Versions Compared

Old Version 10

changes.mady.by.user Luis Valverde

Saved on

compared with

New Version Current

changes.mady.by.user Steven Peraza

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

The Calculate Vector Stage is the first step of semantic search. In this stage the vector is calculated or retrieved based on the model given by the user. There are 3 types of models enumerated.

  1. Saga model: This model retrieves the vector from saga, an entry with the value is require in saga. The value needs to be the same as the saga stage name.
  2. Open AI model: This model calculates the vector with Open AI API, this needs the credentials to make calls to the API as environment variables. These are the supported Open AI models:

    1. text-embedding-ada-002

    2. text-search-ada-doc-001

    3. text-search-curie-doc-001

  3. Sentence Transformer GTR: This model calculates the vector with the GTR component of the python library sentence_transformer. These are the supported GTR models:
    1. sentence-transformers/gtr-t5-base
    2. sentence-transformers/gtr-t5-large
    3. sentence-transformers/gtr-t5-xl
    4. sentence-transformers/gtr-t5-xxl

The Calculate Vector Stage stores the vector on intermediate for the Create Query Stage usage.

Table of Contents
maxLevel3

Properties

PropertyDescriptionDefaultTypeRequired
QPL Config?
typeStage class name-stringYes
No
enableEnable stage for executiontrueboolean
No
No
nameName for this specific stage"vector"stringNo
No
save_to_intermediateIf true, the result of the stage will be stored in the intermediate instead of the final sectionfalseboolean
No
No
expand_resultIndicates if the result of this stage should be expanded into the final data dictionary instead of being appended as usualfalsebooleanNo
No
halt_on_exceptionIndicates if the pipeline should be interrupted in case of an exceptiontrueboolean
No
No
modelIndicates the model to be used to calculate or retrieve the vectors. Its restricted by the types allowed by the enum.

EnumSaga.SAGA

EnumYes
No

open_ai_api_key

This is your Open AI key to use the chat from your service provideros.environ.get('OPEN_AI_API_KEY', 'default_key')string
No
No

open_ai_api_base_url

Base url of your service provider for Open AI chat.os.environ.get('OPEN_AI_API_BASE_URL', 'default_url')string
No
No

open_ai_api_type

API type, its restricted by the types allowed by the enum.EnumOpenAiType.AZUREEnumNo
No

open_ai_api_version

API version of the Open AI chatos.environ.get('OPEN_AI_API_VERSION', '2023-03-15-preview')stringNo

azure_deployment_name

Deployment name for the model (AZURE ONLY).os.environ.get('OPEN_AI_AZURE_DEPLOYMENT_NAME', None)Union[string, None]No

path_to_input

Path to the input in the intermediate that is going to be targeted by this stage to calculate the vectorqstringNo


Calculate Vector Stage Intermediate Parameters

The Calculate Vector Stage offers a range of parameters that can be passed via the intermediate input to customize your search request or modify the configuration of the current stage. These parameters provide flexibility and control over the search process.


Calculated filters for . This with knn parameter get stored on the same variable as a tuple second parameter of the tuple.
ParameterDescription
qA string query for performing a search. Can be transformed into engine-specific queries using PyQPL (Query Parser Language).
queryEngine-specific queries for the search.
knnEngine-specific queries specifically for k-nearest neighbor (KNN) searches.
filters search, this is the
sizeNumber of results to return from the search request. Overrides the size specified in the configuration.
from/startIndicates the starting point for retrieving search results. Can be used interchangeably with the page parameter.
pageIt can be an alternative to from/start. It calculates the start based on the size parameter.
fetch_fieldsList of fields to fetch for each search result. Overrides the fields specified in the configuration.
exclude_fieldsList of fields to exclude from the search results. Overrides the fields specified in the configuration.
scrollScroll ID used to retrieve large numbers of results from a single search request, similar to a cursor in a traditional database.
operatorThe default operator for query string queries: AND or OR. Overrides the default operator specified in the configuration.
vectorCalculated vectors use to create the knn query.
target text for the calculate vector. Its path is specified in path_to_input property
Tip

Remember that the intermediate can be fill with either other stages or the original request body that trigger the pipeline, making this essentially REST API parameters


Example Configuration

Code Block
languagepy
themeDJango
_calculate_vector_stage = CalculateVectorStage(
    enabletype=True'CalculateVectorStage',
    save_to_intermediate=True,
    expand_result=False,
    halt_on_exception=Falseenable=True,
    name=VECTOR_STAGE_NAME'VectorStage',
    model=EnumOpenAI.OPENAI_EMBEDDING_ADA,
    open_ai_api_key=os.environ.get('OPEN_AI_API_KEY')'yourapikey',
    open_ai_api_base_url=os.environ.get('OPEN_AI_API_BASE_URL')'baseurl',
	azure_deployment_name=my_deployment_name,
     open open_ai_api_type=EnumOpenAiType.AZURE,
    open_ai_api_version='2023-03-15-preview',
    type='CalculateVectorStage	path_to_input='q'
)