upgrade to SB 3.4 and polish observability (#130)

* upgrade to SB 3.4 and polish observability * upgrade docker * fix : tests * polish
rajadilipkolli · Dec 24, 2024 · 8815e97 · 8815e97
1 parent b037b5c
commit 8815e97
Show file tree

Hide file tree

Showing 10 changed files with 177 additions and 103 deletions.
diff --git a/rag/rag-springai-ollama-llm/docker/docker-compose.yml b/rag/rag-springai-ollama-llm/docker/docker-compose.yml
@@ -1,19 +1,62 @@
 services:
-    ollama:
-        image: langchain4j/ollama-llama3:latest
-        ports:
-          - '11434:11434'
-    redis-stack:
-        image: redis/redis-stack-server
-        ports:
-          - '6379:6379'
-    lgtm-stack:
-        image: grafana/otel-lgtm:0.8.0
-        extra_hosts: ['host.docker.internal:host-gateway']
-        container_name: lgtm-stack
-        environment:
-          - OTEL_METRIC_EXPORT_INTERVAL=500
-        ports:
-          - "3000:3000"
-          - "4317:4317"
-          - "4318:4318"
+
+  ollama:
+    container_name: ollama
+    image: ollama/ollama:latest
+    ports:
+      - '11434:11434'
+
+  postgresqldb:
+    container_name: postgresqldb
+    image: pgvector/pgvector:pg17
+    extra_hosts: [ 'host.docker.internal:host-gateway' ]
+    restart: always
+    environment:
+      - POSTGRES_USER=appuser
+      - POSTGRES_PASSWORD=secret
+      - POSTGRES_DB=appdb
+      - PGPASSWORD=secret
+    logging:
+      options:
+        max-size: 10m
+        max-file: "3"
+    ports:
+      - '5432:5432'
+    healthcheck:
+      test: "pg_isready -U appuser -d appdb"
+      interval: 2s
+      timeout: 20s
+      retries: 10
+
+  pgadmin:
+    container_name: pgadmin_container
+    image: dpage/pgadmin4
+    extra_hosts: [ 'host.docker.internal:host-gateway' ]
+    environment:
+      PGADMIN_DEFAULT_EMAIL: ${PGADMIN_DEFAULT_EMAIL:[email protected]}
+      PGADMIN_DEFAULT_PASSWORD: ${PGADMIN_DEFAULT_PASSWORD:-admin}
+      PGADMIN_CONFIG_SERVER_MODE: "False"
+      PGADMIN_CONFIG_MASTER_PASSWORD_REQUIRED: "False"
+    ports:
+      - "${PGADMIN_PORT:-5050}:80"
+    depends_on:
+      postgresqldb:
+        condition: service_healthy
+    volumes:
+      - ./docker_pgadmin_servers.json:/pgadmin4/servers.json
+    entrypoint:
+      - "/bin/sh"
+      - "-c"
+      - "/bin/echo 'postgresqldb:5432:*:appuser:secret' > /tmp/pgpassfile && chmod 600 /tmp/pgpassfile && /entrypoint.sh"
+
+  lgtm-stack:
+    image: grafana/otel-lgtm:0.8.1
+    extra_hosts: [ 'host.docker.internal:host-gateway' ]
+    container_name: lgtm-stack
+    environment:
+      - OTEL_METRIC_EXPORT_INTERVAL=500
+    ports:
+      - "3000:3000"
+      - "4317:4317"
+      - "4318:4318"
+      - "9090:9090"
diff --git a/rag/rag-springai-ollama-llm/docker/docker_pgadmin_servers.json b/rag/rag-springai-ollama-llm/docker/docker_pgadmin_servers.json
@@ -0,0 +1,14 @@
+{
+    "Servers": {
+        "1": {
+            "Name": "Docker Compose DB",
+            "Group": "Servers",
+            "Port": 5432,
+            "Username": "appuser",
+            "Host": "postgresqldb",
+            "SSLMode": "prefer",
+            "MaintenanceDB": "appdb",
+            "PassFile": "/tmp/pgpassfile"
+        }
+    }
+}
diff --git a/rag/rag-springai-ollama-llm/pom.xml b/rag/rag-springai-ollama-llm/pom.xml
@@ -5,7 +5,7 @@
     <parent>
         <groupId>org.springframework.boot</groupId>
         <artifactId>spring-boot-starter-parent</artifactId>
-        <version>3.3.6</version>
+        <version>3.4.1</version>
         <relativePath/> <!-- lookup parent from repository -->
     </parent>
     <groupId>com.learning.ai</groupId>
@@ -16,7 +16,8 @@
 
