package com.custom.webui.service.impl;
|
|
import com.custom.webui.config.props.LlmProperties;
|
import com.custom.webui.exception.BusinessException;
|
import com.custom.webui.service.LlmService;
|
import com.fasterxml.jackson.databind.JsonNode;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
import com.fasterxml.jackson.databind.node.ArrayNode;
|
import com.fasterxml.jackson.databind.node.ObjectNode;
|
import lombok.extern.slf4j.Slf4j;
|
import org.springframework.boot.autoconfigure.condition.ConditionalOnProperty;
|
import org.springframework.stereotype.Service;
|
|
import java.io.BufferedReader;
|
import java.io.IOException;
|
import java.io.InputStream;
|
import java.io.InputStreamReader;
|
import java.net.HttpURLConnection;
|
import java.net.URI;
|
import java.nio.charset.StandardCharsets;
|
import java.util.List;
|
|
/**
|
* Ollama LLM 实现,对接 {@code POST /api/chat}。
|
*
|
* <p><b>为什么用 HttpURLConnection 而不是 RestTemplate?</b>
|
* Ollama 的流式响应是 NDJSON(每行一个 JSON 对象),RestTemplate 没有开箱即用的
|
* 「逐行消费」能力,需要写自定义 ResponseExtractor 反而更绕。
|
* 直接用 {@link HttpURLConnection} + {@link BufferedReader#readLine()} 最直观,
|
* 也避免引入 WebClient 这套响应式依赖(会显著增大打包体积)。
|
*
|
* <p>请求体示例:
|
* <pre>
|
* {
|
* "model": "qwen2.5:7b",
|
* "messages": [{"role":"user","content":"你好"}],
|
* "stream": true,
|
* "options": {"temperature":0.7,"top_p":0.9,"num_ctx":8192}
|
* }
|
* </pre>
|
*
|
* <p>响应体每行形如:
|
* <pre>
|
* {"model":"qwen2.5:7b","message":{"role":"assistant","content":"你"},"done":false}
|
* {"model":"qwen2.5:7b","message":{"role":"assistant","content":""},"done":true,...}
|
* </pre>
|
*
|
* <p>前置条件:Ollama 必须监听 0.0.0.0 才能被其他进程/机器访问 ——
|
* 启动命令 {@code OLLAMA_HOST=0.0.0.0 ollama serve}。
|
*/
|
@Slf4j
|
@Service
|
@ConditionalOnProperty(name = "webui.llm.provider", havingValue = "ollama", matchIfMissing = true)
|
public class OllamaLlmService implements LlmService {
|
|
private final LlmProperties properties;
|
private final ObjectMapper objectMapper;
|
|
public OllamaLlmService(LlmProperties properties, ObjectMapper objectMapper) {
|
this.properties = properties;
|
this.objectMapper = objectMapper;
|
log.info("LLM 实现: Ollama, baseUrl={}, defaultModel={}",
|
properties.getOllama().getBaseUrl(), properties.getOllama().getDefaultModel());
|
}
|
|
@Override
|
public void streamChat(List<LlmMessage> messages, LlmOptions options, TokenConsumer consumer) {
|
HttpURLConnection conn = null;
|
try {
|
conn = openConnection("/api/chat", properties.getOllama().getTimeoutMillis());
|
String body = buildRequestBody(messages, options, true);
|
writeBody(conn, body);
|
|
int status = conn.getResponseCode();
|
if (status != 200) {
|
String err = readErrorBody(conn);
|
log.error("Ollama 返回非 200: status={}, url={}/api/chat, body={}",
|
status, properties.getOllama().getBaseUrl(), err);
|
throw BusinessException.serverError(describeFailure(status, err, resolveModel(options)));
|
}
|
|
try (BufferedReader reader = new BufferedReader(
|
new InputStreamReader(conn.getInputStream(), StandardCharsets.UTF_8))) {
|
String line;
|
while ((line = reader.readLine()) != null) {
|
if (line.isBlank()) {
|
continue;
|
}
|
JsonNode node;
|
try {
|
node = objectMapper.readTree(line);
|
} catch (IOException parseError) {
|
// 单行解析失败不应中断整个流,跳过即可
|
log.warn("无法解析 Ollama 响应行: {}", abbreviate(line));
|
continue;
|
}
|
|
// 错误字段优先:Ollama 可能在中途返回 {"error": "..."}
