docs: astra component update (#6720)
* starter-project-update * update-component-add-vectorize * update-quickstart * style-cleanup * Apply suggestions from code review Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com> * split-large-steps-add-admonition * dimensions-not-required-for-astra-vectorize * Apply suggestions from code review Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com> * fix-numbering * Apply suggestions from code review Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com> --------- Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com>
This commit is contained in:
Mendon Kissling
GitHub
parent
e8d2635e1c
commit
c18f65cac9
4 changed files with 83 additions and 38 deletions
|
|
@ -37,31 +37,46 @@ For more information, see the [DataStax documentation](https://docs.datastax.com
|
|||
|
||||
| Name | Display Name | Info |
|
||||
|------|--------------|------|
|
||||
| collection_name | Collection Name | The name of the collection within Astra DB where the vectors will be stored (required) |
|
||||
| token | Astra DB Application Token | Authentication token for accessing Astra DB (required) |
|
||||
| api_endpoint | API Endpoint | API endpoint URL for the Astra DB service (required) |
|
||||
| search_input | Search Input | Query string for similarity search |
|
||||
| ingest_data | Ingest Data | Data to be ingested into the vector store |
|
||||
| namespace | Namespace | Optional namespace within Astra DB to use for the collection |
|
||||
| embedding_choice | Embedding Model or Astra Vectorize | Determines whether to use an Embedding Model or Astra Vectorize for the collection |
|
||||
| embedding | Embedding Model | Allows an embedding model configuration (when using Embedding Model) |
|
||||
| provider | Vectorize Provider | Provider for Astra Vectorize (when using Astra Vectorize) |
|
||||
| metric | Metric | Optional distance metric for vector comparisons |
|
||||
| batch_size | Batch Size | Optional number of data to process in a single batch |
|
||||
| setup_mode | Setup Mode | Configuration mode for setting up the vector store (options: "Sync", "Async", "Off", default: "Sync") |
|
||||
| pre_delete_collection | Pre Delete Collection | Boolean flag to determine whether to delete the collection before creating a new one |
|
||||
| number_of_results | Number of Results | Number of results to return in similarity search (default: 4) |
|
||||
| search_type | Search Type | Search type to use (options: "Similarity", "Similarity with score threshold", "MMR (Max Marginal Relevance)") |
|
||||
| search_score_threshold | Search Score Threshold | Minimum similarity score threshold for search results |
|
||||
| search_filter | Search Metadata Filter | Optional dictionary of filters to apply to the search query |
|
||||
| token | Astra DB Application Token | The authentication token for accessing Astra DB. |
|
||||
| environment | Environment | The environment for the Astra DB API Endpoint. For example, `dev` or `prod`. |
|
||||
| database_name | Database | The database name for the Astra DB instance. |
|
||||
| api_endpoint | Astra DB API Endpoint | The API endpoint for the Astra DB instance. This supersedes the database selection. |
|
||||
| collection_name | Collection | The name of the collection within Astra DB where the vectors are stored. |
|
||||
| keyspace | Keyspace | An optional keyspace within Astra DB to use for the collection. |
|
||||
| embedding_choice | Embedding Model or Astra Vectorize | Choose an embedding model or use Astra vectorize. |
|
||||
| embedding_model | Embedding Model | Specify the embedding model. Not required for Astra vectorize collections. |
|
||||
| number_of_results | Number of Search Results | The number of search results to return (default: `4`). |
|
||||
| search_type | Search Type | The search type to use. The options are `Similarity`, `Similarity with score threshold`, and `MMR (Max Marginal Relevance)`. |
|
||||
| search_score_threshold | Search Score Threshold | The minimum similarity score threshold for search results when using the `Similarity with score threshold` option. |
|
||||
| advanced_search_filter | Search Metadata Filter | An optional dictionary of filters to apply to the search query. |
|
||||
| autodetect_collection | Autodetect Collection | A boolean flag to determine whether to autodetect the collection. |
|
||||
| content_field | Content Field | A field to use as the text content field for the vector store. |
|
||||
| deletion_field | Deletion Based On Field | When provided, documents in the target collection with metadata field values matching the input metadata field value are deleted before new data is loaded. |
|
||||
| ignore_invalid_documents | Ignore Invalid Documents | A boolean flag to determine whether to ignore invalid documents at runtime. |
|
||||
| astradb_vectorstore_kwargs | AstraDBVectorStore Parameters | An optional dictionary of additional parameters for the AstraDBVectorStore. |
|
||||
|
||||
### Outputs
|
||||
|
||||
| Name | Display Name | Info |
|
||||
|------|--------------|------|
|
||||
| vector_store | Vector Store | Astra DB vector store instance configured with the specified parameters. |
|
||||
| search_results | Search Results | The results of the similarity search as a list of `Data` objects. |
|
||||
| search_results | Search Results | The results of the similarity search as a list of [Data](/concepts-objects#data-object) objects. |
|
||||
|
||||
### Generate embeddings
|
||||
|
||||
The **Astra DB Vector Store** component offers two methods for generating embeddings.
|
||||
|
||||
1. **Embedding Model**: Use your own embedding model by connecting an [Embeddings](/components-embedding-models) component in Langflow.
|
||||
|
||||
2. **Astra Vectorize**: Use Astra DB's built-in embedding generation service. When creating a new collection, choose the embeddings provider and models, including NVIDIA's `NV-Embed-QA` model hosted by Datastax.
|
||||
|
||||
:::important
|
||||
The embedding model selection is made when creating a new collection and cannot be changed later.
|
||||
:::
|
||||
|
||||
For an example of using the **Astra DB Vector Store** component with an embedding model, see the [Vector Store RAG starter project](/starter-projects-vector-store-rag).
|
||||
|
||||
For more information, see the [Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html).
|
||||
|
||||
## AstraDB Graph vector store
|
||||
|
||||
|
|
|
|||
|
|
@ -11,8 +11,8 @@ Get to know Langflow by building an OpenAI-powered chatbot application. After yo
|
|||
|
||||
* [An OpenAI API key](https://platform.openai.com/)
|
||||
* [An Astra DB vector database](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html) with:
|
||||
* An AstraDB application token
|
||||
* [A collection in Astra](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection)
|
||||
* An Astra DB application token scoped to read and write to the database
|
||||
* A collection created in [Astra](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection) or a new collection created in the **Astra DB** component
|
||||
|
||||
## Open Langflow and start a new project
|
||||
|
||||
|
|
@ -31,7 +31,7 @@ Continue to [Run the basic prompting flow](#run-basic-prompting-flow).
|
|||
|
||||
The Basic Prompting flow will look like this when it's completed:
|
||||
|
||||
|
||||
|
||||
|
||||
To build the **Basic Prompting** flow, follow these steps:
|
||||
|
||||
|
|
@ -46,7 +46,7 @@ The [OpenAI](components-models#openai) model component sends the user input and
|
|||
|
||||
You should now have a flow that looks like this:
|
||||
|
||||
|
||||
|
||||
|
||||
With no connections between them, the components won't interact with each other.
|
||||
You want data to flow from **Chat Input** to **Chat Output** through the connections between the components.
|
||||
|
|
@ -111,7 +111,7 @@ If you don't want to create a blank flow, click **New Flow**, and then select **
|
|||
|
||||
Adding vector RAG to the basic prompting flow will look like this when completed:
|
||||
|
||||
|
||||
|
||||
|
||||
To build the flow, follow these steps:
|
||||
|
||||
|
|
@ -120,24 +120,39 @@ To build the flow, follow these steps:
|
|||
The [Astra DB vector store](/components-vector-stores#astra-db-vector-store) component connects to your **Astra DB** database.
|
||||
3. Click **Data**, select the **File** component, and then drag it to the canvas.
|
||||
The [File](/components-data#file) component loads files from your local machine.
|
||||
3. Click **Processing**, select the **Split Text** component, and then drag it to the canvas.
|
||||
4. Click **Processing**, select the **Split Text** component, and then drag it to the canvas.
|
||||
The [Split Text](/components-processing#split-text) component splits the loaded text into smaller chunks.
|
||||
4. Click **Processing**, select the **Parse Data** component, and then drag it to the canvas.
|
||||
5. Click **Processing**, select the **Parse Data** component, and then drag it to the canvas.
|
||||
The [Data to Message](/components-processing#data-to-message) component converts the data from the **Astra DB** component into plain text.
|
||||
5. Click **Embeddings**, select the **OpenAI Embeddings** component, and then drag it to the canvas.
|
||||
6. Click **Embeddings**, select the **OpenAI Embeddings** component, and then drag it to the canvas.
|
||||
The [OpenAI Embeddings](/components-embedding-models#openai-embeddings) component generates embeddings for the user's input, which are compared to the vector data in the database.
|
||||
6. Connect the new components into the existing flow, so your flow looks like this:
|
||||
7. Connect the new components into the existing flow, so your flow looks like this:
|
||||
|
||||
|
||||
|
||||
|
||||
8. Configure the **Astra DB** component.
|
||||
1. In the **Astra DB Application Token** field, add your **Astra DB** application token.
|
||||
The component connects to your database and populates the menus with existing databases and collections.
|
||||
2. Select your **Database**.
|
||||
If you don't have a collection, select **New database**.
|
||||
Complete the **Name**, **Cloud provider**, and **Region** fields, and then click **Create**. **Database creation takes a few minutes**.
|
||||
3. Select your **Collection**. Collections are created in your [Astra DB deployment](https://astra.datastax.com) for storing vector data.
|
||||
If you don't have a collection, see the [DataStax Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection).
|
||||
4. Select **Embedding Model** to bring your own embeddings model, which is the connected **OpenAI Embeddings** component.
|
||||
The **Dimensions** value must match the dimensions of your collection. This value can be found in your **Collection** in your [Astra DB deployment](https://astra.datastax.com).
|
||||
:::info
|
||||
If you select a collection embedded with NVIDIA through Astra's vectorize service, the **Embedding Model** port is removed, because you have already generated embeddings for this collection with the NVIDIA `NV-Embed-QA` model. The component fetches the data from the collection, and uses the same embeddings for queries.
|
||||
:::
|
||||
|
||||
9. If you don't have a collection, create a new one within the component.
|
||||
1. Select **New collection**.
|
||||
2. Complete the **Name**, **Embedding generation method**, **Embedding model**, and **Dimensions** fields, and then click **Create**.
|
||||
|
||||
Your choice for the **Embedding generation method** and **Embedding model** depends on whether you want to use embeddings generated by a provider through Astra's vectorize service, or generated by a component in Langflow.
|
||||
|
||||
* To use embeddings generated by a provider through Astra's vectorize service, select the model from the **Embedding generation method** dropdown menu, and then select the model from the **Embedding model** dropdown menu.
|
||||
* To use embeddings generated by a component in Langflow, select **Bring your own** for both the **Embedding generation method** and **Embedding model** fields. In this starter project, the option for the embeddings method and model is the **OpenAI Embeddings** component connected to the **Astra DB** component.
|
||||
* The **Dimensions** value must match the dimensions of your collection. This field is **not required** if you use embeddings generated through Astra's vectorize service. You can find this value in the **Collection** in your [Astra DB deployment](https://astra.datastax.com).
|
||||
|
||||
For more information, see the [DataStax Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html).
|
||||
|
||||
|
||||
If you used Langflow's **Global Variables** feature, the RAG application flow components are already configured with the necessary credentials.
|
||||
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ This opens a starter flow with the necessary components to run an agentic applic
|
|||
|
||||
## Simple Agent flow
|
||||
|
||||
<img src="/img/starter-flow-simple-agent.png" alt="Starter flow simple agent" width="75%"/>
|
||||
|
||||
|
||||
The **Simple Agent** flow consists of these components:
|
||||
|
||||
|
|
|
|||
|
|
@ -20,9 +20,9 @@ We've chosen [Astra DB](https://astra.datastax.com/signup?utm_source=langflow-p
|
|||
## Prerequisites
|
||||
|
||||
* [An OpenAI API key](https://platform.openai.com/)
|
||||
* [An Astra DB vector database](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html) with:
|
||||
* An Astra DB application token
|
||||
* [A collection in Astra](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection)
|
||||
* [An Astra DB vector database](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html) with the following:
|
||||
* An Astra DB application token scoped to read and write to the database
|
||||
* A collection created in [Astra](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection) or a new collection created in the **Astra DB** component
|
||||
|
||||
|
||||
## Open Langflow and start a new project
|
||||
|
|
@ -60,10 +60,25 @@ The **Retriever Flow** (top of the screen) embeds the user's queries into vecto
|
|||
1. In the **Astra DB Application Token** field, add your **Astra DB** application token.
|
||||
The component connects to your database and populates the menus with existing databases and collections.
|
||||
2. Select your **Database**.
|
||||
If you don't have a collection, select **New database**.
|
||||
Complete the **Name**, **Cloud provider**, and **Region** fields, and then click **Create**. **Database creation takes a few minutes**.
|
||||
3. Select your **Collection**. Collections are created in your [Astra DB deployment](https://astra.datastax.com) for storing vector data.
|
||||
If you don't have a collection, see the [DataStax Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/manage-collections.html#create-collection).
|
||||
4. Select **Embedding Model** to bring your own embeddings model, which is the connected **OpenAI Embeddings** component.
|
||||
The **Dimensions** value must match the dimensions of your collection. You can find this value in the **Collection** in your [Astra DB deployment](https://astra.datastax.com).
|
||||
:::info
|
||||
If you select a collection embedded with Nvidia through Astra's vectorize service, the **Embedding Model** port is removed, because you have already generated embeddings for this collection with the Nvidia `NV-Embed-QA` model. The component fetches the data from the collection, and uses the same embeddings for queries.
|
||||
:::
|
||||
|
||||
3. If you don't have a collection, create a new one within the component.
|
||||
1. Select **New collection**.
|
||||
2. Complete the **Name**, **Embedding generation method**, **Embedding model**, and **Dimensions** fields, and then click **Create**.
|
||||
|
||||
Your choice for the **Embedding generation method** and **Embedding model** depends on whether you want to use embeddings generated by a provider through Astra's vectorize service, or generated by a component in Langflow.
|
||||
|
||||
* To use embeddings generated by a provider through Astra's vectorize service, select the model from the **Embedding generation method** dropdown menu, and then select the model from the **Embedding model** dropdown menu.
|
||||
* To use embeddings generated by a component in Langflow, select **Bring your own** for both the **Embedding generation method** and **Embedding model** fields. In this starter project, the option for the embeddings method and model is the **OpenAI Embeddings** component connected to the **Astra DB** component.
|
||||
* The **Dimensions** value must match the dimensions of your collection. This field is **not required** if you use embeddings generated through Astra's vectorize service. You can find this value in the **Collection** in your [Astra DB deployment](https://astra.datastax.com).
|
||||
|
||||
For more information, see the [DataStax Astra DB Serverless documentation](https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html).
|
||||
|
||||
|
||||
If you used Langflow's **Global Variables** feature, the RAG application flow components are already configured with the necessary credentials.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue