Oracle
In this example, we will show how to use the Oracle as in DB-GPT Datasource. Using Oracle to implement Datasource can, to some extent, alleviate the uncertainty and interpretability issues brought about by vector database retrieval.
Install Dependenciesâ
First, you need to install the dbgpt oracle datasource library.
uv sync --all-packages \
--extra "base" \
--extra "datasource_oracle" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "dbgpts"
Prepare Oracleâ
Prepare Oracle database service, reference-Oracle Installation.
Then run the following command to start the webserver:
uv run dbgpt start webserver --config configs/dbgpt-proxy-openai.toml
Optionally, you can also use the following command to start the webserver:
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/dbgpt-proxy-openai.toml