mirror of
https://github.com/amithkoujalgi/ollama4j.git
synced 2025-05-15 11:57:12 +02:00
Updated default request timeout to 10 seconds
This commit is contained in:
parent
e4e717b747
commit
04124cf978
@ -112,7 +112,7 @@ You will get a response similar to:
|
||||
|
||||
## Use a simple Console Output Stream Handler
|
||||
|
||||
```
|
||||
```java
|
||||
import io.github.amithkoujalgi.ollama4j.core.impl.ConsoleOutputStreamHandler;
|
||||
|
||||
public class Main {
|
||||
|
@ -9,18 +9,13 @@ import io.github.amithkoujalgi.ollama4j.core.models.chat.OllamaChatResult;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.embeddings.OllamaEmbeddingResponseModel;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.embeddings.OllamaEmbeddingsRequestModel;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.generate.OllamaGenerateRequestModel;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.CustomModelFileContentsRequest;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.CustomModelFilePathRequest;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.ModelRequest;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.OllamaChatEndpointCaller;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.OllamaGenerateEndpointCaller;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.request.*;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.Options;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.Utils;
|
||||
import java.io.BufferedReader;
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import java.io.*;
|
||||
import java.net.URI;
|
||||
import java.net.URISyntaxException;
|
||||
import java.net.http.HttpClient;
|
||||
@ -33,16 +28,16 @@ import java.time.Duration;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Base64;
|
||||
import java.util.List;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
/** The base Ollama API class. */
|
||||
/**
|
||||
* The base Ollama API class.
|
||||
*/
|
||||
@SuppressWarnings("DuplicatedCode")
|
||||
public class OllamaAPI {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(OllamaAPI.class);
|
||||
private final String host;
|
||||
private long requestTimeoutSeconds = 3;
|
||||
private long requestTimeoutSeconds = 10;
|
||||
private boolean verbose = true;
|
||||
private BasicAuth basicAuth;
|
||||
|
||||
@ -323,7 +318,7 @@ public class OllamaAPI {
|
||||
* @param modelRequest request for '/api/embeddings' endpoint
|
||||
* @return embeddings
|
||||
*/
|
||||
public List<Double> generateEmbeddings(OllamaEmbeddingsRequestModel modelRequest) throws IOException, InterruptedException, OllamaBaseException{
|
||||
public List<Double> generateEmbeddings(OllamaEmbeddingsRequestModel modelRequest) throws IOException, InterruptedException, OllamaBaseException {
|
||||
URI uri = URI.create(this.host + "/api/embeddings");
|
||||
String jsonData = modelRequest.toString();
|
||||
HttpClient httpClient = HttpClient.newHttpClient();
|
||||
@ -360,17 +355,17 @@ public class OllamaAPI {
|
||||
throws OllamaBaseException, IOException, InterruptedException {
|
||||
OllamaGenerateRequestModel ollamaRequestModel = new OllamaGenerateRequestModel(model, prompt);
|
||||
ollamaRequestModel.setOptions(options.getOptionsMap());
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel,streamHandler);
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel, streamHandler);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience method to call Ollama API without streaming responses.
|
||||
*
|
||||
* <p>
|
||||
* Uses {@link #generate(String, String, Options, OllamaStreamHandler)}
|
||||
*/
|
||||
public OllamaResult generate(String model, String prompt, Options options)
|
||||
throws OllamaBaseException, IOException, InterruptedException {
|
||||
return generate(model, prompt, options,null);
|
||||
return generate(model, prompt, options, null);
|
||||
}
|
||||
|
||||
/**
|
||||
@ -415,19 +410,19 @@ public class OllamaAPI {
|
||||
}
|
||||
OllamaGenerateRequestModel ollamaRequestModel = new OllamaGenerateRequestModel(model, prompt, images);
|
||||
ollamaRequestModel.setOptions(options.getOptionsMap());
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel,streamHandler);
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel, streamHandler);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience method to call Ollama API without streaming responses.
|
||||
*
|
||||
* <p>
|
||||
* Uses {@link #generateWithImageFiles(String, String, List, Options, OllamaStreamHandler)}
|
||||
*/
|
||||
public OllamaResult generateWithImageFiles(
|
||||
String model, String prompt, List<File> imageFiles, Options options)
|
||||
throws OllamaBaseException, IOException, InterruptedException{
|
||||
throws OllamaBaseException, IOException, InterruptedException {
|
||||
return generateWithImageFiles(model, prompt, imageFiles, options, null);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* With one or more image URLs, ask a question to a model running on Ollama server. This is a
|
||||
@ -451,12 +446,12 @@ public class OllamaAPI {
|
||||
}
|
||||
OllamaGenerateRequestModel ollamaRequestModel = new OllamaGenerateRequestModel(model, prompt, images);
|
||||
ollamaRequestModel.setOptions(options.getOptionsMap());
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel,streamHandler);
|
||||
return generateSyncForOllamaRequestModel(ollamaRequestModel, streamHandler);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience method to call Ollama API without streaming responses.
|
||||
*
|
||||
* <p>
|
||||
* Uses {@link #generateWithImageURLs(String, String, List, Options, OllamaStreamHandler)}
|
||||
*/
|
||||
public OllamaResult generateWithImageURLs(String model, String prompt, List<String> imageURLs,
|
||||
@ -466,7 +461,6 @@ public class OllamaAPI {
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* Ask a question to a model based on a given message stack (i.e. a chat history). Creates a synchronous call to the api
|
||||
* 'api/chat'.
|
||||
@ -478,14 +472,14 @@ public class OllamaAPI {
|
||||
* @throws IOException in case the responseStream can not be read
|
||||
* @throws InterruptedException in case the server is not reachable or network issues happen
|
||||
*/
|
||||
public OllamaChatResult chat(String model, List<OllamaChatMessage> messages) throws OllamaBaseException, IOException, InterruptedException{
|
||||
public OllamaChatResult chat(String model, List<OllamaChatMessage> messages) throws OllamaBaseException, IOException, InterruptedException {
|
||||
OllamaChatRequestBuilder builder = OllamaChatRequestBuilder.getInstance(model);
|
||||
return chat(builder.withMessages(messages).build());
|
||||
}
|
||||
|
||||
/**
|
||||
* Ask a question to a model using an {@link OllamaChatRequestModel}. This can be constructed using an {@link OllamaChatRequestBuilder}.
|
||||
*
|
||||
* <p>
|
||||
* Hint: the OllamaChatRequestModel#getStream() property is not implemented.
|
||||
*
|
||||
* @param request request object to be sent to the server
|
||||
@ -494,13 +488,13 @@ public class OllamaAPI {
|
||||
* @throws IOException in case the responseStream can not be read
|
||||
* @throws InterruptedException in case the server is not reachable or network issues happen
|
||||
*/
|
||||
public OllamaChatResult chat(OllamaChatRequestModel request) throws OllamaBaseException, IOException, InterruptedException{
|
||||
return chat(request,null);
|
||||
public OllamaChatResult chat(OllamaChatRequestModel request) throws OllamaBaseException, IOException, InterruptedException {
|
||||
return chat(request, null);
|
||||
}
|
||||
|
||||
/**
|
||||
* Ask a question to a model using an {@link OllamaChatRequestModel}. This can be constructed using an {@link OllamaChatRequestBuilder}.
|
||||
*
|
||||
* <p>
|
||||
* Hint: the OllamaChatRequestModel#getStream() property is not implemented.
