feat(app): add new agents directory

src/lib/agents/media/image.ts

@@ -0,0 +1,107 @@
+/* I don't think can be classified as agents but to keep the structure consistent i guess ill keep it here */
+
+import {
+  RunnableSequence,
+  RunnableMap,
+  RunnableLambda,
+} from '@langchain/core/runnables';
+import { ChatPromptTemplate } from '@langchain/core/prompts';
+import formatChatHistoryAsString from '@/lib/utils/formatHistory';
+import { BaseMessage } from '@langchain/core/messages';
+import { StringOutputParser } from '@langchain/core/output_parsers';
+import { searchSearxng } from '@/lib/searxng';
+import type { BaseChatModel } from '@langchain/core/language_models/chat_models';
+import LineOutputParser from '@/lib/outputParsers/lineOutputParser';
+
+const imageSearchChainPrompt = `
+You will be given a conversation below and a follow up question. You need to rephrase the follow-up question so it is a standalone question that can be used by the LLM to search the web for images.
+You need to make sure the rephrased question agrees with the conversation and is relevant to the conversation.
+Output only the rephrased query wrapped in an XML <query> element. Do not include any explanation or additional text.
+`;
+
+type ImageSearchChainInput = {
+  chat_history: BaseMessage[];
+  query: string;
+};
+
+interface ImageSearchResult {
+  img_src: string;
+  url: string;
+  title: string;
+}
+
+const strParser = new StringOutputParser();
+
+const createImageSearchChain = (llm: BaseChatModel) => {
+  return RunnableSequence.from([
+    RunnableMap.from({
+      chat_history: (input: ImageSearchChainInput) => {
+        return formatChatHistoryAsString(input.chat_history);
+      },
+      query: (input: ImageSearchChainInput) => {
+        return input.query;
+      },
+    }),
+    ChatPromptTemplate.fromMessages([
+      ['system', imageSearchChainPrompt],
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nWhat is a cat?\n</follow_up>',
+      ],
+      ['assistant', '<query>A cat</query>'],
+
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nWhat is a car? How does it work?\n</follow_up>',
+      ],
+      ['assistant', '<query>Car working</query>'],
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nHow does an AC work?\n</follow_up>',
+      ],
+      ['assistant', '<query>AC working</query>'],
+      [
+        'user',
+        '<conversation>{chat_history}</conversation>\n<follow_up>\n{query}\n</follow_up>',
+      ],
+    ]),
+    llm,
+    strParser,
+    RunnableLambda.from(async (input: string) => {
+      const queryParser = new LineOutputParser({
+        key: 'query',
+      });
+
+      return await queryParser.parse(input);
+    }),
+    RunnableLambda.from(async (input: string) => {
+      const res = await searchSearxng(input, {
+        engines: ['bing images', 'google images'],
+      });
+
+      const images: ImageSearchResult[] = [];
+
+      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);
+    }),
+  ]);
+};
+
+const handleImageSearch = (
+  input: ImageSearchChainInput,
+  llm: BaseChatModel,
+) => {
+  const imageSearchChain = createImageSearchChain(llm);
+  return imageSearchChain.invoke(input);
+};
+
+export default handleImageSearch;

