Merge branch 'main' into main

langchain-ai · Jan 1, 2025 · ed2aca0 · ed2aca0
2 parents d33c54d + 7f729c9
commit ed2aca0
Show file tree

Hide file tree

Showing 47 changed files with 2,032 additions and 162 deletions.
diff --git a/docs/api_refs/blacklisted-entrypoints.json b/docs/api_refs/blacklisted-entrypoints.json
@@ -15,6 +15,7 @@
   "../../langchain/src/embeddings/tensorflow.ts",
   "../../langchain/src/embeddings/hf.ts",
   "../../langchain/src/embeddings/hf_transformers.ts",
+  "../../langchain/src/embeddings/huggingface_transformers.ts",
   "../../langchain/src/embeddings/googlevertexai.ts",
   "../../langchain/src/embeddings/googlepalm.ts",
   "../../langchain/src/embeddings/minimax.ts",

diff --git a/docs/core_docs/docs/integrations/document_loaders/file_loaders/docx.mdx b/docs/core_docs/docs/integrations/document_loaders/file_loaders/docx.mdx
@@ -4,17 +4,38 @@ hide_table_of_contents: true
 
 # Docx files
 
-This example goes over how to load data from docx files.
+The `DocxLoader` allows you to extract text data from Microsoft Word documents. It supports both the modern `.docx` format and the legacy `.doc` format. Depending on the file type, additional dependencies are required.
 
-# Setup
+---
+
+## Setup
+
+To use `DocxLoader`, you'll need the `@langchain/community` integration along with either `mammoth` or `word-extractor` package:
+
+- **`mammoth`**: For processing `.docx` files.
+- **`word-extractor`**: For handling `.doc` files.
+
+### Installation
+
+#### For `.docx` Files
 
 ```bash npm2yarn
 npm install @langchain/community @langchain/core mammoth
 ```
 
-# Usage
+#### For `.doc` Files
+
+```bash npm2yarn
+npm install @langchain/community @langchain/core word-extractor
+```
+
+## Usage
+
+### Loading `.docx` Files
 
-```typescript
+For `.docx` files, there is no need to explicitly specify any parameters when initializing the loader:
+
+```javascript
 import { DocxLoader } from "@langchain/community/document_loaders/fs/docx";
 
 const loader = new DocxLoader(
@@ -23,3 +44,20 @@ const loader = new DocxLoader(
 
 const docs = await loader.load();
 ```
+
+### Loading `.doc` Files
+
+For `.doc` files, you must explicitly specify the `type` as `doc` when initializing the loader:
+
+```javascript
+import { DocxLoader } from "@langchain/community/document_loaders/fs/docx";
+
+const loader = new DocxLoader(
+  "src/document_loaders/tests/example_data/attention.doc",
+  {
+    type: "doc",
+  }
+);
+
+const docs = await loader.load();
+```
diff --git a/docs/core_docs/docs/integrations/document_loaders/web_loaders/jira.mdx b/docs/core_docs/docs/integrations/document_loaders/web_loaders/jira.mdx
@@ -0,0 +1,23 @@
+---
+sidebar_class_name: node-only
+---
+
+# Jira
+
+:::tip Compatibility
+Only available on Node.js.
+:::
+
+This covers how to load document objects from issues in a Jira projects.
+
+## Credentials
+
+- You'll need to set up an access token and provide it along with your Jira username in order to authenticate the request
+- You'll also need the project key and host URL for the project containing the issues to load as documents.
+
+## Usage
+
+import CodeBlock from "@theme/CodeBlock";
+import Example from "@examples/document_loaders/jira.ts";
+
+<CodeBlock language="typescript">{Example}</CodeBlock>
diff --git a/docs/core_docs/docs/integrations/text_embedding/transformers.mdx b/docs/core_docs/docs/integrations/text_embedding/transformers.mdx
@@ -8,10 +8,15 @@ It runs locally and even works directly in the browser, allowing you to create w
 
 ## Setup
 
-You'll need to install the [@xenova/transformers](https://www.npmjs.com/package/@xenova/transformers) package as a peer dependency:
+You'll need to install the [@huggingface/transformers](https://www.npmjs.com/package/@huggingface/transformers) package as a peer dependency:
+
+:::tip Compatibility
+If you are using a version of community older than 0.3.21, install the older `@xenova/transformers` package and
+import the embeddings from `"@langchain/community/embeddings/hf_transformers"` below.
+:::
 
