Multiple database for NLtoSQL query engine

[PradiptaAtByteIQMind-Graph2023]

Hi! Team

I want to connect with multiple databases for the chatbot application. how can i achieve this one?

[dosubot[bot]]

🤖

Hey there, @PradiptaAtByteIQMind-Graph2023!

I'm Dosu, a friendly bot here to assist you while we wait for our human maintainers. I'm here to help you squash bugs, answer your questions, and guide you to be an awesome contributor. Don't hesitate to ask if you need anything!

To connect multiple databases for a chatbot application using the NLtoSQL query engine, you can utilize the SQLJoinQueryEngine class provided in the LlamaIndex framework. This class allows you to "join" a SQL database results with another query engine. It can decide whether it needs to query the SQL database or the other query engine. If it decides to query the SQL database, it will first query the SQL database, then decide whether to augment information with retrieved results from the other query engine.

Here is a basic example of how you can use it:

from llama_index.query_engine.sql_join_query_engine import SQLJoinQueryEngine
from llama_index.tools.query_engine import QueryEngineTool
from llama_index.indices.struct_store.sql_query import NLSQLTableQueryEngine

# Initialize your SQL query tools
sql_query_tool1 = QueryEngineTool(query_engine=NLSQLTableQueryEngine(database1))
sql_query_tool2 = QueryEngineTool(query_engine=NLSQLTableQueryEngine(database2))

# Initialize SQLJoinQueryEngine
sql_join_query_engine = SQLJoinQueryEngine(
    sql_query_tool=sql_query_tool1,
    other_query_tool=sql_query_tool2,
)

# Now you can use sql_join_query_engine to query your databases
response = sql_join_query_engine.query(query_bundle)

In this example, database1 and database2 are your two databases. query_bundle is the query you want to execute. The SQLJoinQueryEngine will decide which database to query based on the selector you provide (by default it uses the LLMSingleSelector or PydanticSingleSelector from the service context). If it decides to query the SQL database, it will first query the SQL database, then decide whether to augment information with retrieved results from the other query engine.

Please replace database1 and database2 with your actual database connections, and query_bundle with the actual query you want to execute.

You can find more details about the SQLJoinQueryEngine class in the LlamaIndex codebase.

Sources

• llama_index/query_engine/sql_join_query_engine.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[PradiptaAtByteIQMind-Graph2023]

Similarily how to achieve multiple mongodb database and collection query?