Documentating and adding a manifest.json

templates/js-langchain/README.md

@@ -2,21 +2,30 @@
 
 > LangChain is a framework for developing applications powered by language models.
 
-This example template illustrates how to use LangChain.js to crawl the web data, vectorize them, and prompt the OpenAI model. All of this within a single Apify Actor.
+This example template illustrates how to use LangChain.js with Apify to crawl the web data, vectorize them, and prompt the OpenAI model. All of this within a single Apify Actor and slightly over a hundered lines of code.
+
+## Included features
+
+- **[Apify SDK](https://docs.apify.com/sdk/js/)** - a toolkit for building actors
+- **[Input schema](https://docs.apify.com/platform/actors/development/input-schema)** - define and easily validate a schema for your actor's input
+- **[Langchain.js](https://github.com/hwchase17/langchainjs)** - a framework for developing applications powered by language models
+- **[OpenAI](https://openai.com/)** - a powerful language model
+
+## How it works
 
 The code contains following steps:
-- Crawls given website using [Website Content Crawler](https://apify.com/mtrunkat/website-content-crawler) Actor.
-- Vectorizes the data using the [OpenAI](https://openai.com/) API.
-- Caches the vector index in the [key-value store](https://docs.apify.com/platform/storage/key-value-store) so that when you run Actor for the same website again, the cached data are used.
-- Data are fed to the OpenAI model using the [Langchain.js](https://github.com/hwchase17/langchainjs), and a given query is asked.
+1. Crawls given website using [Website Content Crawler](https://apify.com/mtrunkat/website-content-crawler) Actor.
+2. Vectorizes the data using the [OpenAI](https://openai.com/) API.
+3. Caches the vector index in the [key-value store](https://docs.apify.com/platform/storage/key-value-store) so that when you run Actor for the same website again, the cached data are used to speed it up.
+4. Data are fed to the OpenAI model using the [Langchain.js](https://github.com/hwchase17/langchainjs), and a given query is asked.
 
-## Prerequisites
+## Before you start
 
 To be able to run this template both locally and at the Apify Platform, you need to:
-- Have an [Apify account](https://console.apify.com/) and sign into it using `apify login` command. This is needed for running the [Website Content Crawler](https://apify.com/mtrunkat/website-content-crawler) Actor to gather the data.
+- Have an [Apify account](https://console.apify.com/) and sign into it using `apify login` command in your terminal. Without this, you won't be able to run the required [Website Content Crawler](https://apify.com/mtrunkat/website-content-crawler) Actor to gather the data.
 - Have an [OpenAI](https://openai.com/) account and an API key. This is needed for vectorizing the data and also to be able to prompt the OpenAI model.
     - When running locally store this as OPENAI_API_KEY environment variable (https://docs.apify.com/cli/docs/vars#set-up-environment-variables-in-apify-console).
-    - When running on Apify platform, you can simply paste this into the input field in the UI.
+    - When running on Apify platform, you can simply paste this into the input field in the input UI.
 
 ## Production use
 

templates/js-langchain/src/main.js

@@ -5,7 +5,7 @@ import { HNSWLib } from 'langchain/vectorstores/hnswlib';
 import { OpenAIEmbeddings } from 'langchain/embeddings/openai';
 import { RetrievalQAChain } from 'langchain/chains';
 import { OpenAI } from 'langchain/llms/openai';
-import { rmdir } from 'node:fs/promises';
+import { rm } from 'node:fs/promises';
 
 import { retrieveVectorIndex, cacheVectorIndex } from './vector_index_cache.js';
 
@@ -58,10 +58,9 @@ if (reinitializeIndex) {
         }
     );
 
-    const docs = await loader.load();
-
     // Initialize the vector index from the crawled documents.
     console.log('Feeding vector index with crawling results...');
+    const docs = await loader.load();
     vectorStore = await HNSWLib.fromDocuments(
         docs,
         new OpenAIEmbeddings({ openAIApiKey })
@@ -93,7 +92,7 @@ const res = await chain.call({ query });
 console.log(`\n${res.text}\n`);
 
 // Remove the vector index directory as we have it cached in the key-value store for the next time.
-await rmdir(VECTOR_INDEX_PATH, { recursive: true });
+await rm(VECTOR_INDEX_PATH, { recursive: true });
 
 await Actor.setValue('OUTPUT', res);
 await Actor.exit();

templates/manifest.json

@@ -360,6 +360,27 @@
                 "cypress/e2e/second-spec.cy.js",
                 "cypress/support/e2e.js"
             ]
+        },
+        {
+            "id": "js-langchain",
+            "name": "project_langchain_js",
+            "label": "Langchain",
+            "category": "javascript",
+            "technologies": [
+                "nodejs",
+                "langchain"
+            ],
+            "description": "Example of how to use LangChain.js with Apify to crawl the web data, vectorize them, and prompt the OpenAI model.",
+            "archiveUrl": "https://github.com/apify/actor-templates/blob/master/dist/templates/js-crawlee-puppeteer-chrome.zip?raw=true",
+            "defaultRunOptions": {
+                "build": "latest",
+                "memoryMbytes": 4096,
+                "timeoutSecs": 3600
+            },
+            "showcaseFiles": [
+                "src/main.js",
+                "src/vector_index_cache.js"
+            ]
         }
     ]
 }