 ```bash npm2yarn
-npm install @xenova/transformers
+npm install @huggingface/transformers
 ```
 
 import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";

diff --git a/environment_tests/test-exports-cjs/src/import.js b/environment_tests/test-exports-cjs/src/import.js
@@ -3,7 +3,7 @@ async function test() {
   const { OpenAI } = await import("@langchain/openai");
   const { LLMChain } = await import("langchain/chains");
   const { ChatPromptTemplate } = await import("@langchain/core/prompts");
-  const { HuggingFaceTransformersEmbeddings } = await import("@langchain/community/embeddings/hf_transformers");
+  const { HuggingFaceTransformersEmbeddings } = await import("@langchain/community/embeddings/huggingface_transformers");
   const { Document } = await import("@langchain/core/documents");
   const { MemoryVectorStore } = await import("langchain/vectorstores/memory");
 

diff --git a/environment_tests/test-exports-cjs/src/index.mjs b/environment_tests/test-exports-cjs/src/index.mjs
@@ -3,7 +3,7 @@ import { OpenAI } from "@langchain/openai";
 import { LLMChain } from "langchain/chains";
 import { MemoryVectorStore } from "langchain/vectorstores/memory";
 import { ChatPromptTemplate } from "@langchain/core/prompts";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { Document } from "@langchain/core/documents";
 
 // Test exports

diff --git a/environment_tests/test-exports-cjs/src/index.ts b/environment_tests/test-exports-cjs/src/index.ts
@@ -3,7 +3,7 @@ import { OpenAI } from "@langchain/openai";
 import { LLMChain } from "langchain/chains";
 import { ChatPromptTemplate } from "@langchain/core/prompts";
 import { MemoryVectorStore } from "langchain/vectorstores/memory";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { Document } from "@langchain/core/documents";
 
 async function test(useAzure: boolean = false) {
@@ -25,7 +25,9 @@ async function test(useAzure: boolean = false) {
         openAIApiKey: "sk-XXXX",
       };
 
-  const vs = new MemoryVectorStore(new HuggingFaceTransformersEmbeddings({ model: "Xenova/all-MiniLM-L6-v2" }));
+  const vs = new MemoryVectorStore(
+    new HuggingFaceTransformersEmbeddings({ model: "Xenova/all-MiniLM-L6-v2" })
+  );
 
   await vs.addVectors(
     [

diff --git a/environment_tests/test-exports-cjs/src/require.js b/environment_tests/test-exports-cjs/src/require.js
@@ -3,7 +3,7 @@ const { OpenAI } = require("@langchain/openai");
 const { LLMChain } = require("langchain/chains");
 const { ChatPromptTemplate } = require("@langchain/core/prompts");
 const { MemoryVectorStore } = require("langchain/vectorstores/memory");
-const { HuggingFaceTransformersEmbeddings } = require("@langchain/community/embeddings/hf_transformers");
+const { HuggingFaceTransformersEmbeddings } = require("@langchain/community/embeddings/huggingface_transformers");
 const { Document } = require("@langchain/core/documents");
 
 async function test() {

diff --git a/environment_tests/test-exports-esm/src/import.cjs b/environment_tests/test-exports-esm/src/import.cjs
@@ -4,7 +4,7 @@ async function test() {
   const { LLMChain } = await import("langchain/chains");
   const { ChatPromptTemplate } = await import("@langchain/core/prompts");
   const { MemoryVectorStore } = await import("langchain/vectorstores/memory");
-  const { HuggingFaceTransformersEmbeddings } = await import("@langchain/community/embeddings/hf_transformers");
+  const { HuggingFaceTransformersEmbeddings } = await import("@langchain/community/embeddings/huggingface_transformers");
   const { Document } = await import("@langchain/core/documents");
 
   // Test exports

diff --git a/environment_tests/test-exports-esm/src/index.js b/environment_tests/test-exports-esm/src/index.js
@@ -3,7 +3,7 @@ import { OpenAI } from "@langchain/openai";
 import { LLMChain } from "langchain/chains";
 import { ChatPromptTemplate } from "@langchain/core/prompts";
 import { MemoryVectorStore } from "langchain/vectorstores/memory";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { Document } from "@langchain/core/documents";