|
if (node.hasNonNull("error")) {
|
throw BusinessException.serverError("Ollama 错误: " + node.get("error").asText());
|
}
|
|
JsonNode messageNode = node.get("message");
|
if (messageNode != null) {
|
// 思考内容(qwen3 / deepseek-r1 等 reasoning 模型)
|
JsonNode thinkingNode = messageNode.get("thinking");
|
if (thinkingNode != null && !thinkingNode.asText().isEmpty()) {
|
if (properties.getOllama().isIncludeThinking()) {
|
consumer.accept(thinkingNode.asText(), true);
|
}
|
}
|
JsonNode contentNode = messageNode.get("content");
|
if (contentNode != null && !contentNode.asText().isEmpty()) {
|
consumer.accept(contentNode.asText(), false);
|
}
|
}
|
|
if (node.path("done").asBoolean(false)) {
|
break;
|
}
|
}
|
}
|
} catch (BusinessException e) {
|
throw e;
|
} catch (IOException e) {
|
log.error("调用 Ollama 失败", e);
|
throw BusinessException.serverError(
|
"无法连接 LLM 服务 " + properties.getOllama().getBaseUrl()
|
+ ",请确认 Ollama 已启动(OLLAMA_HOST=0.0.0.0 ollama serve)。原因: " + e.getMessage());
|
} finally {
|
if (conn != null) {
|
conn.disconnect();
|
}
|
}
|
}
|
|
@Override
|
public String complete(List<LlmMessage> messages, LlmOptions options) {
|
HttpURLConnection conn = null;
|
try {
|
conn = openConnection("/api/chat", 30000);
|
writeBody(conn, buildRequestBody(messages, options, false));
|
|
if (conn.getResponseCode() != 200) {
|
log.warn("Ollama 非流式调用失败, status={}", conn.getResponseCode());
|
return null;
|
}
|
try (InputStream in = conn.getInputStream()) {
|
JsonNode node = objectMapper.readTree(in);
|
JsonNode contentNode = node.path("message").path("content");
|
return contentNode.isMissingNode() ? null : contentNode.asText();
|
}
|
} catch (Exception e) {
|
// 标题生成属于锦上添花,失败不抛出,由调用方回退到截断标题
|
log.warn("Ollama 非流式调用异常: {}", e.getMessage());
|
return null;
|
} finally {
|
if (conn != null) {
|
conn.disconnect();
|
}
|
}
|
}
|
|
@Override
|
public String defaultModel() {
|
return properties.getOllama().getDefaultModel();
|
}
|
|
// ==================== 内部辅助 ====================
|
|
private HttpURLConnection openConnection(String path, int timeoutMillis) throws IOException {
|
String baseUrl = properties.getOllama().getBaseUrl();
|
// 去掉末尾斜杠,避免拼出 //api/chat
|
if (baseUrl.endsWith("/")) {
|
baseUrl = baseUrl.substring(0, baseUrl.length() - 1);
|
}
|
URI uri = URI.create(baseUrl + path);
|
HttpURLConnection conn = (HttpURLConnection) uri.toURL().openConnection();
|
conn.setRequestMethod("POST");
|
conn.setDoOutput(true);
|
conn.setConnectTimeout(5000);
|
conn.setReadTimeout(timeoutMillis);
|
conn.setRequestProperty("Content-Type", "application/json; charset=UTF-8");
|
conn.setRequestProperty("Accept", "application/x-ndjson");
|
return conn;
|
}
|
|
/** 组装请求体 JSON */
|
private String buildRequestBody(List<LlmMessage> messages, LlmOptions options, boolean stream)
|
throws IOException {
|
ObjectNode root = objectMapper.createObjectNode();
|
root.put("model", resolveModel(options));
|
root.put("stream", stream);
|
|
ArrayNode messageArray = root.putArray("messages");
|
for (LlmMessage m : messages) {
|
ObjectNode item = messageArray.addObject();
|
item.put("role", m.role());
|
item.put("content", m.content());
|
}
|
|
ObjectNode optionsNode = root.putObject("options");
|
Double temperature = options.temperature() != null
|
? options.temperature() : properties.getDefaults().getTemperature();
