Para agentes de IA: um índice de documentação está disponível em https://www.mongodb.com/pt-br/docs/llms.txt — as versões de markdown de todas as páginas estão disponíveis anexando .md a qualquer caminho de URL.

Integre o MongoDB com os agentes Strands

Você pode integrar o MongoDB com os Agentes Strands., um SDK Python de código aberto para a criação de agentes de IA. O strands-mongodb Este pacote permite que você utilize uma implementação do MongoDB como backend para as seguintes classes:

  • O MongoDBStorage é responsável por armazenar sessões de agentes, gerenciamento de contexto e transcrições no MongoDB.

  • O MongoDBMemoryStore salva e recupera informações por significado semântico, palavra-chave ou uma combinação de ambos.

Para concluir o tutorial que configura os Agentes Strands para usar o MongoDB, consulte Introdução à integração dos Agentes Strands com o MongoDB.

To install the strands-mongodb package and the dependencies for the MongoDBStorage and MongoDBMemoryStore classes, run the following command:

pip install 'strands-mongodb[all]'

Este comando instala as seguintes dependências:

  • strands-mongodbO pacote de integração do MongoDB para agentes Strands.

  • strands-agents: The Strands Agents SDK. The package requires v1.54 or later.

  • pymongo: The official Python driver for MongoDB. The package requires v4.14 or later.

  • pymongo-search-utils: Utilities for working with MongoDB's vector search features. The package requires v0.3 or later.

  • opentelemetry-api: The OpenTelemetry API for Python. The package requires v1.30 or later.

  • typing-extensions: Backported typing features for Python. The package requires v4.13.2 or later.

Alternativamente, instale as dependências para classes individuais executando um dos seguintes comandos:

pip install 'strands-mongodb[storage]' # MongoDBStoragepip install 'strands-mongodb[memory]' # MongoDBMemoryStore

To configure your MongoDB connection, pass a MongoDBConfig dictionary to the MongoDBStorage or MongoDBMemoryStore class. Create one MongoDBConfig dictionary per process and pass it to every class you use, which allows them to share one connection pool.

You can specify either an existing client or a connection string to configure your connection. Select the Existing client or Connection string tab to view a corresponding example:

from pymongo import AsyncMongoClientfrom strands_mongodb.types import MongoDBConfig client = AsyncMongoClient("<connection-string>")connection: MongoDBConfig = { "client": client, "database": "agents",}

Observação

O pacote não assume a propriedade do cliente. Você é responsável por fechá-lo.

To learn more about AsyncMongoClient, see Create a MongoClient.

The MongoDBStorage class allows you to save an agent's persistent data in MongoDB. Once configured, the SDK stores the agent's sessions, context management data, and transcripts as documents in a MongoDB collection instead of in local files or memory. The persistent data is stored under string keys, and each key becomes a document's _id value. As a result, read and write operations perform primary-key lookups.

This section describes how to configure and use the methods provided by the MongoDBStorage class.

To configure this class, pass a MongoDBConfig dictionary and a collection name to the MongoDBStorage constructor. The following example writes persistent data to MongoDB, retrieves this data, lists keys that start with a specified prefix, and deletes the data:

import asyncio from strands_mongodb import MongoDBStorage async def main() -> None: storage = MongoDBStorage(connection, collection="storage") try: await storage.write("notes/colony", b"emperor penguins live in Antarctica") print(await storage.read("notes/colony")) print(await storage.list("notes/")) await storage.delete("notes/colony") finally: await storage.close() asyncio.run(main())

Para aprender como configurar um agente para usar essa classe, consulte Configurar um Agente.

The following table lists the methods provided by the MongoDBStorage class:

Método
Descrição
Parâmetros
Valor de retorno

write()

Stores persistent data as bytes in a key, replacing any existing value. If you set ttl_seconds, this method also adds an expires_at field to the document it writes.

key: The key to store the data under.
data: The bytes to store.

None

read()

Retorna os bytes armazenados em uma chave.

keyA chave para a leitura.

bytes, or None when the key is absent

delete()

Remove uma chave. Se você excluir uma chave que não existe, este método não gera um erro.

keyA chave para remover.