 import { CallbackManager } from "@langchain/core/callbacks/manager";
 

diff --git a/environment_tests/test-exports-esm/src/index.ts b/environment_tests/test-exports-esm/src/index.ts
@@ -3,7 +3,7 @@ import { OpenAI } from "@langchain/openai";
 import { LLMChain } from "langchain/chains";
 import { ChatPromptTemplate } from "@langchain/core/prompts";
 import { MemoryVectorStore } from "langchain/vectorstores/memory";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { Document } from "@langchain/core/documents";
 
 async function test(useAzure: boolean = false) {
@@ -24,7 +24,9 @@ async function test(useAzure: boolean = false) {
         openAIApiKey: "sk-XXXX",
       };
 
-  const vs = new MemoryVectorStore(new HuggingFaceTransformersEmbeddings({ model: "Xenova/all-MiniLM-L6-v2", }));
+  const vs = new MemoryVectorStore(
+    new HuggingFaceTransformersEmbeddings({ model: "Xenova/all-MiniLM-L6-v2" })
+  );
 
   await vs.addVectors(
     [

diff --git a/environment_tests/test-exports-esm/src/require.cjs b/environment_tests/test-exports-esm/src/require.cjs
@@ -3,7 +3,7 @@ const { OpenAI } = require("@langchain/openai");
 const { LLMChain } = require("langchain/chains");
 const { ChatPromptTemplate } = require("@langchain/core/prompts");
 const { MemoryVectorStore } = require("langchain/vectorstores/memory");
-const { HuggingFaceTransformersEmbeddings } = require("@langchain/community/embeddings/hf_transformers");
+const { HuggingFaceTransformersEmbeddings } = require("@langchain/community/embeddings/huggingface_transformers");
 const { Document } = require("@langchain/core/documents");
 
 async function test() {

diff --git a/examples/.env.example b/examples/.env.example
@@ -84,4 +84,8 @@ HANA_HOST=HANA_DB_ADDRESS
 HANA_PORT=HANA_DB_PORT
 HANA_UID=HANA_DB_USER
 HANA_PWD=HANA_DB_PASSWORD
-ARK_API_KEY=ADD_YOURS_HERE # https://console.volcengine.com/
+ARK_API_KEY=ADD_YOURS_HERE # https://console.volcengine.com/
+JIRA_HOST=ADD_YOURS_HERE
+JIRA_USERNAME=ADD_YOURS_HERE
+JIRA_ACCESS_TOKEN=ADD_YOURS_HERE
+JIRA_PROJECT_KEY=ADD_YOURS_HERE
diff --git a/examples/src/document_loaders/jira.ts b/examples/src/document_loaders/jira.ts
@@ -0,0 +1,26 @@
+import { JiraProjectLoader } from "@langchain/community/document_loaders/web/jira";
+
+const host = process.env.JIRA_HOST || "https://jira.example.com";
+const username = process.env.JIRA_USERNAME;
+const accessToken = process.env.JIRA_ACCESS_TOKEN;
+const projectKey = process.env.JIRA_PROJECT_KEY || "PROJ";
+
+if (username && accessToken) {
+  // Created within last 30 days
+  const createdAfter = new Date();
+  createdAfter.setDate(createdAfter.getDate() - 30);
+  const loader = new JiraProjectLoader({
+    host,
+    projectKey,
+    username,
+    accessToken,
+    createdAfter,
+  });
+
+  const documents = await loader.load();
+  console.log(`Loaded ${documents.length} Jira document(s)`);
+} else {
+  console.log(
+    "You must provide a username and access token to run this example."
+  );
+}
diff --git a/examples/src/models/embeddings/hf_transformers.ts b/examples/src/models/embeddings/hf_transformers.ts
@@ -1,4 +1,4 @@
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 
 const model = new HuggingFaceTransformersEmbeddings({
   model: "Xenova/all-MiniLM-L6-v2",

diff --git a/examples/src/use_cases/local_retrieval_qa/chain.ts b/examples/src/use_cases/local_retrieval_qa/chain.ts
@@ -2,7 +2,7 @@ import { CheerioWebBaseLoader } from "@langchain/community/document_loaders/web/
 import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
 import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
 import { Ollama } from "@langchain/community/llms/ollama";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { formatDocumentsAsString } from "langchain/util/document";
 import { PromptTemplate } from "@langchain/core/prompts";
 import {

