feat(ChatKnowledge): ChatKnowledge Support Keyword Retrieve

[Aries-ckt]

Close #1623

Description

• ChatKnowledge Support Keyword Retrieve
  
• Add IndexStoreBase in RAG module
• Refactor connector module

When to Use Keyword Retrieve:

Looking for something ultra-specific and already understand the topic
Research is narrowly focused with clear objectives
Queries contain unique proper nouns like brand names
Needs require fast results more than exhaustive relevancy For precise or time-sensitive queries, keyword search will target the exact terms efficiently. Vector search may meander with unnecessary semantic expansion.

How Has This Been Tested?

ChatKnowledge App

1. install Elasticsearch, refer https://www.elastic.co/guide/en/elasticsearch/reference/current/install-elasticsearch.html
2. set Elasticsearch envrionment in .env

ELASTICSEARCH_URL=localhost
ELASTICSEARCH_PORT=9200
ELASTICSEARCH_USERNAME=elastic
ELASTICSEARCH_PASSWORD=dbgpt

3. create knowledge space via Full Text
4. Knowledge Chat via Keyword Search
   

Test IndexStore in examples

# test keyword rag
python examples/rag/keyword_rag_example.py
# test embedding rag
python examples/rag/embedding_rag_example.py
# test graph rag
python examples/rag/graph_rag_example.py

Snapshots:

Include snapshots for easier review.

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules

[csunny]

r+

[fangyinc]

LGTM