Merge 47c7bb688f into 64d2a467b0

Only set scrollIntoView for user msg.

.gitignore

@@ -2,7 +2,6 @@
 node_modules/
 npm-debug.log
 yarn-error.log
-package-lock.json
 
 # Build output
 /.next/
@@ -38,6 +37,3 @@ Thumbs.db
 # Db
 db.sqlite
 /searxng
-
-# Dev
-docker-compose-dev.yaml

README.md

@@ -1,5 +1,21 @@
 # 🚀 Perplexica - An AI-powered search engine 🔎 <!-- omit in toc -->
 
+<div align="center" markdown="1">
+   <sup>Special thanks to:</sup>
+   <br>
+   <br>
+   <a href="https://www.warp.dev/perplexica">
+      <img alt="Warp sponsorship" width="400" src="https://github.com/user-attachments/assets/775dd593-9b5f-40f1-bf48-479faff4c27b">
+   </a>
+
+### [Warp, the AI Devtool that lives in your terminal](https://www.warp.dev/perplexica)
+
+[Available for MacOS, Linux, & Windows](https://www.warp.dev/perplexica)
+
+</div>
+
+<hr/>
+
 [![Discord](https://dcbadge.vercel.app/api/server/26aArMy8tT?style=flat&compact=true)](https://discord.gg/26aArMy8tT)
 
 ![preview](.assets/perplexica-screenshot.png?)

docker-compose.yaml

@@ -4,7 +4,7 @@ services:
     volumes:
       - ./searxng:/etc/searxng:rw
     ports:
-      - '4000:8080'
+      - 4000:8080
     networks:
       - perplexica-network
     restart: unless-stopped
@@ -19,7 +19,7 @@ services:
     depends_on:
       - searxng
     ports:
-      - '3001:3001'
+      - 3001:3001
     volumes:
       - backend-dbstore:/home/perplexica/data
       - uploads:/home/perplexica/uploads
@@ -41,7 +41,7 @@ services:
     depends_on:
       - perplexica-backend
     ports:
-      - '3000:3000'
+      - 3000:3000
     networks:
       - perplexica-network
     restart: unless-stopped

package.json

@@ -30,8 +30,8 @@
     "@iarna/toml": "^2.2.5",
     "@langchain/anthropic": "^0.2.3",
     "@langchain/community": "^0.2.16",
-    "@langchain/google-genai": "^0.0.23",
     "@langchain/openai": "^0.0.25",
+    "@langchain/google-genai": "^0.0.23",
     "@xenova/transformers": "^2.17.1",
     "axios": "^1.6.8",
     "better-sqlite3": "^11.0.0",

sample.config.toml

@@ -3,12 +3,6 @@ PORT = 3001 # Port to run the server on
 SIMILARITY_MEASURE = "cosine" # "cosine" or "dot"
 KEEP_ALIVE = "5m" # How long to keep Ollama models loaded into memory. (Instead of using -1 use "-1m")
 
-[SEARCH_ENGINE_BACKENDS] # "google" | "searxng" | "bing" | "brave" | "yacy"
-SEARCH = "searxng"
-IMAGE = "searxng"
-VIDEO = "searxng"
-NEWS = "searxng"
-
 [MODELS.OPENAI]
 API_KEY = ""
 
@@ -24,22 +18,13 @@ API_KEY = ""
 [MODELS.CUSTOM_OPENAI]
 API_KEY = ""
 API_URL = ""
+MODEL_NAME = ""
 
 [MODELS.OLLAMA]
 API_URL = "" # Ollama API URL - http://host.docker.internal:11434
 
-[SEARCH_ENGINES.GOOGLE]
+[API_ENDPOINTS]
-API_KEY = ""
+SEARXNG = "http://localhost:32768" # SearxNG API URL
-CSE_ID = ""
 
-[SEARCH_ENGINES.SEARXNG]
+[API_KEYS]
-ENDPOINT = ""
+JINA = ""
-
-[SEARCH_ENGINES.BING]
-SUBSCRIPTION_KEY = ""
-
-[SEARCH_ENGINES.BRAVE]
-API_KEY = ""
-
-[SEARCH_ENGINES.YACY]
-ENDPOINT = ""

searxng/settings.yml

@@ -15,5 +15,3 @@ server:
 engines:
   - name: wolframalpha
     disabled: false
-  - name: qwant
-    disabled: true

src/chains/imageSearchAgent.ts

@@ -7,12 +7,7 @@ import { PromptTemplate } from '@langchain/core/prompts';
 import formatChatHistoryAsString from '../utils/formatHistory';
 import { BaseMessage } from '@langchain/core/messages';
 import { StringOutputParser } from '@langchain/core/output_parsers';
-import { searchSearxng } from '../lib/searchEngines/searxng';
+import { searchSearxng } from '../lib/searxng';
-import { searchGooglePSE } from '../lib/searchEngines/google_pse';
-import { searchBraveAPI } from '../lib/searchEngines/brave';
-import { searchYaCy } from '../lib/searchEngines/yacy';
-import { searchBingAPI } from '../lib/searchEngines/bing';
-import { getImageSearchEngineBackend } from '../config';
 import type { BaseChatModel } from '@langchain/core/language_models/chat_models';
 
 const imageSearchChainPrompt = `
@@ -41,103 +36,6 @@ type ImageSearchChainInput = {
   query: string;
 };
 