diff --git a/examples/src/use_cases/local_retrieval_qa/load_documents.ts b/examples/src/use_cases/local_retrieval_qa/load_documents.ts
@@ -1,7 +1,7 @@
 import { CheerioWebBaseLoader } from "@langchain/community/document_loaders/web/cheerio";
 import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
 import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 
 const loader = new CheerioWebBaseLoader(
   "https://lilianweng.github.io/posts/2023-06-23-agent/"

diff --git a/examples/src/use_cases/local_retrieval_qa/qa_chain.ts b/examples/src/use_cases/local_retrieval_qa/qa_chain.ts
@@ -3,7 +3,7 @@ import { CheerioWebBaseLoader } from "@langchain/community/document_loaders/web/
 import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
 import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
 import { Ollama } from "@langchain/community/llms/ollama";
-import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/hf_transformers";
+import { HuggingFaceTransformersEmbeddings } from "@langchain/community/embeddings/huggingface_transformers";
 import { PromptTemplate } from "@langchain/core/prompts";
 
 const loader = new CheerioWebBaseLoader(

diff --git a/langchain-core/package.json b/langchain-core/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@langchain/core",
-  "version": "0.3.26",
+  "version": "0.3.27",
   "description": "Core LangChain.js abstractions and schemas",
   "type": "module",
   "engines": {

diff --git a/libs/langchain-aws/package.json b/libs/langchain-aws/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@langchain/aws",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "LangChain AWS integration",
   "type": "module",
   "engines": {

diff --git a/libs/langchain-community/.env.example b/libs/langchain-community/.env.example
@@ -0,0 +1,4 @@
+JIRA_HOST=ADD_YOURS_HERE
+JIRA_USERNAME=ADD_YOURS_HERE
+JIRA_ACCESS_TOKEN=ADD_YOURS_HERE
+JIRA_PROJECT_KEY=ADD_YOURS_HERE
diff --git a/libs/langchain-community/.gitignore b/libs/langchain-community/.gitignore
@@ -178,6 +178,10 @@ embeddings/hf_transformers.cjs
 embeddings/hf_transformers.js
 embeddings/hf_transformers.d.ts
 embeddings/hf_transformers.d.cts
+embeddings/huggingface_transformers.cjs
+embeddings/huggingface_transformers.js
+embeddings/huggingface_transformers.d.ts
+embeddings/huggingface_transformers.d.cts
 embeddings/ibm.cjs
 embeddings/ibm.js
 embeddings/ibm.d.ts
@@ -930,6 +934,10 @@ document_loaders/web/imsdb.cjs
 document_loaders/web/imsdb.js
 document_loaders/web/imsdb.d.ts
 document_loaders/web/imsdb.d.cts
+document_loaders/web/jira.cjs
+document_loaders/web/jira.js
+document_loaders/web/jira.d.ts
+document_loaders/web/jira.d.cts
 document_loaders/web/figma.cjs
 document_loaders/web/figma.js
 document_loaders/web/figma.d.ts

diff --git a/libs/langchain-community/langchain.config.js b/libs/langchain-community/langchain.config.js
@@ -80,6 +80,7 @@ export const config = {
     "embeddings/gradient_ai": "embeddings/gradient_ai",
     "embeddings/hf": "embeddings/hf",
     "embeddings/hf_transformers": "embeddings/hf_transformers",
+    "embeddings/huggingface_transformers": "embeddings/huggingface_transformers",
     "embeddings/ibm": "embeddings/ibm",
     "embeddings/jina": "embeddings/jina",
     "embeddings/llama_cpp": "embeddings/llama_cpp",
@@ -288,6 +289,7 @@ export const config = {
     "document_loaders/web/gitbook": "document_loaders/web/gitbook",
     "document_loaders/web/hn": "document_loaders/web/hn",
     "document_loaders/web/imsdb": "document_loaders/web/imsdb",
+    "document_loaders/web/jira": "document_loaders/web/jira",
     "document_loaders/web/figma": "document_loaders/web/figma",
     "document_loaders/web/firecrawl": "document_loaders/web/firecrawl",
     "document_loaders/web/github": "document_loaders/web/github",
@@ -356,6 +358,7 @@ export const config = {
     "embeddings/tensorflow",
     "embeddings/hf",
     "embeddings/hf_transformers",
+    "embeddings/huggingface_transformers",
     "embeddings/ibm",
     "embeddings/jina",
     "embeddings/llama_cpp",