     <properties>
         <java.version>21</java.version>
-        <spring-ai.version>1.0.0-M4</spring-ai.version>
+        <spring-ai.version>1.0.0-M5</spring-ai.version>
+        <otelInstrumentation.version>2.10.0-alpha</otelInstrumentation.version>
         <spotless.version>2.43.0</spotless.version>
     </properties>
 
@@ -39,11 +40,7 @@
         </dependency>
         <dependency>
             <groupId>org.springframework.ai</groupId>
-            <artifactId>spring-ai-redis-store-spring-boot-starter</artifactId>
-        </dependency>
-        <dependency>
-            <groupId>org.apache.commons</groupId>
-            <artifactId>commons-pool2</artifactId>
+            <artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>
         </dependency>
         <dependency>
             <groupId>org.springframework.ai</groupId>
@@ -56,7 +53,14 @@
         <dependency>
             <groupId>org.springdoc</groupId>
             <artifactId>springdoc-openapi-starter-webmvc-ui</artifactId>
-            <version>2.6.0</version>
+            <version>2.7.0</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.springframework.boot</groupId>
+            <artifactId>spring-boot-devtools</artifactId>
+            <scope>runtime</scope>
+            <optional>true</optional>
         </dependency>
 
         <dependency>
@@ -76,6 +80,17 @@
             <groupId>io.micrometer</groupId>
             <artifactId>micrometer-registry-otlp</artifactId>
         </dependency>
+        <dependency>
+            <groupId>net.ttddyy.observation</groupId>
+            <artifactId>datasource-micrometer-spring-boot</artifactId>
+            <version>1.0.6</version>
+        </dependency>
+        <dependency>
+            <groupId>io.opentelemetry.instrumentation</groupId>
+            <artifactId>opentelemetry-logback-appender-1.0</artifactId>
+            <scope>runtime</scope>
+        </dependency>
+
         <dependency>
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-test</artifactId>
@@ -97,16 +112,14 @@
             <scope>test</scope>
         </dependency>
         <dependency>
-            <groupId>com.redis.testcontainers</groupId>
-            <artifactId>testcontainers-redis</artifactId>
+            <groupId>org.testcontainers</groupId>
+            <artifactId>grafana</artifactId>
             <scope>test</scope>
-            <version>1.6.4</version>
         </dependency>
         <dependency>
             <groupId>org.testcontainers</groupId>
-            <artifactId>grafana</artifactId>
+            <artifactId>postgresql</artifactId>
             <scope>test</scope>
-            <version>1.20.4</version>
         </dependency>
         <dependency>
             <groupId>io.rest-assured</groupId>
@@ -124,6 +137,13 @@
                 <type>pom</type>
                 <scope>import</scope>
             </dependency>
+            <dependency>
+                <groupId>io.opentelemetry.instrumentation</groupId>
+                <artifactId>opentelemetry-instrumentation-bom-alpha</artifactId>
+                <version>${otelInstrumentation.version}</version>
+                <type>pom</type>
+                <scope>import</scope>
+            </dependency>
         </dependencies>
     </dependencyManagement>
 