-async function performImageSearch(query: string) {
-  const searchEngine = getImageSearchEngineBackend();
-  let images = [];
-
-  switch (searchEngine) {
-    case 'google': {
-      const googleResult = await searchGooglePSE(query);
-      images = googleResult.results
-        .map((result) => {
-          if (result.img_src && result.url && result.title) {
-            return {
-              img_src: result.img_src,
-              url: result.url,
-              title: result.title,
-              source: result.displayLink,
-            };
-          }
-        })
-        .filter(Boolean);
-      break;
-    }
-
-    case 'searxng': {
-      const searxResult = await searchSearxng(query, {
-        engines: ['google images', 'bing images'],
-        pageno: 1,
-      });
-      searxResult.results.forEach((result) => {
-        if (result.img_src && result.url && result.title) {
-          images.push({
-            img_src: result.img_src,
-            url: result.url,
-            title: result.title,
-          });
-        }
-      });
-      break;
-    }
-
-    case 'brave': {
-      const braveResult = await searchBraveAPI(query);
-      images = braveResult.results
-        .map((result) => {
-          if (result.img_src && result.url && result.title) {
-            return {
-              img_src: result.img_src,
-              url: result.url,
-              title: result.title,
-              source: result.url,
-            };
-          }
-        })
-        .filter(Boolean);
-      break;
-    }
-
-    case 'yacy': {
-      const yacyResult = await searchYaCy(query);
-      images = yacyResult.results
-        .map((result) => {
-          if (result.img_src && result.url && result.title) {
-            return {
-              img_src: result.img_src,
-              url: result.url,
-              title: result.title,
-              source: result.url,
-            };
-          }
-        })
-        .filter(Boolean);
-      break;
-    }
-
-    case 'bing': {
-      const bingResult = await searchBingAPI(query);
-      images = bingResult.results
-        .map((result) => {
-          if (result.img_src && result.url && result.title) {
-            return {
-              img_src: result.img_src,
-              url: result.url,
-              title: result.title,
-              source: result.url,
-            };
-          }
-        })
-        .filter(Boolean);
-      break;
-    }
-
-    default:
-      throw new Error(`Unknown search engine ${searchEngine}`);
-  }
-
-  return images;
-}
-
 const strParser = new StringOutputParser();
 
 const createImageSearchChain = (llm: BaseChatModel) => {
@@ -154,7 +52,22 @@ const createImageSearchChain = (llm: BaseChatModel) => {
     llm,
     strParser,
     RunnableLambda.from(async (input: string) => {
-      const images = await performImageSearch(input);
+      const res = await searchSearxng(input, {
+        engines: ['bing images', 'google images'],
+      });
+
+      const images = [];
+
+      res.results.forEach((result) => {
+        if (result.img_src && result.url && result.title) {
+          images.push({
+            img_src: result.img_src,
+            url: result.url,
+            title: result.title,
+          });
+        }
+      });
+
       return images.slice(0, 10);
     }),
   ]);

src/chains/videoSearchAgent.ts

@@ -7,11 +7,7 @@ import { PromptTemplate } from '@langchain/core/prompts';
 import formatChatHistoryAsString from '../utils/formatHistory';
 import { BaseMessage } from '@langchain/core/messages';
 import { StringOutputParser } from '@langchain/core/output_parsers';
-import { searchSearxng } from '../lib/searchEngines/searxng';
+import { searchSearxng } from '../lib/searxng';
-import { searchGooglePSE } from '../lib/searchEngines/google_pse';
-import { searchBraveAPI } from '../lib/searchEngines/brave';
-import { searchBingAPI } from '../lib/searchEngines/bing';
-import { getVideoSearchEngineBackend } from '../config';
 import type { BaseChatModel } from '@langchain/core/language_models/chat_models';
 
 const VideoSearchChainPrompt = `
@@ -42,102 +38,6 @@ type VideoSearchChainInput = {
 
 const strParser = new StringOutputParser();
 
-async function performVideoSearch(query: string) {
-  const searchEngine = getVideoSearchEngineBackend();
-  const youtubeQuery = `${query} site:youtube.com`;
-  let videos = [];
-
-  switch (searchEngine) {
-    case 'google': {
-      const googleResult = await searchGooglePSE(youtubeQuery);
-      googleResult.results.forEach((result) => {
-        // Use .results instead of .originalres
-        if (result.img_src && result.url && result.title) {
-          const videoId = new URL(result.url).searchParams.get('v');
-          videos.push({
-            img_src: result.img_src,
-            url: result.url,
-            title: result.title,
-            iframe_src: videoId
-              ? `https://www.youtube.com/embed/${videoId}`
-              : null,
-          });
-        }
-      });
-      break;
-    }
-
-    case 'searxng': {
-      const searxResult = await searchSearxng(query, {
-        engines: ['youtube'],
-      });
-      searxResult.results.forEach((result) => {
-        if (
-          result.thumbnail &&
-          result.url &&
-          result.title &&
-          result.iframe_src
-        ) {
-          videos.push({
-            img_src: result.thumbnail,
-            url: result.url,
-            title: result.title,
-            iframe_src: result.iframe_src,
-          });
-        }
-      });
-      break;
-    }
-
-    case 'brave': {
-      const braveResult = await searchBraveAPI(youtubeQuery);
-      braveResult.results.forEach((result) => {
-        if (result.img_src && result.url && result.title) {
-          const videoId = new URL(result.url).searchParams.get('v');
-          videos.push({
-            img_src: result.img_src,
-            url: result.url,
-            title: result.title,
-            iframe_src: videoId
-              ? `https://www.youtube.com/embed/${videoId}`
-              : null,
-          });
-        }
-      });
-      break;
-    }
-
-    case 'yacy': {
-      console.log('Not available for yacy');
-      videos = [];
-      break;
-    }
-
-    case 'bing': {
-      const bingResult = await searchBingAPI(youtubeQuery);
-      bingResult.results.forEach((result) => {
-        if (result.img_src && result.url && result.title) {
-          const videoId = new URL(result.url).searchParams.get('v');
-          videos.push({
-            img_src: result.img_src,
-            url: result.url,
-            title: result.title,
-            iframe_src: videoId
-              ? `https://www.youtube.com/embed/${videoId}`
-              : null,
-          });
-        }
-      });
-      break;
-    }
-
-    default:
-      throw new Error(`Unknown search engine ${searchEngine}`);
-  }
-
-  return videos;
-}
-
 const createVideoSearchChain = (llm: BaseChatModel) => {
   return RunnableSequence.from([
     RunnableMap.from({
@@ -152,7 +52,28 @@ const createVideoSearchChain = (llm: BaseChatModel) => {
     llm,
     strParser,
     RunnableLambda.from(async (input: string) => {
-      const videos = await performVideoSearch(input);
+      const res = await searchSearxng(input, {
+        engines: ['youtube'],
+      });
+
+      const videos = [];
+
+      res.results.forEach((result) => {
+        if (
+          result.thumbnail &&
+          result.url &&
+          result.title &&
+          result.iframe_src
+        ) {
+          videos.push({
+            img_src: result.thumbnail,
+            url: result.url,
+            title: result.title,
+            iframe_src: result.iframe_src,
+          });
+        }
+      });
+
       return videos.slice(0, 10);
     }),
   ]);

