Merge pull request #250087 from likebupt/update-tool-20230901

update vector index tool related docs

Author: prmerger-automator[bot]

articles/machine-learning/prompt-flow/tools-reference/faiss-index-lookup-tool.md

@@ -16,9 +16,6 @@ ms.date: 06/30/2023
 
 Faiss Index Lookup is a tool tailored for querying within a user-provided Faiss-based vector store. In combination with our Large Language Model (LLM) tool, it empowers users to extract contextually relevant information from a domain knowledge base.
 
-## Requirements
-- embeddingstore --extra-index-url https://azuremlsdktestpypi.azureedge.net/embeddingstore
-
 ## Prerequisites
 - Prepare an accessible path on Azure Blob Storage. Here's the guide if a new storage account needs to be created:  [Azure Storage Account](../../../storage/common/storage-account-create.md).
 - Create related Faiss-based index files on Azure Blob Storage. We support the LangChain format (index.faiss + index.pkl) for the index files, which can be prepared either by employing our EmbeddingStore SDK or following the quick guide from [LangChain documentation](https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/faiss). Please refer to [the sample notebook for creating Faiss index](https://aka.ms/pf-sample-build-faiss-index) for building index using EmbeddingStore SDK.

articles/machine-learning/prompt-flow/tools-reference/vector-db-lookup-tool.md

@@ -26,10 +26,6 @@ This tool adds support for more vector databases, including Pinecone, Weaviete,
 > Prompt flow is currently in public preview. This preview is provided without a service-level agreement, and is not recommended for production workloads. Certain features might not be supported or might have constrained capabilities.
 > For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).
 
-## Requirements
-
-- embeddingstore --extra-index-url https://azuremlsdktestpypi.azureedge.net/embeddingstore
-
 ## Prerequisites
 
 The tool searches data from a third-party vector database. To use it, you should create resources in advance and establish connections between the tool and the resource.
@@ -67,7 +63,7 @@ The following is an example JSON format response returned by the tool, which inc
 |-----------------|--------|-------------------------------------------------------------------|
 | vector          | list   | vector of the entity, the vector field name is specified in input |
 | text            | string | text of the entity, the text field name is specified in input     |
-| score           | float  | computed by the BM25 similarity algorithm                         |
+| score           | float  | @search.score from the original entity, which evaluates the similarity between the entity and the query vector                   |
 | original_entity | dict   | the original response json from search REST API                   |
 
 

articles/machine-learning/prompt-flow/tools-reference/vector-index-lookup-tool.md

@@ -20,10 +20,6 @@ Vector index lookup is a tool tailored for querying within an Azure Machine Lear
 > Prompt flow is currently in public preview. This preview is provided without a service-level agreement, and is not recommended for production workloads. Certain features might not be supported or might have constrained capabilities.
 > For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).
 
-## Requirements
-
-- embeddingstore --extra-index-url https://azuremlsdktestpypi.azureedge.net/embeddingstore
-
 ## Prerequisites
 
 - Follow the instructions from sample flow `Bring your own Data QnA` to prepare a Vector Index as an input.
@@ -51,7 +47,7 @@ The following is an example for JSON format response returned by the tool, which
 | Field Name | Type | Description |
 | ---- | ---- | ----------- |
 | text | string | Text of the entity |
-| score | float | Depends on index type defined in Vector Index. Might be value of distance or similarity |
+| score | float | Depends on index type defined in Vector Index. If index type is Faiss, score is L2 distance. If index type is Azure Cognitive Search, score is cosine similarity. |
 | metadata | dict | Customized key-value pairs provided by user when creating the index |
 | original_entity | dict | Depends on index type defined in Vector Index. The original response json from search REST API|