@@ -144,7 +164,7 @@
                 <configuration>
                     <java>
                         <palantirJavaFormat>
-                            <version>2.47.0</version>
+                            <version>2.50.0</version>
                         </palantirJavaFormat>
                         <importOrder/>
                         <removeUnusedImports/>

diff --git a/...-llm/src/main/java/com/learning/ai/llmragwithspringai/config/RestClientBuilderConfig.java b/...-llm/src/main/java/com/learning/ai/llmragwithspringai/config/RestClientBuilderConfig.java
diff --git a/...ai-ollama-llm/src/main/java/com/learning/ai/llmragwithspringai/service/AIChatService.java b/...ai-ollama-llm/src/main/java/com/learning/ai/llmragwithspringai/service/AIChatService.java
@@ -3,10 +3,9 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.ai.chat.client.ChatClient;
-import org.springframework.ai.chat.client.advisor.QuestionAnswerAdvisor;
-import org.springframework.ai.chat.model.ChatResponse;
-import org.springframework.ai.chat.model.Generation;
-import org.springframework.ai.vectorstore.SearchRequest;
+import org.springframework.ai.chat.client.advisor.RetrievalAugmentationAdvisor;
+import org.springframework.ai.rag.generation.augmentation.ContextualQueryAugmenter;
+import org.springframework.ai.rag.retrieval.search.VectorStoreDocumentRetriever;
 import org.springframework.ai.vectorstore.VectorStore;
 import org.springframework.stereotype.Service;
 
@@ -15,33 +14,29 @@ public class AIChatService {
 
     private static final Logger LOGGER = LoggerFactory.getLogger(AIChatService.class);
 
-    private static final String template =
-            """
-            You are a helpful assistant, conversing with a user about the subjects contained in a set of documents.
-            Use the information from the DOCUMENTS section to provide accurate answers. If unsure or if the answer
-            isn't found in the DOCUMENTS section, simply state that you don't know the answer.
+    private final ChatClient aiClient;
 
-            DOCUMENTS:
-            {question_answer_context}
+    public AIChatService(ChatClient.Builder builder, VectorStore vectorStore) {
 
-            """;
+        var documentRetriever = VectorStoreDocumentRetriever.builder()
+                .vectorStore(vectorStore)
+                .similarityThreshold(0.50)
+                .build();
 
-    private final ChatClient aiClient;
-    private final VectorStore vectorStore;
+        var queryAugmenter =
+                ContextualQueryAugmenter.builder().allowEmptyContext(true).build();
 
-    public AIChatService(ChatClient.Builder builder, VectorStore vectorStore) {
-        this.aiClient = builder.build();
-        this.vectorStore = vectorStore;
+        RetrievalAugmentationAdvisor retrievalAugmentationAdvisor = RetrievalAugmentationAdvisor.builder()
+                .documentRetriever(documentRetriever)
+                .queryAugmenter(queryAugmenter)
+                .build();
+        this.aiClient =
+                builder.clone().defaultAdvisors(retrievalAugmentationAdvisor).build();
     }
 
     public String chat(String query) {
-        ChatResponse aiResponse = aiClient.prompt()
-                .advisors(new QuestionAnswerAdvisor(vectorStore, SearchRequest.query(query), template))
-                .user(query)
-                .call()
-                .chatResponse();
+        String aiResponse = aiClient.prompt().user(query).call().content();
         LOGGER.info("Response received from call :{}", aiResponse);
-        Generation generation = aiResponse.getResult();
-        return (generation != null) ? generation.getOutput().getContent() : "";
+        return aiResponse;
     }
 }
diff --git a/...lama-llm/src/main/java/com/learning/ai/llmragwithspringai/service/DataIndexerService.java b/...lama-llm/src/main/java/com/learning/ai/llmragwithspringai/service/DataIndexerService.java
@@ -1,6 +1,7 @@
 package com.learning.ai.llmragwithspringai.service;
 