src/config.ts

@@ -10,12 +10,6 @@ interface Config {
     SIMILARITY_MEASURE: string;
     KEEP_ALIVE: string;
   };
-  SEARCH_ENGINE_BACKENDS: {
-    SEARCH: string;
-    IMAGE: string;
-    VIDEO: string;
-    NEWS: string;
-  };
   MODELS: {
     OPENAI: {
       API_KEY: string;
@@ -38,24 +32,12 @@ interface Config {
       MODEL_NAME: string;
     };
   };
-  SEARCH_ENGINES: {
+  API_ENDPOINTS: {
-    GOOGLE: {
+    SEARXNG: string;
-      API_KEY: string;
-      CSE_ID: string;
-    };
-    SEARXNG: {
-      ENDPOINT: string;
-    };
-    BING: {
-      SUBSCRIPTION_KEY: string;
-    };
-    BRAVE: {
-      API_KEY: string;
-    };
-    YACY: {
-      ENDPOINT: string;
-    };
   };
+  API_KEYS: {
+    JINA: string;
+  }
 }
 
 type RecursivePartial<T> = {
@@ -82,32 +64,8 @@ export const getAnthropicApiKey = () => loadConfig().MODELS.ANTHROPIC.API_KEY;
 
 export const getGeminiApiKey = () => loadConfig().MODELS.GEMINI.API_KEY;
 
-export const getSearchEngineBackend = () =>
-  loadConfig().SEARCH_ENGINE_BACKENDS.SEARCH;
-
-export const getImageSearchEngineBackend = () =>
-  loadConfig().SEARCH_ENGINE_BACKENDS.IMAGE || getSearchEngineBackend();
-
-export const getVideoSearchEngineBackend = () =>
-  loadConfig().SEARCH_ENGINE_BACKENDS.VIDEO || getSearchEngineBackend();
-
-export const getNewsSearchEngineBackend = () =>
-  loadConfig().SEARCH_ENGINE_BACKENDS.NEWS || getSearchEngineBackend();
-
-export const getGoogleApiKey = () => loadConfig().SEARCH_ENGINES.GOOGLE.API_KEY;
-
-export const getGoogleCseId = () => loadConfig().SEARCH_ENGINES.GOOGLE.CSE_ID;
-
-export const getBraveApiKey = () => loadConfig().SEARCH_ENGINES.BRAVE.API_KEY;
-
-export const getBingSubscriptionKey = () =>
-  loadConfig().SEARCH_ENGINES.BING.SUBSCRIPTION_KEY;
-
-export const getYacyJsonEndpoint = () =>
-  loadConfig().SEARCH_ENGINES.YACY.ENDPOINT;
-
 export const getSearxngApiEndpoint = () =>
-  process.env.SEARXNG_API_URL || loadConfig().SEARCH_ENGINES.SEARXNG.ENDPOINT;
+  process.env.SEARXNG_API_URL || loadConfig().API_ENDPOINTS.SEARXNG;
 
 export const getOllamaApiEndpoint = () => loadConfig().MODELS.OLLAMA.API_URL;
 
@@ -120,6 +78,9 @@ export const getCustomOpenaiApiUrl = () =>
 export const getCustomOpenaiModelName = () =>
   loadConfig().MODELS.CUSTOM_OPENAI.MODEL_NAME;
 
+export const getJinaApiKey = () =>
+  loadConfig().API_KEYS.JINA;
+
 const mergeConfigs = (current: any, update: any): any => {
   if (update === null || update === undefined) {
     return current;

src/lib/searchEngines/bing.ts

@@ -1,105 +0,0 @@
-import axios from 'axios';
-import { getBingSubscriptionKey } from '../../config';
-
-interface BingAPISearchResult {
-  _type: string;
-  name: string;
-  url: string;
-  displayUrl: string;
-  snippet?: string;
-  dateLastCrawled?: string;
-  thumbnailUrl?: string;
-  contentUrl?: string;
-  hostPageUrl?: string;
-  width?: number;
-  height?: number;
-  accentColor?: string;
-  contentSize?: string;
-  datePublished?: string;
-  encodingFormat?: string;
-  hostPageDisplayUrl?: string;
-  id?: string;
-  isLicensed?: boolean;
-  isFamilyFriendly?: boolean;
-  language?: string;
-  mediaUrl?: string;
-  motionThumbnailUrl?: string;
-  publisher?: string;
-  viewCount?: number;
-  webSearchUrl?: string;
-  primaryImageOfPage?: {
-    thumbnailUrl?: string;
-    width?: number;
-    height?: number;
-  };
-  video?: {
-    allowHttpsEmbed?: boolean;
-    embedHtml?: string;
-    allowMobileEmbed?: boolean;
-    viewCount?: number;
-    duration?: string;
-  };
-  image?: {
-    thumbnail?: {
-      contentUrl?: string;
-      width?: number;
-      height?: number;
-    };
-    imageInsightsToken?: string;
-    imageId?: string;
-  };
-}
-
-export const searchBingAPI = async (query: string) => {
-  try {
-    const bingApiKey = await getBingSubscriptionKey();
-    const url = new URL(`https://api.cognitive.microsoft.com/bing/v7.0/search`);
-    url.searchParams.append('q', query);
-    url.searchParams.append('responseFilter', 'Webpages,Images,Videos');
-
-    const res = await axios.get(url.toString(), {
-      headers: {
-        'Ocp-Apim-Subscription-Key': bingApiKey,
-        Accept: 'application/json',
-      },
-    });
-
-    if (res.data.error) {
-      throw new Error(`Bing API Error: ${res.data.error.message}`);
-    }
-
-    const originalres = res.data;
-
-    // Extract web, image, and video results
-    const webResults = originalres.webPages?.value || [];
-    const imageResults = originalres.images?.value || [];
-    const videoResults = originalres.videos?.value || [];
-
-    const results = webResults.map((item: BingAPISearchResult) => ({
-      title: item.name,
-      url: item.url,
-      content: item.snippet,
-      img_src:
-        item.primaryImageOfPage?.thumbnailUrl ||
-        imageResults.find((img: any) => img.hostPageUrl === item.url)
-          ?.thumbnailUrl ||
-        videoResults.find((vid: any) => vid.hostPageUrl === item.url)
-          ?.thumbnailUrl,
-      ...(item.video && {
-        videoData: {
-          duration: item.video.duration,
-          embedUrl: item.video.embedHtml?.match(/src="(.*?)"/)?.[1],
-        },
-        publisher: item.publisher,
-        datePublished: item.datePublished,
-      }),
-    }));
-
-    return { results, originalres };
-  } catch (error) {
-    const errorMessage = error.response?.data
-      ? JSON.stringify(error.response.data, null, 2)
-      : error.message || 'Unknown error';
-    throw new Error(`Bing API Error: ${errorMessage}`);
-  }
-};

