enable support for HNSW in dataprep and retriever for better performance

[leslieluyu]

Description

For improve performance with large dataset, enable support HNSW in dataprep and retriever

• In dataprep

  1. add parameter of vector_schema of from_texts_return_keys
  2. add VECTOR_SCHEMA environment variable to enable easily switch the algorithm

• In retriver

  1. add ENABLE_SCHEMA in config.py
  2. add logic of using index_schema=INDEX_SCHEMA
  3. add redis_schema_hnsw.yml for enable HNSW

Issues

List the issue or RFC link this PR is working on. If there is no such link, please mark it as n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

Describe the tests that you ran to verify your changes.

see the performance comparison between this PR(HNSW) and v1.3 oob(FLAT) when ingested pubmed_100files.txt(≈3.7M chunks)