Semantic Search Node

The semantic search nodes embeds and queries documents semantically at run time.

In contrast to the knowledge base, which is a permanent store of data, documents embedded using the semantic search node are immediately deleted after the pipeline finishes running.

Node Inputs

1. Search Query: The query that will be used to search the embedded documents semantically for relevant pieces

   1. Type: Text

2. Documents for Search: The text that will be semantically searched

   1. Type: Text

Node Parameters

Face of the node

1. Embedding model: Select an embedding model to use to embed the documents

In the gear:

1. Max chunks per query: the maximum number of pieces of data to be returned per query

2. Enable Filter: enable the ability to write a metadata filter

3. Enable Context: enable a text field to provide additional context for the search query

4. Re-rank documents: Performs an additional Reranking step to reorder the documents by relevance to the query.

5. Score Cutoff: The minimum relevancy score (between 0 and 1) that each piece of data will have semantically to the query

6. Retrieval Units: Return the most relevant chunks (text content) or Documents (will return document metadata)

7. Transform Query: Transform the query for better results

8. Answer Multiple Questions: Extract separate questions from the query and retrieve content separately for each question to improve search performance

9. Expand Query: Expand query to improve semantic search

10. Do Advanced QA: Use additional LLM calls to analyze each document to improve answer correctness

11. Show Immediate Steps: Display the process the knowledge base is conducting at a given time in the chatUI

12. Format Context for a LLM: Do an additional LLM call to format output

Node Outputs

1. Chunks: Semantically similar chunks retrieved from the knowledge base

2. Type: List of text

3. Example usage: {{semantic_search_0.chunks}}

If Do Advanced QA is checked:

1. Response: the response of the additional LLMs calls conducted on each document

2. Type: Text

3. Example usage: {{semantic_search_0.response}}

Considerations

• Use a semantic search node when your pipeline loads new data at run time for querying. Use a Knowledge Base Reader node when you want to query previously loaded data that has already been loaded.

• If the semantic search node is not returning relevant information to a query, try increasing the number of max chunks per query in the gear of the knowledge base

• For debugging purposes, you may attach an output node to the semantic search node to view the chunks that are returned for the query

Example

The below example is a pipeline that allows the user to ask a question to a website. Hence, it has two inputs: the question (input_1) and the URL of the website (input_2).

The website link is passed to the scrape URL node, which scrapes the website and passes the content to the “Documents for Search” input on the semantic search node. Input_1 (the user question) is passed to the Search Query input of the semantic search node.

Then, the openAI node both receives the user question (input_1) and the semantic similar chunks (semantic_search_1) to generate a response that is displayed by the output node.