src/lib/searchEngines/brave.ts

@@ -1,102 +0,0 @@
-import axios from 'axios';
-import { getBraveApiKey } from '../../config';
-
-interface BraveSearchResult {
-  title: string;
-  url: string;
-  content?: string;
-  img_src?: string;
-  age?: string;
-  family_friendly?: boolean;
-  language?: string;
-  video?: {
-    embedUrl?: string;
-    duration?: string;
-  };
-  rating?: {
-    value: number;
-    scale: number;
-  };
-  products?: Array<{
-    name: string;
-    price?: string;
-  }>;
-  recipe?: {
-    ingredients?: string[];
-    cookTime?: string;
-  };
-  meta?: {
-    fetched?: string;
-    lastCrawled?: string;
-  };
-}
-
-export const searchBraveAPI = async (
-  query: string,
-  numResults: number = 20,
-): Promise<{ results: BraveSearchResult[]; originalres: any }> => {
-  try {
-    const braveApiKey = await getBraveApiKey();
-    const url = new URL(`https://api.search.brave.com/res/v1/web/search`);
-
-    url.searchParams.append('q', query);
-    url.searchParams.append('count', numResults.toString());
-
-    const res = await axios.get(url.toString(), {
-      headers: {
-        'X-Subscription-Token': braveApiKey,
-        Accept: 'application/json',
-      },
-    });
-
-    if (res.data.error) {
-      throw new Error(`Brave API Error: ${res.data.error.message}`);
-    }
-
-    const originalres = res.data;
-    const webResults = originalres.web?.results || [];
-
-    const results: BraveSearchResult[] = webResults.map((item: any) => ({
-      title: item.title,
-      url: item.url,
-      content: item.description,
-      img_src: item.thumbnail?.src || item.deep_results?.images?.[0]?.src,
-      age: item.age,
-      family_friendly: item.family_friendly,
-      language: item.language,
-      video: item.video
-        ? {
-            embedUrl: item.video.embed_url,
-            duration: item.video.duration,
-          }
-        : undefined,
-      rating: item.rating
-        ? {
-            value: item.rating.value,
-            scale: item.rating.scale_max,
-          }
-        : undefined,
-      products: item.deep_results?.product_cluster?.map((p: any) => ({
-        name: p.name,
-        price: p.price,
-      })),
-      recipe: item.recipe
-        ? {
-            ingredients: item.recipe.ingredients,
-            cookTime: item.recipe.cook_time,
-          }
-        : undefined,
-      meta: {
-        fetched: item.meta?.fetched,
-        lastCrawled: item.meta?.last_crawled,
-      },
-    }));
-
-    return { results, originalres };
-  } catch (error) {
-    const errorMessage = error.response?.data
-      ? JSON.stringify(error.response.data, null, 2)
-      : error.message || 'Unknown error';
-    throw new Error(`Brave API Error: ${errorMessage}`);
-  }
-};

src/lib/searchEngines/google_pse.ts

@@ -1,85 +0,0 @@
-import axios from 'axios';
-import { getGoogleApiKey, getGoogleCseId } from '../../config';
-
-interface GooglePSESearchResult {
-  kind: string;
-  title: string;
-  htmlTitle: string;
-  link: string;
-  displayLink: string;
-  snippet?: string;
-  htmlSnippet?: string;
-  cacheId?: string;
-  formattedUrl: string;
-  htmlFormattedUrl: string;
-  pagemap?: {
-    videoobject: any;
-    cse_thumbnail?: Array<{
-      src: string;
-      width: string;
-      height: string;
-    }>;
-    metatags?: Array<{
-      [key: string]: string;
-      author?: string;
-    }>;
-    cse_image?: Array<{
-      src: string;
-    }>;
-  };
-  fileFormat?: string;
-  image?: {
-    contextLink: string;
-    thumbnailLink: string;
-  };
-  mime?: string;
-  labels?: Array<{
-    name: string;
-    displayName: string;
-  }>;
-}
-
-export const searchGooglePSE = async (query: string) => {
-  try {
-    const [googleApiKey, googleCseID] = await Promise.all([
-      getGoogleApiKey(),
-      getGoogleCseId(),
-    ]);
-
-    const url = new URL(`https://www.googleapis.com/customsearch/v1`);
-    url.searchParams.append('q', query);
-    url.searchParams.append('cx', googleCseID);
-    url.searchParams.append('key', googleApiKey);
-
-    const res = await axios.get(url.toString());
-
-    if (res.data.error) {
-      throw new Error(`Google PSE Error: ${res.data.error.message}`);
-    }
-
-    const originalres = res.data.items;
-
-    const results = originalres.map((item: GooglePSESearchResult) => ({
-      title: item.title,
-      url: item.link,
-      content: item.snippet,
-      img_src:
-        item.pagemap?.cse_image?.[0]?.src ||
-        item.pagemap?.cse_thumbnail?.[0]?.src ||
-        item.image?.thumbnailLink,
-      ...(item.pagemap?.videoobject?.[0] && {
-        videoData: {
-          duration: item.pagemap.videoobject[0].duration,
-          embedUrl: item.pagemap.videoobject[0].embedurl,
-        },
-      }),
-    }));
-
-    return { results, originalres };
-  } catch (error) {
-    const errorMessage = error.response?.data
-      ? JSON.stringify(error.response.data, null, 2)
-      : error.message || 'Unknown error';
-    throw new Error(`Google PSE Error: ${errorMessage}`);
-  }
-};

