admin/hermione
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Delete try/catch block in step

Browse Source
This commit is contained in:
Emanuele Ferrelli
2025-07-08 10:01:51 +02:00
parent 170c5515eb
commit be31b1e83c
1 changed files with 55 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
src/main/java/com/olympus/hermione/stepSolvers/EmbeddingDocTempSolver.java
View File

@@ -4,9 +4,11 @@ import ch.qos.logback.classic.Logger;
import com.olympus.hermione.models.ScenarioExecution;
import com.olympus.hermione.utility.AttributeParser;
import java.io.File;
import java.io.IOException;
import java.util.Collections;
import java.util.List;
import org.apache.tika.Tika;
import org.apache.tika.exception.TikaException;
import org.slf4j.LoggerFactory;
import org.springframework.ai.document.Document;
import org.springframework.ai.transformer.splitter.TokenTextSplitter;
@@ -20,11 +22,9 @@ public class EmbeddingDocTempSolver extends StepSolver {
private int min_chunk_length_to_embed;
private int max_num_chunks;
Logger logger = (Logger) LoggerFactory.getLogger(EmbeddingDocTempSolver.class);
private void loadParameters(){
private void loadParameters() {
logger.info("Loading parameters");
this.scenarioExecution.getExecSharedMap().put("scenario_execution_id", this.scenarioExecution.getId());
logger.info("Scenario Execution ID: {}", this.scenarioExecution.getId());
@@ -36,40 +36,39 @@ public class EmbeddingDocTempSolver extends StepSolver {
this.path_file = attributeParser.parse((String) this.step.getAttributes().get("path_file"));
logger.info("Parsed path_file: {}", this.path_file);
if(this.step.getAttributes().containsKey("default_chunk_size")){
if (this.step.getAttributes().containsKey("default_chunk_size")) {
this.default_chunk_size = (int) this.step.getAttributes().get("default_chunk_size");
logger.info("Parsed default_chunk_size from attributes: {}", this.default_chunk_size);
}else{
} else {
this.default_chunk_size = 8000;
logger.info("default_chunk_size not found in attributes, using default: 8000");
}
if(this.step.getAttributes().containsKey("min_chunk_size")){
if (this.step.getAttributes().containsKey("min_chunk_size")) {
this.min_chunk_size = (int) this.step.getAttributes().get("min_chunk_size");
}else{
} else {
this.min_chunk_size = 50;
logger.info("min_chunk_size not found in attributes, using default: 50");
}
if(this.step.getAttributes().containsKey("min_chunk_length_to_embed")){
if (this.step.getAttributes().containsKey("min_chunk_length_to_embed")) {
this.min_chunk_length_to_embed = (int) this.step.getAttributes().get("min_chunk_length_to_embed");
}else{
} else {
this.min_chunk_length_to_embed = 50;
logger.info("min_chunk_length_to_embed not found in attributes, using default: 50");
}
if(this.step.getAttributes().containsKey("max_num_chunks")){
if (this.step.getAttributes().containsKey("max_num_chunks")) {
this.max_num_chunks = (int) this.step.getAttributes().get("max_num_chunks");
}else{
} else {
this.max_num_chunks = 1000;
logger.info("max_num_chunks not found in attributes, using default: 1000");
}
}
@Override
public ScenarioExecution solveStep(){
public ScenarioExecution solveStep() {
try{
logger.info("Solving step: " + this.step.getName());
this.scenarioExecution.setCurrentStepId(this.step.getStepId());
logger.info("Loading parameters for step: {}", this.step.getName());
@@ -79,13 +78,20 @@ public class EmbeddingDocTempSolver extends StepSolver {
logger.info("Reading file from path: {}", this.path_file);
Tika tika = new Tika();
tika.setMaxStringLength(-1);
String text = tika.parseToString(file);
String text;
try {
text = tika.parseToString(file);
} catch (IOException | TikaException e) {
logger.error("Error parsing file: ", e);
throw new RuntimeException("Error parsing file", e);
}
logger.info("File read successfully. Length: {} characters", text.length());
Document myDoc = new Document(text);
List<Document> docs = Collections.singletonList(myDoc);
logger.info("Initializing TokenTextSplitter with default_chunk_size={}, min_chunk_size={}, min_chunk_length_to_embed={}, max_num_chunks={}",
logger.info(
"Initializing TokenTextSplitter with default_chunk_size={}, min_chunk_size={}, min_chunk_length_to_embed={}, max_num_chunks={}",
this.default_chunk_size, this.min_chunk_size, this.min_chunk_length_to_embed, this.max_num_chunks);
TokenTextSplitter splitter = new TokenTextSplitter(this.default_chunk_size,
this.min_chunk_size,
@@ -101,7 +107,7 @@ public class EmbeddingDocTempSolver extends StepSolver {
for (Document splitDoc : splitDocs) {
splitDoc.getMetadata().put("KsDocumentId", this.scenario_execution_id);
splitDoc.getMetadata().put("KsDocumentIndex",docIndex.toString());
splitDoc.getMetadata().put("KsDocumentIndex", docIndex.toString());
splitDoc.getMetadata().put("KsDoctype", "temp");
logger.info("Adding split document with index {} to vector store", docIndex);
docIndex++;
@@ -116,15 +122,10 @@ public class EmbeddingDocTempSolver extends StepSolver {
vectorStore.add(batch);
logger.info("Added batch of {} documents to vector store (from {} to {})", batch.size(), i, end - 1);
}
//vectorStore.add(splitDocs);
// vectorStore.add(splitDocs);
});
logger.info("All documents embedded and added to vector store successfully");
}catch (Exception e){
logger.error("Error while solvingStep: "+e.getMessage(), e);
e.printStackTrace();
}
logger.info("Setting next step id: {}", this.step.getNextStepId());
this.scenarioExecution.setNextStepId(this.step.getNextStepId());