src/lib/agents/media/video.ts

@@ -0,0 +1,110 @@
+import {
+  RunnableSequence,
+  RunnableMap,
+  RunnableLambda,
+} from '@langchain/core/runnables';
+import { ChatPromptTemplate } from '@langchain/core/prompts';
+import formatChatHistoryAsString from '@/lib/utils/formatHistory';
+import { BaseMessage } from '@langchain/core/messages';
+import { StringOutputParser } from '@langchain/core/output_parsers';
+import { searchSearxng } from '@/lib/searxng';
+import type { BaseChatModel } from '@langchain/core/language_models/chat_models';
+import LineOutputParser from '@/lib/outputParsers/lineOutputParser';
+
+const videoSearchChainPrompt = `
+You will be given a conversation below and a follow up question. You need to rephrase the follow-up question so it is a standalone question that can be used by the LLM to search Youtube for videos.
+You need to make sure the rephrased question agrees with the conversation and is relevant to the conversation.
+Output only the rephrased query wrapped in an XML <query> element. Do not include any explanation or additional text.
+`;
+
+type VideoSearchChainInput = {
+  chat_history: BaseMessage[];
+  query: string;
+};
+
+interface VideoSearchResult {
+  img_src: string;
+  url: string;
+  title: string;
+  iframe_src: string;
+}
+
+const strParser = new StringOutputParser();
+
+const createVideoSearchChain = (llm: BaseChatModel) => {
+  return RunnableSequence.from([
+    RunnableMap.from({
+      chat_history: (input: VideoSearchChainInput) => {
+        return formatChatHistoryAsString(input.chat_history);
+      },
+      query: (input: VideoSearchChainInput) => {
+        return input.query;
+      },
+    }),
+    ChatPromptTemplate.fromMessages([
+      ['system', videoSearchChainPrompt],
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nHow does a car work?\n</follow_up>',
+      ],
+      ['assistant', '<query>How does a car work?</query>'],
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nWhat is the theory of relativity?\n</follow_up>',
+      ],
+      ['assistant', '<query>Theory of relativity</query>'],
+      [
+        'user',
+        '<conversation>\n</conversation>\n<follow_up>\nHow does an AC work?\n</follow_up>',
+      ],
+      ['assistant', '<query>AC working</query>'],
+      [
+        'user',
+        '<conversation>{chat_history}</conversation>\n<follow_up>\n{query}\n</follow_up>',
+      ],
+    ]),
+    llm,
+    strParser,
+    RunnableLambda.from(async (input: string) => {
+      const queryParser = new LineOutputParser({
+        key: 'query',
+      });
+      return await queryParser.parse(input);
+    }),
+    RunnableLambda.from(async (input: string) => {
+      const res = await searchSearxng(input, {
+        engines: ['youtube'],
+      });
+
+      const videos: VideoSearchResult[] = [];
+
+      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);
+    }),
+  ]);
+};
+
+const handleVideoSearch = (
+  input: VideoSearchChainInput,
+  llm: BaseChatModel,
+) => {
+  const videoSearchChain = createVideoSearchChain(llm);
+  return videoSearchChain.invoke(input);
+};
+
+export default handleVideoSearch;

src/lib/agents/suggestions/index.ts

@@ -0,0 +1,55 @@
+import { RunnableSequence, RunnableMap } from '@langchain/core/runnables';
+import ListLineOutputParser from '@/lib/outputParsers/listLineOutputParser';
+import { PromptTemplate } from '@langchain/core/prompts';
+import formatChatHistoryAsString from '@/lib/utils/formatHistory';
+import { BaseMessage } from '@langchain/core/messages';
+import { BaseChatModel } from '@langchain/core/language_models/chat_models';
+import { ChatOpenAI } from '@langchain/openai';
+
+const suggestionGeneratorPrompt = `
+You are an AI suggestion generator for an AI powered search engine. You will be given a conversation below. You need to generate 4-5 suggestions based on the conversation. The suggestion should be relevant to the conversation that can be used by the user to ask the chat model for more information.
+You need to make sure the suggestions are relevant to the conversation and are helpful to the user. Keep a note that the user might use these suggestions to ask a chat model for more information. 
+Make sure the suggestions are medium in length and are informative and relevant to the conversation.
+
+Provide these suggestions separated by newlines between the XML tags <suggestions> and </suggestions>. For example:
+
+<suggestions>
+Tell me more about SpaceX and their recent projects
+What is the latest news on SpaceX?
+Who is the CEO of SpaceX?
+</suggestions>
+
+Conversation:
+{chat_history}
+`;
+
+type SuggestionGeneratorInput = {
+  chat_history: BaseMessage[];
+};
+
+const outputParser = new ListLineOutputParser({
+  key: 'suggestions',
+});
+
+const createSuggestionGeneratorChain = (llm: BaseChatModel) => {
+  return RunnableSequence.from([
+    RunnableMap.from({
+      chat_history: (input: SuggestionGeneratorInput) =>
+        formatChatHistoryAsString(input.chat_history),
+    }),
+    PromptTemplate.fromTemplate(suggestionGeneratorPrompt),
+    llm,
+    outputParser,
+  ]);
+};
+
+const generateSuggestions = (
+  input: SuggestionGeneratorInput,
+  llm: BaseChatModel,
+) => {
+  (llm as unknown as ChatOpenAI).temperature = 0;
+  const suggestionGeneratorChain = createSuggestionGeneratorChain(llm);
+  return suggestionGeneratorChain.invoke(input);
+};
+
+export default generateSuggestions;