src/lib/searchEngines/yacy.ts

@@ -1,79 +0,0 @@
-import axios from 'axios';
-import { getYacyJsonEndpoint } from '../../config';
-
-interface YaCySearchResult {
-  channels: {
-    title: string;
-    description: string;
-    link: string;
-    image: {
-      url: string;
-      title: string;
-      link: string;
-    };
-    startIndex: string;
-    itemsPerPage: string;
-    searchTerms: string;
-    items: {
-      title: string;
-      link: string;
-      code: string;
-      description: string;
-      pubDate: string;
-      image?: string;
-      size: string;
-      sizename: string;
-      guid: string;
-      faviconUrl: string;
-      host: string;
-      path: string;
-      file: string;
-      urlhash: string;
-      ranking: string;
-    }[];
-    navigation: {
-      facetname: string;
-      displayname: string;
-      type: string;
-      min: string;
-      max: string;
-      mean: string;
-      elements: {
-        name: string;
-        count: string;
-        modifier: string;
-        url: string;
-      }[];
-    }[];
-  }[];
-}
-
-export const searchYaCy = async (query: string, numResults: number = 20) => {
-  try {
-    const yacyBaseUrl = getYacyJsonEndpoint();
-
-    const url = new URL(`${yacyBaseUrl}/yacysearch.json`);
-    url.searchParams.append('query', query);
-    url.searchParams.append('count', numResults.toString());
-
-    const res = await axios.get(url.toString());
-
-    const originalres = res.data as YaCySearchResult;
-
-    const results = originalres.channels[0].items.map((item) => ({
-      title: item.title,
-      url: item.link,
-      content: item.description,
-      img_src: item.image || null,
-      pubDate: item.pubDate,
-      host: item.host,
-    }));
-
-    return { results, originalres };
-  } catch (error) {
-    const errorMessage = error.response?.data
-      ? JSON.stringify(error.response.data, null, 2)
-      : error.message || 'Unknown error';
-    throw new Error(`YaCy Error: ${errorMessage}`);
-  }
-};

src/lib/searxng.ts

@@ -1,5 +1,5 @@
 import axios from 'axios';
-import { getSearxngApiEndpoint } from '../../config';
+import { getSearxngApiEndpoint } from '../config';
 
 interface SearxngSearchOptions {
   categories?: string[];

src/routes/config.ts

@@ -13,16 +13,6 @@ import {
   getCustomOpenaiApiUrl,
   getCustomOpenaiApiKey,
   getCustomOpenaiModelName,
-  getSearchEngineBackend,
-  getImageSearchEngineBackend,
-  getVideoSearchEngineBackend,
-  getNewsSearchEngineBackend,
-  getSearxngApiEndpoint,
-  getGoogleApiKey,
-  getGoogleCseId,
-  getBingSubscriptionKey,
-  getBraveApiKey,
-  getYacyJsonEndpoint,
 } from '../config';
 import logger from '../utils/logger';
 
@@ -71,21 +61,6 @@ router.get('/', async (_, res) => {
     config['customOpenaiApiKey'] = getCustomOpenaiApiKey();
     config['customOpenaiModelName'] = getCustomOpenaiModelName();
 
-    // Add search engine configuration
-    config['searchEngineBackends'] = {
-      search: getSearchEngineBackend(),
-      image: getImageSearchEngineBackend(),
-      video: getVideoSearchEngineBackend(),
-      news: getNewsSearchEngineBackend(),
-    };
-    
-    config['searxngEndpoint'] = getSearxngApiEndpoint();
-    config['googleApiKey'] = getGoogleApiKey();
-    config['googleCseId'] = getGoogleCseId();
-    config['bingSubscriptionKey'] = getBingSubscriptionKey();
-    config['braveApiKey'] = getBraveApiKey();
-    config['yacyEndpoint'] = getYacyJsonEndpoint();
-
     res.status(200).json(config);
   } catch (err: any) {
     res.status(500).json({ message: 'An error has occurred.' });
@@ -119,30 +94,6 @@ router.post('/', async (req, res) => {
         MODEL_NAME: config.customOpenaiModelName,
       },
     },
-    SEARCH_ENGINE_BACKENDS: config.searchEngineBackends ? {
-      SEARCH: config.searchEngineBackends.search,
-      IMAGE: config.searchEngineBackends.image,
-      VIDEO: config.searchEngineBackends.video,
-      NEWS: config.searchEngineBackends.news,
-    } : undefined,
-    SEARCH_ENGINES: {
-      GOOGLE: {
-        API_KEY: config.googleApiKey,
-        CSE_ID: config.googleCseId,
-      },
-      SEARXNG: {
-        ENDPOINT: config.searxngEndpoint,
-      },
-      BING: {
-        SUBSCRIPTION_KEY: config.bingSubscriptionKey,
-      },
-      BRAVE: {
-        API_KEY: config.braveApiKey,
-      },
-      YACY: {
-        ENDPOINT: config.yacyEndpoint,
-      },
-    },
   };
 
   updateConfig(updatedConfig);

src/routes/discover.ts

@@ -1,125 +1,42 @@
 import express from 'express';
-import { searchSearxng } from '../lib/searchEngines/searxng';
+import { searchSearxng } from '../lib/searxng';
-import { searchGooglePSE } from '../lib/searchEngines/google_pse';
-import { searchBraveAPI } from '../lib/searchEngines/brave';
-import { searchYaCy } from '../lib/searchEngines/yacy';
-import { searchBingAPI } from '../lib/searchEngines/bing';
-import { getNewsSearchEngineBackend } from '../config';
 import logger from '../utils/logger';
 
 const router = express.Router();
 
