You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+18-18Lines changed: 18 additions & 18 deletions
Original file line number
Diff line number
Diff line change
@@ -21,8 +21,6 @@ The demo shows a Retrieval-Augmented Generation using the following modules:
21
21
* OLLAMA local LLM embeddings model
22
22
* OLLAMA local LLM LLama2 model for chat
23
23
24
-
## Introduction
25
-
26
24
This demo is based on a early draft example of **Spring AI API**'s implementation for the **Oracle 23ai** as vector store, according to the specifications reported here: **[Vector DBs](https://docs.spring.io/spring-ai/reference/api/vectordbs.html)**.
27
25
28
26
There are two different types of files that contribute to the Retrieval-Augmented Generation (RAG) system in this solution:
@@ -113,7 +111,7 @@ The following tests have also been implemented, to debug and play with the solut
113
111
114
112
Chat client that doesn't use the RAG pipeline. It could be used as a baseline to show the differences between a response provided by the LLM service as-is (OpenAI, OLLAMA) and an augmented request. It's useful to check if any public content has been used for LLM training, whether the response is near to what you expect, without providing your documents.
115
113
116
-
## 0. Prerequisites and setup
114
+
## 0. Prerequisites
117
115
118
116
### JDBC driver for Oracle DB 23ai
119
117
@@ -154,26 +152,28 @@ Set env with command in a shell:
154
152
source ./env.sh
155
153
```
156
154
157
-
#### DB23ai setup
155
+
##1. Setup
158
156
159
-
Download and install from [Oracle Database Free Get Started](https://www.oracle.com/database/free/get-started/) site an **Oracle Database 23ai Free**, for example, as a docker container in this way:
157
+
### Oracle Database 23ai setup
160
158
161
-
```bash
162
-
docker run -d -p 1521:1521 --name db23ai container-registry.oracle.com/database/free:latest
163
-
docker exec db23ai ./setPassword.sh manager
164
-
```
159
+
1. Download and install from [Oracle Database Free Get Started](https://www.oracle.com/database/free/get-started/) site an **Oracle Database 23ai Free**, for example, as a docker container in this way:
165
160
166
-
After startup, download and install an Oracle Instant Client from the same [site](https://www.oracle.com/database/free/get-started/), and connect to the instance as shown here:
161
+
```bash
162
+
docker run -d -p 1521:1521 --name db23ai container-registry.oracle.com/database/free:latest
163
+
docker exec db23ai ./setPassword.sh manager
164
+
```
167
165
168
-
```bash
169
-
sqlplus sys/manager@"${VECTORDB}:1521/FREEPDB1" as sysdba
170
-
```
166
+
2. After startup, download and install an Oracle Instant Client from the same [site](https://www.oracle.com/database/free/get-started/), and connect to the instance as shown here:
171
167
172
-
If running locally:
168
+
```bash
169
+
sqlplus sys/manager@"${VECTORDB}:1521/FREEPDB1" as sysdba
170
+
```
173
171
174
-
```bash
175
-
sqlplus sys/manager@"localhost:1521/FREEPDB1" as sysdba
176
-
```
172
+
3. If running locally:
173
+
174
+
```bash
175
+
sqlplus sys/manager@"localhost:1521/FREEPDB1" as sysdba
176
+
```
177
177
178
178
to create a **vector** user to run the example:
179
179
@@ -552,7 +552,7 @@ The following shape and images are recommended for the server: (it will require
0 commit comments