None

list()

Retorna os nomes das chaves que começam com um prefixo, em ordem crescente. Retorna apenas as chaves, não os valores armazenados.

query: O prefixo da chave a ser correspondido.

list[str]

search()

By default, this method ranks stored key names by how many words they share with a query. To search the stored values instead, set MongoDBStorage's search_strategy parameter to a strategy that reads values, such as the SDK's KeywordSearchStrategy or MongoDBVectorSearchStrategy for vector search.

queryO texto a ser pesquisado.

list[StorageSearchResult]

delete_prefix()

Remove todas as chaves que começam com um prefixo especificado.

prefix: O prefixo da chave a ser removido.

int, que indica o número de documentos removidos.

namespace()

Returns a new MongoDBStorage scoped to a prefix in the same collection, sharing the original connection pool, collection, TTL, and search strategy. This method is synchronous.

prefix: O prefixo que define o escopo da nova instância.

MongoDBStorage

ensure_indexes()

Creates or verifies the TTL index that ttl_seconds requires. Call this method once at startup.

none

None

close()

Releases the connection pool for every instance that shares the same MongoDBConfig dictionary. Call this method once at process shutdown.

none

None

When you pass a MongoDBStorage instance to an Agent, the agent's session and context subsystems call write(), read(), delete(), list(), and search() for you. You call ensure_indexes(), close(), namespace(), and delete_prefix() yourself.

The MongoDBMemoryStore class allows you to save an agent's long-term memory in MongoDB. Once configured, the agent stores facts in a MongoDB collection and retrieves them by meaning, by keyword, or both. The store uses MongoDB Vector Search for semantic recall and MongoDB Search for keyword recall.

Para usar a Pesquisa Vetorial do MongoDB, o MongoDB compara os vetores de incorporação dos seus dados com a incorporação da consulta. Por padrão, o MongoDB gera essas incorporações automaticamente, portanto, você não precisa gerenciar vetores ou chaves de API do provedor de incorporação.

This section describes how to configure and use the methods provided by the MongoDBMemoryStore class.

To configure this class, pass a name and a MongoDBConfig dictionary to the MongoDBMemoryStore constructor.

This example creates a memory store, adds a memory, and then searches for the memory by semantic meaning. When instantiating a MongoDBMemoryStore, the example also sets the following optional parameters:

  • scope: Limits the memory store's access to documents that store the specified scope field value. The example uses the scope "user-abc".

  • writablePermite operações de escrita no armazenamento em memória.

import asyncio from strands_mongodb import MongoDBMemoryStore async def main() -> None: store = MongoDBMemoryStore( name="preferences", config=connection, scope="user-abc", writable=True ) try: await store.add("Studies emperor penguins in Antarctica.") results = await store.search("Which animals does this researcher observe?") for entry in results: print(f"search type: {entry.metadata['_search_type']}") print(f"score: {entry.metadata['_relevance_score']}") print(f"content: {entry.content}") finally: await store.close() asyncio.run(main())

MongoDBMemoryStore Utiliza os seguintes tipos de pesquisa para responder a uma consulta:

  • Busca vetorial, que realiza correspondências por significado.

  • Pesquisa de texto, que encontra correspondência por palavra-chave.

  • Busca híbrida, que combina os dois tipos de busca.

The search_type key in the MongoDBConfig dictionary controls which search types the store uses. The default value, "auto", prepares every search type the deployment supports and prefers the highest one available.

Because this deployment prepares both indexes, a search_type value of "auto" uses hybrid search. Hybrid search ranks results differently from vector search, so scores from the two are not directly comparable. A min_score or max_score value that you configured for vector search can exclude results that you expect to keep.

Para aprender como configurar um agente para usar essa classe, consulte Configurar um Agente.

The following table lists the methods provided by the MongoDBMemoryStore class:

Método
Descrição
Parâmetros
Valor de retorno

add()

Armazena uma única informação na memória dentro do escopo deste armazenamento. As gravações são desduplicadas com base no escopo, nome do armazenamento e conteúdo; portanto, adicionar o mesmo fato novamente não cria um segundo documento.

content: The text of the memory.
metadata: Optional key-value pairs to store with the memory.

MongoDBAddResult, which contains ids, inserted, and duplicates

search()

Returns the memories that best match a query in order of relevance. Accepts a plain string or a MongoDBSearchQuery dictionary for a per-query filter, limit, or vector.

query: The text to search for, or a MongoDBSearchQuery dictionary.
options: Optional SDK search options, such as max_search_results.

list[MemoryEntry]. Each entry's metadata includes _relevance_score, _search_type, _scope, and _id.

initialize()

Identifies which search features the deployment supports, and then creates this store's indexes. This method is called automatically by MemoryManager and by every method that reads or writes memories.

none

None

delete()

Deletes one memory, identified by the _id that a search result reports. To use this method, you must set writable to True.

memory_id: The _id value from a search result.

int, which is 1 if a document was deleted or 0 if none matched

delete_all()

Deletes every memory that this store can read. To use this method, you must set writable to True.

none

int, que indica o número de documentos excluídos

close()

Releases the connection pool for every instance that shares the same MongoDBConfig dictionary.

none

None

When you register this store with MemoryManager, the agent calls initialize(), search(), and, when you enable it, add(). You call delete(), delete_all(), and close() yourself, because the SDK's MemoryStore interface has no deletion or connection methods.

Você pode configurar um agente para armazenar suas sessões e memória de longo prazo na mesma implementação do MongoDB. Essa configuração permite que o agente salve e recupere esses dados automaticamente durante a execução.

To configure the agent, pass a MongoDBConfig dictionary to both the MongoDBStorage and MongoDBMemoryStore constructors, then pass the resulting instances to the Agent constructor.

O exemplo a seguir cria um agente que usa o MongoDB tanto para sessões quanto para memória:

from strands import Agentfrom strands.memory import MemoryManagerfrom strands.session import SnapshotSessionManagerfrom strands_mongodb import MongoDBStorage, MongoDBMemoryStore store = MongoDBMemoryStore( name="preferences", config=connection, scope="user-abc", writable=True,) agent = Agent( model=your_model, storage=MongoDBStorage(connection), session_manager=SnapshotSessionManager(session_id="support-ticket-4127"), memory_manager=MemoryManager(stores=[store], add_tool_config=True),)

As seguintes considerações se aplicam:

  • To allow the agent to save memories, set the writable key to True.

  • The MemoryManager class always provides the model with a search_memory tool, but it provides an add_memory tool only when add_tool_config is set to True. If you want the model to decide when to save a memory, enable the add_tool_config parameter.

  • The add_tool_config parameter raises a ValueError if no store you pass is writable.

  • The storage parameter alone does not persist sessions. You must set session_manager to save the sessions under the specified session_id value.

MongoDBMemoryStore creates two search indexes on first use, unless you set the ensure_indexes key to False.

The MongoDB Vector Search index is named by the MongoDBConfig dictionary's vector_index_name key and has the following definition:

{ "fields": [ { "type": "autoEmbed", "path": "content", "model": "voyage-4-lite", "modality": "text" }, { "type": "filter", "path": "scope" }, { "type": "filter", "path": "store_name" } ]}

Observação

By default, this MongoDB Vector Search index uses the autoEmbed type, which instructs MongoDB to generate the embeddings automatically.

The MongoDB Search index is named by the MongoDBConfig dictionary's text_index_name key and has the following definition:

{ "mappings": { "dynamic": false, "fields": { "content": [{ "type": "string" }] } }}

Para saber mais sobre como criar esses índices manualmente, consulte Criar um índice de pesquisa vetorial do MongoDB e Índice de pesquisa do MongoDB.

To supply your own vector embeddings, set the MongoDBConfig dictionary's embedding_dimensions and similarity keys. Do not set the embedding_model key. With this configuration, MongoDB indexes an embedding field as the vector type, instead of a content field as the autoEmbed type.

Em seguida, forneça os vetores de uma das seguintes maneiras:

  • Pass an embedder object to the MongoDBMemoryStore constructor, which instructs the store to embed memories and string queries

  • When calling the search() method, pass a precomputed vector in the vector key of a MongoDBSearchQuery dictionary

A tabela a seguir descreve os privilégios que seu usuário de banco de dados precisa para realizar diferentes ações:

Privilégio
Necessário para
Necessário quando

Todas as leituras, em ambas as turmas.

Sempre

write(), add(), delete(), and similar methods

Sempre, para uma instância de armazenamento ou armazenamento gravável.

Collation check that every initialize() call runs before any index

Sempre

Verificação de índices

Sempre

Criação de índices

Only when ensure_indexes is set to True, its default value

Para conceder esses privilégios, crie uma função personalizada com escopo definido para suas coleções de armazenamento e memória.

Observação

By default, the initialize() and ensure_indexes() methods create the indexes the package requires if they don't already exist. Production applications often run as a user without the createIndex, createCollection, and createSearchIndexes privileges, or leave index creation to a separate deployment step. In that case, set the MongoDBConfig dictionary's ensure_indexes key to False. This instructs the package to verify the indexes instead of creating them.

Para saber mais sobre como usar os Agentes Strands com o MongoDB, consulte os seguintes recursos: