Knowledge Search

Semantic search in knowledge

A vectorized dataset can be used in a Knowledge search where you look for specific entries relevant to a query.

If you have not enabled knowledge in the process of uploading your dataset, go to the Data page, switch from “Knowledge” to “Datasets”, and use the Vectorize button on the top to vectorize your data. If you use other options than knowledge, you will see the name of the vector field as shown in the image below.

How to Use the Knowledge Search Step

Add the Component

1. Navigate to the Workflow page.

2. Click on + Create Workflow or select an existing workflow.

3. Click on + Add Action.

4. Select Knowledge Search from the list of action components.

Knowledge Source

Select the target dataset (datasets containing at least a vector field) from the drop-down menu. You can also select “All knowledge sets” to perform the search across all the uploaded and vectorized data.

Note: Only use “All knowledge sets” if they all contain relevant data.

Query

The query is your reference to what you want from your data; it is similar to what you type in Google when performing web searches. Form your queries wisely— not too long, not too short, and precisely mention what needs to be fetched from the data.

Search Type

• Keyword: This search is suitable for word/phrase matching.

• Vector search: This search is suitable for semantic search, looking not just at words but at the concept.

Use word matching when looking for specific words, or even IDs such as model numbers or response IDs.

Model

This is the model used for vectorizing your data. By default, AgenticFlow uses the MpNet model for enabling knowledge. So, if you have vectorized your data with a model other than MpNet, make sure to select the model from the drop-down menu. Otherwise, you do not need to make any selection.

Content Field

You can select which specific column in your knowledge table to be searched. Enter the name of the column (i.e., the header) EXACTLY as seen in the table. If you do not select any field, AgenticFlow searches across the whole dataset (Keyword) or the first vector field (Vector).

When uploading a CSV file knowing one column will be used for search, it is better to only select that target column when enabling knowledge, instead of selecting all columns.

Page Size

After a search query finalizes, you can specify how many of the top matching results should be returned as the search result.

Raw Filters

If you wish to look at a subset of entries in your dataset and perform a search on that subset, you can set raw filters. Keep in mind you must form your filters as JSON objects.

Supported operators and conditions: ==, !=, neq, <=, >=, <, and >. The AND logic is applied when multiple filters are used (i.e., a list of filters).

Filter Samples

Exact Match:

List rows where entries in the field product_name are exactly Durian Leather 2 Seater Sofa:

{
    "field": "product_name",
    "filter_type": "exact_match",
    "condition": "==",
    "condition_value": "Durian Leather 2 Seater Sofa"
}

Exists:

{
    "field": "user_id",
    "filter_type": "exists"
}

Date:

{
    "field": "created_at",
    "filter_type": "date",
    "condition": ">=",
    "condition_value": "2023-01-01"
}

Numeric:

{
    "field": "price",
    "filter_type": "numeric",
    "condition": "<",
    "condition_value": 100
}

IDs:

{
    "field": "id",
    "filter_type": "ids",
    "condition_value": ["id1", "id2", "id3"]
}

Regexp:

{
    "field": "email",
    "filter_type": "regexp",
    "condition_value": "^[e-mail]$"
}

Additional Information

Follow the links below for more information about:

• How to run an action

• How to delete an action

• How to configure output

• How to configure a default value

• How to move an action in a Workflow

• How to duplicate an action

• How to add condition to an action (i.e., execute only if a condition is met)

• How to loop an action (i.e., run one step multiple times)

Access the Step Output

The output is a dictionary with two keys: results and documents, containing the extracted relevant chunks of text from the knowledge set and the full documents respectively. Below are examples where the default name assigned to the step is vector_search.

Example Access

# Accessing the extracted relevant text
vector_search.results

# Accessing the full documents
vector_search.documents

Note that a step name is different from the step title. Step titles can be found on the top left of steps. A step name is shown on the bottom left, in a smaller font and highlighted green.

Common Errors

Wrong URL Formatting

This error occurs when the URL field is set to a value that is not of type string. When using the output of another step, make sure you access the URL field correctly.

Error:

URL must be a string

Non-array Elements

When setting up specific elements to be scraped, make sure to use + Add new to have more than one element. If the button is clicked, do not leave it as an empty list. Use the x icon to the right of the row to remove the extra line.

Error:

Studio transformation browserless_scrape input validation error: must be array {"type":"array"} /element_selector

Invalid URL

This error occurs when the provided URL is not valid.

Error:

Protocol error (Page.navigate): Cannot navigate to invalid URL

Network Issue

This error normally occurs when there are network issues. Ensure your connection is strong, refresh the page, and try again.

Error:

Navigation failed because browser has disconnected!

Timeout

This error occurs when the navigation timeout exceeds 30000 ms.

Error:

Navigation timeout of 30000 ms exceeded