|
Double topP = options.topP() != null
|
? options.topP() : properties.getDefaults().getTopP();
|
Integer numCtx = options.numCtx() != null
|
? options.numCtx() : properties.getDefaults().getNumCtx();
|
|
if (temperature != null) {
|
optionsNode.put("temperature", temperature);
|
}
|
if (topP != null) {
|
optionsNode.put("top_p", topP);
|
}
|
if (numCtx != null) {
|
optionsNode.put("num_ctx", numCtx);
|
}
|
|
return objectMapper.writeValueAsString(root);
|
}
|
|
/** 模型名解析优先级:会话参数 > 全局配置 */
|
private String resolveModel(LlmOptions options) {
|
if (options != null && options.modelName() != null && !options.modelName().isBlank()) {
|
return options.modelName().trim();
|
}
|
return properties.getOllama().getDefaultModel();
|
}
|
|
/**
|
* 拼装「能定位问题」的失败信息。
|
*
|
* <p><b>为什么要专门写这个方法</b>:早先这里只有一句
|
* 「请确认模型 X 已通过 {@code ollama pull} 下载」。问题在于,
|
* 触发非 200 的原因里,**模型没下载只占很小一部分**:
|
* <ul>
|
* <li>Ollama 根本没启动(连接被拒,此时连非 200 都走不到)</li>
|
* <li>base-url 被指到了别的服务上 —— 比如 OpenAI 兼容服务,
|
* 它只有 {@code /v1/chat/completions},没有 {@code /api/chat},
|
* 于是返回 404</li>
|
* </ul>
|
* 这几种情况用户都会看到「模型没下载」,然后花大量时间去
|
* {@code ollama pull},而真实原因与模型毫无关系。
|
*
|
* <p>所以这里把**实际请求地址**和**协议是否匹配的判断**一并给出。
|
* 尤其 404:它几乎从不意味着「模型没下载」,因为模型不存在时
|
* Ollama 返回的是 200 + 流内 {@code {"error": "model ... not found"}}。
|
*/
|
private String describeFailure(int status, String err, String model) {
|
String baseUrl = properties.getOllama().getBaseUrl();
|
StringBuilder sb = new StringBuilder(256);
|
sb.append("LLM 服务返回错误 (HTTP ").append(status).append(")。")
|
.append("请求地址: ").append(baseUrl).append("/api/chat")
|
.append(",模型: ").append(model).append("。");
|
|
if (status == 404) {
|
sb.append("404 基本可以断定**不是**模型没下载 —— Ollama 的模型不存在时返回的是 HTTP 200 "
|
+ "和流内的 model not found 消息。404 说明这个地址上跑的不是 Ollama:")
|
.append("它的原生接口是 /api/chat,而 OpenAI 兼容服务(vLLM / LM Studio / SGLang / one-api 等)")
|
.append("只有 /v1/chat/completions。若你用的是后者,请把 webui.llm.provider 改为 openai-compat,")
|
.append("并把 webui.llm.openaiCompat.base-url 配成以 /v1 结尾的地址。");
|
} else if (status == 401 || status == 403) {
|
sb.append("这通常是网关或鉴权层拒绝,请检查 webui.llm.ollama.base-url 是否指向了需要 API Key 的服务。");
|
} else {
|
sb.append("请确认 Ollama 已启动,且模型已下载(`ollama pull ").append(model).append("`)。");
|
}
|
|
sb.append("详情: ").append(sanitize(err));
|
return sb.toString();
|
}
|
|
/**
|
* 清洗错误响应体。
|
*
|
* <p>踩过的坑:某些服务(实测那个 node 写的转发器)返回的 404 文本
|
* 后面跟着几十个 NUL 字节,原样塞进 JSON 之后前端提示里显示成一串方块,
|
* 用户完全看不出内容。这里把控制字符去掉并限长。
|
*/
|
private String sanitize(String body) {
|
if (body == null || body.isBlank()) {
|
return "(无响应体)";
|
}
|
String cleaned = body.replaceAll("[\\p{Cntrl}&&[^\r\n\t]]", "").trim();
|
if (cleaned.isEmpty()) {
|
return "(响应体只有控制字符,内容不可读)";
|
}
|
return abbreviate(cleaned);
|
}
|
|
private void writeBody(HttpURLConnection conn, String body) throws IOException {
|
try (var out = conn.getOutputStream()) {
|
out.write(body.getBytes(StandardCharsets.UTF_8));
|
out.flush();
|
}
|
}
|
|
/** 读取错误响应体,供日志与前端提示使用 */
|
private String readErrorBody(HttpURLConnection conn) {
|
try (InputStream err = conn.getErrorStream()) {
|
if (err == null) {
|
return "(无响应体)";
|
}
|
return new String(err.readAllBytes(), StandardCharsets.UTF_8);
|
} catch (IOException e) {
|
return "(读取错误响应失败)";
|
}
|
}
|
|
private String abbreviate(String s) {
|
return s.length() > 200 ? s.substring(0, 200) + "..." : s;
|
}
|
}
|