_tools import MySQLTool, MongoDBVectorSearchTool, QdrantVectorSearchTool, NL2SQLTool
# Create database tools
mysql_db = MySQLTool()
-vector_search = QdrantVectorSearchTool()
+mongodb_vector_search = MongoDBVectorSearchTool(
+ connection_string="<MONGODB_URI>",
+ database_name="<database>",
+ collection_name="<collection>",
+)
+qdrant_vector_search = QdrantVectorSearchTool()
nl_to_sql = NL2SQLTool()
# Add to your agent
agent = Agent(
role="Data Analyst",
- tools=[mysql_db, vector_search, nl_to_sql],
+ tools=[mysql_db, mongodb_vector_search, qdrant_vector_search, nl_to_sql],
goal="Extract insights from various data sources"
)
```
diff --git a/docs/edge/pt-BR/tools/overview.mdx b/docs/edge/pt-BR/tools/overview.mdx
index 68004f160..60b2a3b89 100644
--- a/docs/edge/pt-BR/tools/overview.mdx
+++ b/docs/edge/pt-BR/tools/overview.mdx
@@ -43,7 +43,7 @@ O CrewAI oferece uma biblioteca extensa de ferramentas pré-construídas para ap
href="/pt-BR/tools/database-data/overview"
color="#8B5CF6"
>
- Conecte-se a bancos de dados SQL, repositórios vetoriais e data warehouses. Consulte MySQL, PostgreSQL, Snowflake, Qdrant e Weaviate.
+ Conecte-se a bancos de dados, repositórios vetoriais e data warehouses. Consulte MySQL, PostgreSQL, MongoDB, Snowflake, Qdrant e Weaviate.
</Card>
<Card
@@ -87,7 +87,7 @@ O CrewAI oferece uma biblioteca extensa de ferramentas pré-construídas para ap
Precisa de uma ferramenta específica? Aqui estão algumas opções populares:
-<CardGroup cols={3}>
+<CardGroup cols={2}>
<Card title="RAG Tool" icon="image" href="/pt-BR/tools/ai-ml/ragtool">
Implemente Geração com Recuperação de Dados (RAG)
</Card>
@@ -97,6 +97,9 @@ Precisa de uma ferramenta específica? Aqui estão algumas opções populares:
<Card title="File Read" icon="file" href="/pt-BR/tools/file-document/filereadtool">
Leia qualquer tipo de arquivo
</Card>
+ <Card title="Directory Read" icon="folder-open" href="/pt-BR/tools/file-document/directoryreadtool">
+ Liste e leia conteúdos de diretórios
+ </Card>
<Card title="Scrape Website" icon="globe" href="/pt-BR/tools/web-scraping/scrapewebsitetool">
Extraia conteúdo da web
</Card>
@@ -106,6 +109,9 @@ Precisa de uma ferramenta específica? Aqui estão algumas opções populares:
<Card title="S3 Reader" icon="cloud" href="/pt-BR/tools/cloud-storage/s3readertool">
Acesse arquivos no AWS S3
</Card>
+ <Card title="MongoDB Vector Search" icon="database" href="/pt-BR/tools/database-data/mongodbvectorsearchtool">
+ Execute consultas de similaridade vetorial no MongoDB
+ </Card>
</CardGroup>
## **Primeiros Passos**