-async function performSearch(query: string, site: string) {
-  const searchEngine = getNewsSearchEngineBackend();
-  switch (searchEngine) {
-    case 'google': {
-      const googleResult = await searchGooglePSE(query);
-
-      return googleResult.originalres.map((item) => {
-        const imageSources = [
-          item.pagemap?.cse_image?.[0]?.src,
-          item.pagemap?.cse_thumbnail?.[0]?.src,
-          item.pagemap?.metatags?.[0]?.['og:image'],
-          item.pagemap?.metatags?.[0]?.['twitter:image'],
-          item.pagemap?.metatags?.[0]?.['image'],
-        ].filter(Boolean); // Remove undefined values
-
-        return {
-          title: item.title,
-          url: item.link,
-          content: item.snippet,
-          thumbnail: imageSources[0], // First available image
-          img_src: imageSources[0], // Same as thumbnail for consistency
-          iframe_src: null,
-          author: item.pagemap?.metatags?.[0]?.['og:site_name'] || site,
-          publishedDate:
-            item.pagemap?.metatags?.[0]?.['article:published_time'],
-        };
-      });
-    }
-
-    case 'searxng': {
-      const searxResult = await searchSearxng(query, {
-        engines: ['bing news'],
-        pageno: 1,
-      });
-      return searxResult.results;
-    }
-
-    case 'brave': {
-      const braveResult = await searchBraveAPI(query);
-      return braveResult.results.map((item) => ({
-        title: item.title,
-        url: item.url,
-        content: item.content,
-        thumbnail: item.img_src,
-        img_src: item.img_src,
-        iframe_src: null,
-        author: item.meta?.fetched || site,
-        publishedDate: item.meta?.lastCrawled,
-      }));
-    }
-
-    case 'yacy': {
-      const yacyResult = await searchYaCy(query);
-      return yacyResult.results.map((item) => ({
-        title: item.title,
-        url: item.url,
-        content: item.content,
-        thumbnail: item.img_src,
-        img_src: item.img_src,
-        iframe_src: null,
-        author: item?.host || site,
-        publishedDate: item?.pubDate,
-      }));
-    }
-
-    case 'bing': {
-      const bingResult = await searchBingAPI(query);
-      return bingResult.results.map((item) => ({
-        title: item.title,
-        url: item.url,
-        content: item.content,
-        thumbnail: item.img_src,
-        img_src: item.img_src,
-        iframe_src: null,
-        author: item?.publisher || site,
-        publishedDate: item?.datePublished,
-      }));
-    }
-
-    default:
-      throw new Error(`Unknown search engine ${searchEngine}`);
-  }
-}
-
 router.get('/', async (req, res) => {
   try {
-    const queries = [
-      { site: 'businessinsider.com', topic: 'AI' },
-      { site: 'www.exchangewire.com', topic: 'AI' },
-      { site: 'yahoo.com', topic: 'AI' },
-      { site: 'businessinsider.com', topic: 'tech' },
-      { site: 'www.exchangewire.com', topic: 'tech' },
-      { site: 'yahoo.com', topic: 'tech' },
-    ];
-
     const data = (
-      await Promise.all(
+      await Promise.all([
-        queries.map(async ({ site, topic }) => {
+        searchSearxng('site:businessinsider.com AI', {
-          try {
+          engines: ['bing news'],
-            const query = `site:${site} ${topic}`;
+          pageno: 1,
-            return await performSearch(query, site);
-          } catch (error) {
-            logger.error(`Error searching ${site}: ${error.message}`);
-            return [];
-          }
         }),
+        searchSearxng('site:www.exchangewire.com AI', {
+          engines: ['bing news'],
+          pageno: 1,
+        }),
+        searchSearxng('site:yahoo.com AI', {
+          engines: ['bing news'],
+          pageno: 1,
+        }),
+        searchSearxng('site:businessinsider.com tech', {
+          engines: ['bing news'],
+          pageno: 1,
+        }),
+        searchSearxng('site:www.exchangewire.com tech', {
+          engines: ['bing news'],
+          pageno: 1,
+        }),
+        searchSearxng('site:yahoo.com tech', {
+          engines: ['bing news'],
+          pageno: 1,
+        }),
+      ])
     )
-    )
+      .map((result) => result.results)
       .flat()
-      .sort(() => Math.random() - 0.5)
+      .sort(() => Math.random() - 0.5);
-      .filter((item) => item.title && item.url && item.content);
 
     return res.json({ blogs: data });
   } catch (err: any) {

src/search/metaSearchAgent.ts

@@ -17,12 +17,7 @@ import LineListOutputParser from '../lib/outputParsers/listLineOutputParser';
 import LineOutputParser from '../lib/outputParsers/lineOutputParser';
 import { getDocumentsFromLinks } from '../utils/documents';
 import { Document } from 'langchain/document';
-import { searchSearxng } from '../lib/searchEngines/searxng';
+import { searchSearxng } from '../lib/searxng';
-import { searchGooglePSE } from '../lib/searchEngines/google_pse';
-import { searchBingAPI } from '../lib/searchEngines/bing';
-import { searchBraveAPI } from '../lib/searchEngines/brave';
-import { searchYaCy } from '../lib/searchEngines/yacy';
-import { getSearchEngineBackend } from '../config';
 import path from 'path';
 import fs from 'fs';
 import computeSimilarity from '../utils/computeSimilarity';
@@ -208,37 +203,10 @@ class MetaSearchAgent implements MetaSearchAgentType {
 
           return { query: question, docs: docs };
         } else {
-          const searchEngine = getSearchEngineBackend();
+          const res = await searchSearxng(question, {
-
-          let res;
-          switch (searchEngine) {
-            case 'searxng':
-              res = await searchSearxng(question, {
             language: 'en',
             engines: this.config.activeEngines,
           });
-              break;
-            case 'google':
-              res = await searchGooglePSE(question);
-              break;
-            case 'bing':
-              res = await searchBingAPI(question);
-              break;
-            case 'brave':
-              res = await searchBraveAPI(question);
-              break;
-            case 'yacy':
-              res = await searchYaCy(question);
-              break;
-            default:
-              throw new Error(`Unknown search engine ${searchEngine}`);
-          }
-
-          if (!res?.results) {
-            throw new Error(
-              `No results found for search engine: ${searchEngine}`,
-            );
-          }
 
           const documents = res.results.map(
             (result) =>

src/utils/documents.ts

@@ -1,22 +1,30 @@
 import axios from 'axios';
 import { htmlToText } from 'html-to-text';
-import { RecursiveCharacterTextSplitter } from 'langchain/text_splitter';
+import { RecursiveCharacterTextSplitter, MarkdownTextSplitter } from 'langchain/text_splitter';
 import { Document } from '@langchain/core/documents';
 import pdfParse from 'pdf-parse';
 import logger from './logger';
+import { getJinaApiKey } from '../config';
 
 export const getDocumentsFromLinks = async ({ links }: { links: string[] }) => {
-  const splitter = new RecursiveCharacterTextSplitter();
 