|
||||
*
|
||||
* @param request request object to be sent to the server
|
||||
@ -510,14 +504,13 @@ public class OllamaAPI {
|
||||
* @throws IOException in case the responseStream can not be read
|
||||
* @throws InterruptedException in case the server is not reachable or network issues happen
|
||||
*/
|
||||
public OllamaChatResult chat(OllamaChatRequestModel request, OllamaStreamHandler streamHandler) throws OllamaBaseException, IOException, InterruptedException{
|
||||
public OllamaChatResult chat(OllamaChatRequestModel request, OllamaStreamHandler streamHandler) throws OllamaBaseException, IOException, InterruptedException {
|
||||
OllamaChatEndpointCaller requestCaller = new OllamaChatEndpointCaller(host, basicAuth, requestTimeoutSeconds, verbose);
|
||||
OllamaResult result;
|
||||
if(streamHandler != null){
|
||||
if (streamHandler != null) {
|
||||
request.setStream(true);
|
||||
result = requestCaller.call(request, streamHandler);
|
||||
}
|
||||
else {
|
||||
} else {
|
||||
result = requestCaller.callSync(request);
|
||||
}
|
||||
return new OllamaChatResult(result.getResponse(), result.getResponseTime(), result.getHttpStatusCode(), request.getMessages());
|
||||
|
@ -1,5 +1,15 @@
|
||||
package io.github.amithkoujalgi.ollama4j.core.models.request;
|
||||
|
||||
import io.github.amithkoujalgi.ollama4j.core.OllamaAPI;
|
||||
import io.github.amithkoujalgi.ollama4j.core.exceptions.OllamaBaseException;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.BasicAuth;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.OllamaErrorResponseModel;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.OllamaResult;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.OllamaRequestBody;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.Utils;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
@ -12,17 +22,6 @@ import java.nio.charset.StandardCharsets;
|
||||
import java.time.Duration;
|
||||
import java.util.Base64;
|
||||
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import io.github.amithkoujalgi.ollama4j.core.OllamaAPI;
|
||||
import io.github.amithkoujalgi.ollama4j.core.exceptions.OllamaBaseException;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.BasicAuth;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.OllamaErrorResponseModel;
|
||||
import io.github.amithkoujalgi.ollama4j.core.models.OllamaResult;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.OllamaRequestBody;
|
||||
import io.github.amithkoujalgi.ollama4j.core.utils.Utils;
|
||||
|
||||
/**
|
||||
* Abstract helperclass to call the ollama api server.
|
||||
*/
|
||||
@ -56,8 +55,7 @@ public abstract class OllamaEndpointCaller {
|
||||
* @throws IOException in case the responseStream can not be read
|
||||
* @throws InterruptedException in case the server is not reachable or network issues happen
|
||||
*/
|
||||
public OllamaResult callSync(OllamaRequestBody body) throws OllamaBaseException, IOException, InterruptedException{
|
||||
|
||||
public OllamaResult callSync(OllamaRequestBody body) throws OllamaBaseException, IOException, InterruptedException {
|
||||
// Create Request
|
||||
long startTime = System.currentTimeMillis();
|
||||
HttpClient httpClient = HttpClient.newHttpClient();
|
||||
@ -71,7 +69,6 @@ public abstract class OllamaEndpointCaller {
|
||||
HttpResponse<InputStream> response =
|
||||
httpClient.send(request, HttpResponse.BodyHandlers.ofInputStream());
|
||||
|
||||
|
||||
int statusCode = response.statusCode();
|
||||
InputStream responseBodyStream = response.body();
|
||||
StringBuilder responseBuffer = new StringBuilder();
|
||||
@ -96,7 +93,7 @@ public abstract class OllamaEndpointCaller {
|
||||
OllamaErrorResponseModel.class);
|
||||
responseBuffer.append(ollamaResponseModel.getError());
|
||||
} else {
|
||||
boolean finished = parseResponseAndAddToBuffer(line,responseBuffer);
|
||||
boolean finished = parseResponseAndAddToBuffer(line, responseBuffer);
|
||||
if (finished) {
|
||||
break;
|
||||
}
|
||||
|
Loading…
x
Reference in New Issue
Block a user