Check:
dnf -y install oracle-database-preinstall-23ai
Prenos softvera:
https://www.oracle.com/database/technologies/free-downloads.html
dnf -y install oracle-database-free-23ai-1.0-1.el8.x86_64.rpm
Konfiguriranje : /etc/init.d/oracle-free-23ai configure
| Lokacije programske opreme | Namen |
|---|---|
/opt/oracle | Oracle base. This is the root of the Oracle Database Free directory tree. |
/opt/oracle/product/23ai/dbhomeFree | Oracle home. This home is where the Oracle Database Free is installed. It contains the directories of the Oracle Database Free executables and network files. |
/opt/oracle/oradata/FREE | Database files. |
/opt/oracle/diag subdirectories | Diagnostic logs. The database alert log is /opt/oracle/diag/rdbms/free/FREE/trace/alert_FREE.log |
/opt/oracle/cfgtoollogs/dbca/FREE | Database creation logs. The FREE.log file contains the results of the database creation script execution. |
/etc/sysconfig/oracle-free-23ai.conf | Configuration default parameters. |
/etc/init.d/oracle-free-23ai | Configuration and services script. |
Nastavitev spremenljivk po namestitvi
export ORACLE_SID=FREE v
export ORAENV_ASK=NO
. /opt/oracle/product/23ai/dbhomeFree/bin/oraen
Start baze
sqlplus / as sysdba
startup
lsnrctl start
Preveri požarno pregrado
# systemctl status firewalld
Po potrebi stopiraj
# systemctl stop firewalld
Getting Started with Vector Search in 23c AI | Vili Tajnić
Link:
https://github.com/ViliTajnic/OracleVectorSearch23ai
Oracle Database 23ai – Oracle AI Vector Search & Retrieval Augmented Generation (RAG) with Oracle APEX | Madhusudhan Rao
This is part 2 of the Oracle Database 23ai series of technical articles. While searching for large external language models to get answers to the questions will solve one type of problem, the requirements might also differ slightly from searching for Corporate internal knowledge repositories and datasets.
For example, consider that your company is working on internal research and has several internal PDFs that should be searched by the AI Search engine rather than going and looking for public LLM for questions that concern us. Also, the possibility of traditional RDBMS queries along with Gen AI queries will make it more powerful.
In this article, we will understand Open Neural Network Exchange (ONNX) concepts, create our own ONNX models, Use these models to read PDFs and vectorise content, and Develop an Oracle APEX Vector-based search engine that can query internal knowledge repositories or sometimes also query external large language models.
About Retrieval augmented generation (RAG)
RAG uses the results of similarity search to improve the accuracy and contextual relevance of large language model responses to questions about business data. RAG helps identify contextually relevant private data that the LLM may not have been trained on and then uses it to augment user prompts so LLMs can respond with greater accuracy. RAG helps organizations provide customized answers to business questions without the high cost of retraining or fine-tuning the LLMs.
The desire to get higher quality answers from LLMs is universal, spanning many industries. Some examples of using RAG for improved accuracy include the following:
- Chatbots for internal and external users
- Document searches and summaries
- Language to code synthesis
- Answers to questions that require specialized, domain-specific knowledge
https://www.linkedin.com/pulse/oracle-database-23ai-ai-vector-search-retrieval-augmented-rao-bqkcf