+  links = links.map(link => link.startsWith('http://') || link.startsWith('https://')
+    ? link
+    : `https://${link}`)
+
+  if (getJinaApiKey()) {
+    return await getDocumentsFromJinaReader({ links });
+  }
+
+  return await getDocumentsFromLocal({ links });
+};
+
+const getDocumentsFromLocal = async ({links}: {links: string[]}) => {
+  const splitter = new RecursiveCharacterTextSplitter();
   let docs: Document[] = [];
 
   await Promise.all(
     links.map(async (link) => {
-      link =
-        link.startsWith('http://') || link.startsWith('https://')
-          ? link
-          : `https://${link}`;
-
       try {
         const res = await axios.get(link, {
           responseType: 'arraybuffer',
@@ -94,6 +102,62 @@ export const getDocumentsFromLinks = async ({ links }: { links: string[] }) => {
       }
     }),
   );
-
+  return docs;
+};
+
+const getDocumentsFromJinaReader = async ({links}: { links: string[] }) => {
+  const splitter = new MarkdownTextSplitter();
+  let docs: Document[] = [];
+
+  await Promise.all(
+    links.map(async link => {
+      try {
+        const res = await axios.get(`https://r.jina.ai/${link}`, {
+          headers: {
+            'Accept': 'application/json',
+            'Content-Type': 'application/json',
+            'Authorization': `Bearer ${getJinaApiKey()}`,
+          }
+        });
+
+        if(res.data.code === 200) {
+          const data = res.data.data
+          const splittedText = await splitter.splitText(data.content);
+          const linkDocs = splittedText.map((text) => {
+            return new Document({
+              pageContent: text,
+              metadata: {
+                title: data.title,
+                url: link,
+              },
+            });
+          });
+
+          docs.push(...linkDocs);
+          return;
+        } else {
+          docs.push(
+            new Document({
+              pageContent: `Failed to retrieve content from the link in the Jina reader API, code: ${res.data.code}`,
+              metadata: {
+                title: 'Failed to retrieve content',
+                url: link,
+              },
+            }),
+          );
+        }
+      } catch (err) {
+        docs.push(
+          new Document({
+            pageContent: `Failed to retrieve content from the link: ${err.message}`,
+            metadata: {
+              title: 'Failed to retrieve content',
+              url: link,
+            },
+          }),
+        );
+      }
+    })
+  );
   return docs;
 };

ui/app/settings/page.tsx

@@ -23,18 +23,6 @@ interface SettingsType {
   customOpenaiApiKey: string;
   customOpenaiApiUrl: string;
   customOpenaiModelName: string;
-  searchEngineBackends: {
-    search: string;
-    image: string;
-    video: string;
-    news: string;
-  };
-  searxngEndpoint: string;
-  googleApiKey: string;
-  googleCseId: string;
-  bingSubscriptionKey: string;
-  braveApiKey: string;
-  yacyEndpoint: string;
 }
 
 interface InputProps extends React.InputHTMLAttributes<HTMLInputElement> {
@@ -124,12 +112,6 @@ const Page = () => {
   const [automaticImageSearch, setAutomaticImageSearch] = useState(false);
   const [automaticVideoSearch, setAutomaticVideoSearch] = useState(false);
   const [savingStates, setSavingStates] = useState<Record<string, boolean>>({});
-  const [searchEngineBackends, setSearchEngineBackends] = useState({
-    search: '',
-    image: '',
-    video: '',
-    news: '',
-  });
 
   useEffect(() => {
     const fetchConfig = async () => {
@@ -143,16 +125,6 @@ const Page = () => {
       const data = (await res.json()) as SettingsType;
       setConfig(data);
 
