Searching with Trieve

​

Overview

We provide the ability for you to search your data in a fast and performant manner. We have multiple search paradigms, which are exposed through the search over chunks route, the search within groups route, and the search over groups route.

​

Different Search Paradigms

We offer three different search strategies for you to choose from:

1. Search over chunks: This strategy allows you to search all of your chunks independently. This is useful when your chunks are independent and do not need to be grouped together.
2. Search within groups: This strategy lets you constrain your results to within a selected group. This is useful for searching distinct groups within your dataset independently.
3. Search over groups: This strategy allows you to search over the groups of chunks within your dataset. This returns the groups and the top chunks within each group that matched your query, providing better search quality for datasets with highly related chunks within groups.

​

Important Parameters

• query: The user query that is embedded and searched against the dataset.
• search_type: Can be semantic, fulltext, or hybrid.
  • Semantic: Uses cosine distance to determine the most relevant results.
  • Fulltext: Uses a SPLADE model to find the most relevant results.
  • Hybrid: Uses a reranker model that pulls one page of results from both fulltext and semantic searches to find the most relevant results.
• page: The page of chunks to fetch. Pages are 1-indexed.
• page_size: This lets you tune the number of results that are returned.
• highlight_results: Enables subsentence highlighting of relevant portions of the text.
• slim_chunks: Excludes chunk_html from the returned results to reduce network bandwidth. Useful for large chunks.
• recency_bias: A value from 0-1 that tunes how much the recency of chunks (based on the timestamp field) affects the ranking.
• filters: Apply filters to get exactly the results you want.

​

Search Customizations

​

Embedding Models

Trieve supports multiple embedding models that can be used to search over your data. You can specify the embedding model to use in the server_configuration field when creating a dataset.

​

Reranker models

Trieve supports multiple reranker models that can be used to rerank the search results.

Currently, Trieve supports bge-reranker-large and cohere’s rerank-v3.5 model.

​

BAAI/bge-reranker-large

bge-reranker-large is a model by the Beijing Academy of Artificial Intelligence (BAAI) and is hosted by Trieve. This model does not require any additional configuration. and will be used by default on all hybrid searches.

To switch your reranker model to cohere’s rerank-v3.5, make a request to the update dataset route. With the following Parameters

curl --request POST \
  --url https://api.trieve.ai/api/dataset \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \
  --data '{
    "dataset_name": "New Dataset", // Replace with a name for your dataset
    "organization_id": "********-****-****-****-************",

    // Update with the desired configurations for your dataset
    "server_configuration": {
      "RERANKER_MODEL_NAME":"bge-reranker-large"
    }
}'

​

Cohere rerank-v3.5

rerank-v3.5 is a model hosted by docs.cohere.com. To use this model, you must provide the cohere_api_key in the server_configuration field when creating a dataset.

To switch your reranker model to cohere’s rerank-v3.5, make a request to the update dataset route. With the following Parameters

curl --request POST \
  --url https://api.trieve.ai/api/dataset \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \
  --data '{
    "dataset_name": "New Dataset", // Replace with a name for your dataset
    "organization_id": "********-****-****-****-************",

    // Update with the desired configurations for your dataset
    "server_configuration": {
      "RERANKER_BASE_URL":"https://api.cohere.com/v2",
      "RERANKER_MODEL_NAME":"rerank-v3.5"
      "RERANKER_API_KEY":"<cohere_api_key>"
    }
}'