Manage vector data

Vector data is critical to AI applications. Langflow provides several components to help you store and retrieve vector data in your flows, including embedding models, vector stores, and knowledge bases.

Embedding models

Embedding model components generate text embeddings using a specified Large Language Model (LLM).

There are two common use cases for these components:

• Store vectors: Generate embeddings for content written to a vector database.
• Search vectors: Generate an embedding from a query to run a similarity search.

In both cases the embedding model component is attached to a vector store component. For more information, examples, and available options, see Embedding model components.

Alternatively, you can use knowledge bases, which include built-in support for several embedding models.

Vector stores

Vector store components read and write to vector databases. Typically, these components connect to remote databases, but some vector store components support local databases.

By design, vector data is essential for LLM applications, such as chatbots and agents.

While you can use an LLM alone for generic chat interactions and common tasks, you can take your application to the next level with context sensitivity (such as RAG) and custom datasets (such as internal business data). This often requires integrating vector databases and vector searches that provide the additional context and define meaningful queries.

Langflow includes vector store components that can read and write vector data, including embedding storage, similarity search, Graph RAG traversals, and dedicated search instances like OpenSearch. Because of their interdependent functionality, it is common to use vector store, language model, and embedding model components in the same flow or in a series of dependent flows.

To find available vector store components, browse Bundles or Search for your preferred vector database provider.

Example: Vector search flow

tip

For a tutorial that uses vector data in a flow, see Create a vector RAG chatbot.

The following example demonstrates how to use vector store components in flows alongside related components like embedding model and language model components. These steps walk through important configuration details, functionality, and best practices for using these components effectively. This is only one example; it isn't a prescriptive guide to all possible use cases or configurations.

1. Create a flow with the Vector Store RAG template.

   This template has two subflows. The Load Data subflow loads embeddings and content into a vector database, and the Retriever subflow runs a vector search to retrieve relevant context based on a user's query.

2. Configure the database connection for both Astra DB components, or replace them with another pair of vector store components of your choice. Make sure the components connect to the same vector store, and that the component in the Retriever subflow is able to run a similarity search.

   The parameters you set in each vector store component depend on the component's role in your flow. In this example, the Load Data subflow writes to the vector store, whereas the Retriever subflow reads from the vector store. Therefore, search-related parameters are only relevant to the Vector Search component in the Retriever subflow.

   For information about specific parameters, see the documentation for your chosen vector store component.

3. To configure the embedding model, do one of the following:

   • Use an OpenAI model: In both OpenAI Embeddings components, enter your OpenAI API key. You can use the default model or select a different OpenAI embedding model.

   • Use another provider: Replace the OpenAI Embeddings components with another pair of embedding model components of your choice, and then configure the parameters and credentials accordingly.

   • Use Astra DB vectorize: If you are using an Astra DB vector store that has a vectorize integration, you can remove both OpenAI Embeddings components. If you do this, the vectorize integration automatically generates embeddings from the Ingest Data (in the Load Data subflow) and Search Query (in the Retriever subflow).

   tip

   If your vector store already contains embeddings, make sure your embedding model components use the same model as your previous embeddings. Mixing embedding models in the same vector store can produce inaccurate search results.

4. Recommended: In the Split Text component, optimize the chunking settings for your embedding model. For example, if your embedding model has a token limit of 512, then the Chunk Size parameter must not exceed that limit.

   Additionally, because the Retriever subflow passes the chat input directly to the vector store component for vector search, make sure that your chat input string doesn't exceed your embedding model's limits. For this example, you can enter a query that is within the limits; however, in a production environment, you might need to implement additional checks or preprocessing steps to ensure compliance. For example, use additional components to prepare the chat input before running the vector search, or enforce chat input limits in your application code.

5. In the Language Model component, enter your OpenAI API key, or select a different provider and model to use for the chat portion of the flow.

6. Run the Load Data subflow to populate your vector store. In the Read File component, select one or more files, and then click Run component on the vector store component in the Load Data subflow.

   The Load Data subflow loads files from your local machine, chunks them, generates embeddings for the chunks, and then stores the chunks and their embeddings in the vector database.

   

   The Load Data subflow is separate from the Retriever subflow because you probably won't run it every time you use the chat. You can run the Load Data subflow as needed to preload or update the data in your vector store. Then, your chat interactions only use the components that are necessary for chat.

   If your vector store already contains data that you want to use for vector search, then you don't need to run the Load Data subflow.

7. Open the Playground and start chatting to run the Retriever subflow.

   The Retriever subflow generates an embedding from chat input, runs a vector search to retrieve similar content from your vector store, parses the search results into supplemental context for the LLM, and then uses the LLM to generate a natural language response to your query. The LLM uses the vector search results along with its internal training data and tools, such as basic web search and datetime information, to produce the response.

   

   To avoid passing the entire block of raw search results to the LLM, the Parser component extracts text strings from the search results Data object, and then passes them to the Prompt Template component in Message format. From there, the strings and other template content are compiled into natural language instructions for the LLM.

   You can use other components for this transformation, such as the Data Operations component, depending on how you want to use the search results.

   To view the raw search results, click Inspect output on the vector store component after running the Retriever subflow.

Knowledge bases

A Langflow knowledge base is a local vector database that is stored in Langflow storage.

Because knowledge bases are local, the data isn't remotely requested and re-ingested with every flow run. This can be more efficient than using a remote vector database, and it is a good choice for flows that use custom, domain-specific datasets, like slices of customer and product data.

You can use knowledge base components in much the same way that you use vector store components. However, there are several key differences:

• Local storage: Langflow knowledge bases are exclusively local. In contrast, only some vector store components support local databases.
• Built-in embedding models: Langflow knowledge bases include built-in support for several embedding models. Other models aren't supported for use with knowledge bases. To use a different provider or model, you must use a vector store component along with your preferred embedding model component.
• Basic similarity search: When querying Langflow knowledge bases, only standard similarity search is supported. For more advanced searches, you must use a vector store component for a vector database provider that supports your desired functionality.
• Structured data: Langflow knowledge bases only support structured data. For unstructured data, you must use a compatible vector store component.

Knowledge base storage locations

Each knowledge base is a ChromaDB vector database. Each database is stored in a separate directory that contains the following:

• Vector embeddings: Embeddings are stored using the Chroma vector database.
• Metadata files: Configuration and embedding model information.
• Source data: The original data used to create the knowledge base.

Knowledge bases are stored local to your Langflow instance. The default storage location depends on your operating system and installation method:

• Langflow Desktop:
  • macOS: /Users/<username>/.langflow/knowledge_bases
  • Windows: C:\Users\<name>\AppData\Roaming\com.LangflowDesktop\knowledge_bases
• Langflow OSS:
  • macOS/Windows/Linux/WSL with uv pip install: <path_to_venv>/lib/python3.12/site-packages/langflow/knowledge_bases (Python version can vary. Knowledge bases aren't shared between virtual environments.)
  • macOS/Windows/Linux/WSL with git clone: <path_to_clone>/src/backend/base/langflow/knowledge_bases

If you set the LANGFLOW_CONFIG_DIR environment variable, the knowledge_bases subdirectory is created relative to that path.

To change the default knowledge_bases directory path, set the LANGFLOW_KNOWLEDGE_BASES_DIR environment variable:

_10

export LANGFLOW_KNOWLEDGE_BASES_DIR="/path/to/parent/directory"

Create a knowledge base

In this example, you'll create a knowledge base of chunked customer orders. To follow along with this example, download customer-orders.csv to your local machine, or adapt the steps for your own structured data.

1. On the Projects page page, click Knowledge below the list of projects to view and manage your knowledge bases.

2. To create a new knowledge base, click Add Knowledge.

3. In the Create Knowledge Base pane, enter a name for your knowledge base, and select an embedding model.

   To edit Langflow's global model provider configuration, do the following:

   1. To open the Model Providers pane, click your profile icon, select Settings, and then click Model Providers.

   2. In the Model Providers pane, select a provider.

   3. In the API Key field, add your provider's API key.

      The key must have permission to call the models you want to use in your flow, and your account must have sufficient credits for the actions you want to perform.

      You can only add one key for each provider. Make sure the key has access to all models that you want to use in Langflow.

   4. Enable the specific models that you want to use in Langflow. The available models depend on the provider and your API key's permissions. Models that generate text are listed under Language Models. Models that generate embeddings are listed under Embedding Models.

   After you enable a model in Langflow's global model configuration, you can use that model in any model-driven component in your flows.

4. To configure sources for your knowledge base, click Configure Sources. Optionally, to create an empty knowledge base, click Create.

5. In the Configure Sources pane, configure the sources for your knowledge base's data, and also how the embedded data will be chunked for vector search retrieval. For this example, click Add Sources, and then select the downloaded customer-orders.csv file from your local machine. The default settings for Chunk Size, Chunk Overlap, and Separator are fine. To continue, click Next Step.

6. The Review & Build pane allows you to preview your first chunk before you commit to spending tokens to embedall of the data into the knowledge base. If the chunk isn't what you want to embed, click Back to configure your chunking strategy. To embed this data, click Create.

7. Your data is embedded as a Knowledge. When it is available to use, the Status changes to Ready.

To use the new knowledge base in a flow, see Use the Knowledge Base component in a flow.

Manage knowledge bases

On the Projects page page, click Knowledge below the list of projects to view and manage your knowledge bases.

For each knowledge base, you can see the following information:

• Name
• Embedding model
• Size on disk
• Number of words, characters, and chunks
• The average length and size of chunks
• The knowledge base's status

Chunking behavior is determined by the embedding model, and the embedding model is set when you create the knowledge base. If you need to change the embedding model, you must delete and recreate the knowledge base.

To update a knowledge base with , click More, and then select Update Knowledge Base.

To view a knowledge base's chunks, click More, and then select View Chunks.

To delete a knowledge base, click More, and then click Delete. If any flows use the deleted knowledge base, you must update them to use a different knowledge base.

For more information on using knowledge bases in a flow, see the Knowledge Base component documentation.

See also

• Use Langflow agents
• Language model components