 import java.util.Map;
+import java.util.Objects;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.ai.document.DocumentReader;
@@ -58,11 +59,11 @@ public void loadData(Resource documentResource) {
                 return documents;
             };
             vectorStore.accept(metadataEnricher.apply(tokenTextSplitter.apply(documentReader.get())));
-            LOGGER.info("Loaded document to redis vector database.");
+            LOGGER.info("Loaded document to vector database.");
         }
     }
 
     public long count() {
-        return this.vectorStore.similaritySearch("*").size();
+        return Objects.requireNonNull(this.vectorStore.similaritySearch("*")).size();
     }
 }
diff --git a/rag/rag-springai-ollama-llm/src/main/resources/application-local.properties b/rag/rag-springai-ollama-llm/src/main/resources/application-local.properties
@@ -0,0 +1,11 @@
+## WARNING: Development-only configuration
+## The following setting will DELETE existing vector store data on startup
+spring.ai.vectorstore.pgvector.removeExistingVectorStoreTable=true
+spring.ai.ollama.baseUrl=http://localhost:11434
+
+
+logging.level.org.springframework.ai.rag=debug
+
+spring.datasource.url=jdbc:postgresql://localhost/appdb
+spring.datasource.username=appuser
+spring.datasource.password=secret
diff --git a/rag/rag-springai-ollama-llm/src/main/resources/application.properties b/rag/rag-springai-ollama-llm/src/main/resources/application.properties
@@ -3,26 +3,32 @@ spring.application.name=rag-springai-ollama-llm
 spring.threads.virtual.enabled=true
 spring.mvc.problemdetails.enabled=true
 
+spring.ai.ollama.init.pull-model-strategy=WHEN_MISSING
 spring.ai.ollama.chat.options.model=mistral
 spring.ai.ollama.chat.options.temperature=0.3
 spring.ai.ollama.chat.options.top-k=2
 spring.ai.ollama.chat.options.top-p=0.2
 
 spring.ai.ollama.embedding.options.model=nomic-embed-text
 
-spring.ai.vectorstore.redis.index=vector_store
-spring.ai.vectorstore.redis.prefix=ai
-spring.ai.vectorstore.redis.initialize-schema=true
+#PgVector
+spring.ai.vectorstore.observations.include-query-response=true
+spring.ai.vectorstore.pgvector.initialize-schema=true
 
-spring.ai.ollama.baseUrl=http://localhost:11434
+spring.http.client.connect-timeout=PT1M
+spring.http.client.read-timeout=PT5M
 
 spring.testcontainers.beans.startup=parallel
 
 ##Observability
 spring.ai.chat.observations.include-completion=true
 spring.ai.chat.observations.include-prompt=true
+spring.ai.chat.client.observations.include-input=true
 
 management.endpoints.web.exposure.include=*
 management.metrics.tags.service.name=${spring.application.name}
 management.tracing.sampling.probability=1.0
 management.otlp.tracing.endpoint=http://localhost:4318/v1/traces
+management.otlp.logging.endpoint=http://localhost:4318/v1/logs
+
+logging.level.org.springframework.ai.rag=info
diff --git a/rag/rag-springai-ollama-llm/src/main/resources/logback-spring.xml b/rag/rag-springai-ollama-llm/src/main/resources/logback-spring.xml
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configuration>
+    <include resource="org/springframework/boot/logging/logback/base.xml" />
+
+    <appender name="OpenTelemetry"
+              class="io.opentelemetry.instrumentation.logback.appender.v1_0.OpenTelemetryAppender">
+        <captureExperimentalAttributes>true</captureExperimentalAttributes>
+        <captureCodeAttributes>true</captureCodeAttributes>
+        <captureKeyValuePairAttributes>true</captureKeyValuePairAttributes>
+    </appender>
+
+    <root level="INFO">
+        <appender-ref ref="OpenTelemetry"/>
+    </root>
+
+</configuration>