-      // Set search engine backends if they exist in the response
-      if (data.searchEngineBackends) {
-        setSearchEngineBackends({
-          search: data.searchEngineBackends.search || '',
-          image: data.searchEngineBackends.image || '',
-          video: data.searchEngineBackends.video || '',
-          news: data.searchEngineBackends.news || '',
-        });
-      }
-
       const chatModelProvidersKeys = Object.keys(data.chatModelProviders || {});
       const embeddingModelProvidersKeys = Object.keys(
         data.embeddingModelProviders || {},
@@ -359,8 +331,6 @@ const Page = () => {
         localStorage.setItem('embeddingModelProvider', value);
       } else if (key === 'embeddingModel') {
         localStorage.setItem('embeddingModel', value);
-      } else if (key === 'searchEngineBackends') {
-        localStorage.setItem('searchEngineBackends', value);
       }
     } catch (err) {
       console.error('Failed to save:', err);
@@ -823,234 +793,6 @@ const Page = () => {
                 </div>
               </div>
             </SettingsSection>
-
-            <SettingsSection title="Search Engine Settings">
-              <div className="flex flex-col space-y-4">
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Default Search Engine
-                  </p>
-                  <Select
-                    value={searchEngineBackends.search}
-                    onChange={(e) => {
-                      const value = e.target.value;
-                      setSearchEngineBackends((prev) => ({
-                        ...prev,
-                        search: value,
-                      }));
-                      saveConfig('searchEngineBackends', {
-                        ...searchEngineBackends,
-                        search: value,
-                      });
-                    }}
-                    options={[
-                      { value: 'searxng', label: 'SearXNG' },
-                      { value: 'google', label: 'Google' },
-                      { value: 'bing', label: 'Bing' },
-                      { value: 'brave', label: 'Brave' },
-                      { value: 'yacy', label: 'YaCy' },
-                    ]}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Image Search Engine
-                  </p>
-                  <Select
-                    value={searchEngineBackends.image}
-                    onChange={(e) => {
-                      const value = e.target.value;
-                      setSearchEngineBackends((prev) => ({
-                        ...prev,
-                        image: value,
-                      }));
-                      saveConfig('searchEngineBackends', {
-                        ...searchEngineBackends,
-                        image: value,
-                      });
-                    }}
-                    options={[
-                      { value: '', label: 'Use Default Search Engine' },
-                      { value: 'searxng', label: 'SearXNG' },
-                      { value: 'google', label: 'Google' },
-                      { value: 'bing', label: 'Bing' },
-                      { value: 'brave', label: 'Brave' },
-                    ]}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Video Search Engine
-                  </p>
-                  <Select
-                    value={searchEngineBackends.video}
-                    onChange={(e) => {
-                      const value = e.target.value;
-                      setSearchEngineBackends((prev) => ({
-                        ...prev,
-                        video: value,
-                      }));
-                      saveConfig('searchEngineBackends', {
-                        ...searchEngineBackends,
-                        video: value,
-                      });
-                    }}
-                    options={[
-                      { value: '', label: 'Use Default Search Engine' },
-                      { value: 'searxng', label: 'SearXNG' },
-                      { value: 'google', label: 'Google' },
-                      { value: 'bing', label: 'Bing' },
-                      { value: 'brave', label: 'Brave' },
-                    ]}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    News Search Engine
-                  </p>
-                  <Select
-                    value={searchEngineBackends.news}
-                    onChange={(e) => {
-                      const value = e.target.value;
-                      setSearchEngineBackends((prev) => ({
-                        ...prev,
-                        news: value,
-                      }));
-                      saveConfig('searchEngineBackends', {
-                        ...searchEngineBackends,
-                        news: value,
-                      });
-                    }}
-                    options={[
-                      { value: '', label: 'Use Default Search Engine' },
-                      { value: 'searxng', label: 'SearXNG' },
-                      { value: 'google', label: 'Google' },
-                      { value: 'bing', label: 'Bing' },
-                      { value: 'brave', label: 'Brave' },
-                    ]}
-                  />
-                </div>
-
-                <div className="pt-4 border-t border-light-200 dark:border-dark-200">
-                  <div className="flex flex-col space-y-1">
-                    <p className="text-black/70 dark:text-white/70 text-sm">
-                      SearXNG Endpoint
-                    </p>
-                    <Input
-                      type="text"
-                      placeholder="SearXNG API Endpoint"
-                      value={config.searxngEndpoint || ''}
-                      isSaving={savingStates['searxngEndpoint']}
-                      onChange={(e) => {
-                        setConfig((prev) => ({
-                          ...prev!,
-                          searxngEndpoint: e.target.value,
-                        }));
-                      }}
-                      onSave={(value) => saveConfig('searxngEndpoint', value)}
-                    />
-                  </div>
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Google API Key
-                  </p>
-                  <Input
-                    type="text"
-                    placeholder="Google API Key"
-                    value={config.googleApiKey || ''}
-                    isSaving={savingStates['googleApiKey']}
-                    onChange={(e) => {
-                      setConfig((prev) => ({
-                        ...prev!,
-                        googleApiKey: e.target.value,
-                      }));
-                    }}
-                    onSave={(value) => saveConfig('googleApiKey', value)}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Google CSE ID
-                  </p>
-                  <Input
-                    type="text"
-                    placeholder="Google Custom Search Engine ID"
-                    value={config.googleCseId || ''}
-                    isSaving={savingStates['googleCseId']}
-                    onChange={(e) => {
-                      setConfig((prev) => ({
-                        ...prev!,
-                        googleCseId: e.target.value,
-                      }));
-                    }}
-                    onSave={(value) => saveConfig('googleCseId', value)}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Bing Subscription Key
-                  </p>
-                  <Input
-                    type="text"
-                    placeholder="Bing Subscription Key"
-                    value={config.bingSubscriptionKey || ''}
-                    isSaving={savingStates['bingSubscriptionKey']}
-                    onChange={(e) => {
-                      setConfig((prev) => ({
-                        ...prev!,
-                        bingSubscriptionKey: e.target.value,
-                      }));
-                    }}
-                    onSave={(value) => saveConfig('bingSubscriptionKey', value)}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    Brave API Key
-                  </p>
-                  <Input
-                    type="text"
-                    placeholder="Brave API Key"
-                    value={config.braveApiKey || ''}
-                    isSaving={savingStates['braveApiKey']}
-                    onChange={(e) => {
-                      setConfig((prev) => ({
-                        ...prev!,
-                        braveApiKey: e.target.value,
-                      }));
-                    }}
-                    onSave={(value) => saveConfig('braveApiKey', value)}
-                  />
-                </div>
-
-                <div className="flex flex-col space-y-1">
-                  <p className="text-black/70 dark:text-white/70 text-sm">
-                    YaCy Endpoint
-                  </p>
-                  <Input
-                    type="text"
-                    placeholder="YaCy API Endpoint"
-                    value={config.yacyEndpoint || ''}
-                    isSaving={savingStates['yacyEndpoint']}
-                    onChange={(e) => {
-                      setConfig((prev) => ({
-                        ...prev!,
-                        yacyEndpoint: e.target.value,
-                      }));
-                    }}
-                    onSave={(value) => saveConfig('yacyEndpoint', value)}
-                  />
-                </div>
-              </div>
-            </SettingsSection>
           </div>
         )
       )}

ui/components/Chat.tsx

@@ -48,11 +48,17 @@ const Chat = ({
   });
 
   useEffect(() => {
+    const scroll = () => {
       messageEnd.current?.scrollIntoView({ behavior: 'smooth' });
+    };
 
     if (messages.length === 1) {
       document.title = `${messages[0].content.substring(0, 30)} - Perplexica`;
     }
+
+    if (messages[messages.length - 1]?.role == 'user') {
+      scroll();
+    }
   }, [messages]);
 
   return (