docs[patch],community[minor]: Update AssemblyAI SDK, add user agent, …

…update AssemblyAI URLs (#6084) * Update AssemblyAI SDK, loader, and docs * Update AssemblyAI SDK to 4.6.0 * Apply suggestions from code review --------- Co-authored-by: Brace Sproul <braceasproul@gmail.com>
langchain-ai · Jul 16, 2024 · 795ca0b · 795ca0b
1 parent f624793
commit 795ca0b
Show file tree

Hide file tree

Showing 10 changed files with 55 additions and 24 deletions.
diff --git a/...cs/integrations/document_loaders/web_loaders/assemblyai_audio_transcription.mdx b/...cs/integrations/document_loaders/web_loaders/assemblyai_audio_transcription.mdx
@@ -6,7 +6,7 @@ import CodeBlock from "@theme/CodeBlock";
 
 # AssemblyAI Audio Transcript
 
-This covers how to load audio (and video) transcripts as document objects from a file using the [AssemblyAI API](https://www.assemblyai.com/docs/api-reference/transcript).
+This covers how to load audio (and video) transcripts as document objects from a file using the [AssemblyAI API](https://www.assemblyai.com/docs/api-reference/transcripts/submit?utm_source=langchainjs).
 
 ## Usage
 
@@ -16,8 +16,8 @@ First, you'll need to install the official AssemblyAI package:
 npm install assemblyai
 ```
 
-To use the loaders you need an [AssemblyAI account](https://www.assemblyai.com/dashboard/signup) and
-[get your AssemblyAI API key from the dashboard](https://www.assemblyai.com/app/account).
+To use the loaders you need an [AssemblyAI account](https://www.assemblyai.com/dashboard/signup?utm_source=langchainjs) and
+[get your AssemblyAI API key from the dashboard](https://www.assemblyai.com/app/account?utm_source=langchainjs).
 
 Then, configure the API key as the `ASSEMBLYAI_API_KEY` environment variable or the `apiKey` options parameter.
 
@@ -29,9 +29,9 @@ import TranscriptExample from "@examples/document_loaders/assemblyai_audio_trans
 >
 > - You can use the `AudioTranscriptParagraphsLoader` or `AudioTranscriptSentencesLoader` to split the transcript into paragraphs or sentences.
 > - The `audio` parameter can be a URL, a local file path, a buffer, or a stream.
-> - The `audio` can also be a video file. See the [list of supported file types in the FAQ doc](https://www.assemblyai.com/docs/concepts/faq#:~:text=file%20types%20are%20supported).
+> - The `audio` can also be a video file. See the [list of supported file types in the FAQ doc](https://www.assemblyai.com/docs/concepts/faq?utm_source=langchainjs#:~:text=file%20types%20are%20supported).
 > - If you don't pass in the `apiKey` option, the loader will use the `ASSEMBLYAI_API_KEY` environment variable.
-> - You can add more properties in addition to `audio`. Find the full list of request parameters in the [AssemblyAI API docs](https://www.assemblyai.com/docs/api-reference/transcript#create-a-transcript).
+> - You can add more properties in addition to `audio`. Find the full list of request parameters in the [AssemblyAI API docs](https://www.assemblyai.com/docs/api-reference/transcripts/submit?utm_source=langchainjs#create-a-transcript).
 
 You can also use the `AudioSubtitleLoader` to get `srt` or `vtt` subtitles as a document.
 

diff --git a/examples/src/document_loaders/assemblyai_audio_transcription.ts b/examples/src/document_loaders/assemblyai_audio_transcription.ts
@@ -11,7 +11,7 @@ const audioUrl = "https://storage.googleapis.com/aai-docs-samples/espn.m4a";
 const loader = new AudioTranscriptLoader(
   {
     audio: audioUrl,
-    // any other parameters as documented here: https://www.assemblyai.com/docs/api-reference/transcript#create-a-transcript
+    // any other parameters as documented here: https://www.assemblyai.com/docs/api-reference/transcripts/submit
   },
   {
     apiKey: "<ASSEMBLYAI_API_KEY>", // or set the `ASSEMBLYAI_API_KEY` env variable

diff --git a/examples/src/document_loaders/assemblyai_subtitles.ts b/examples/src/document_loaders/assemblyai_subtitles.ts
@@ -6,7 +6,7 @@ const audioUrl = "https://storage.googleapis.com/aai-docs-samples/espn.m4a";
 const loader = new AudioSubtitleLoader(
   {
     audio: audioUrl,
-    // any other parameters as documented here: https://www.assemblyai.com/docs/api-reference/transcript#create-a-transcript
+    // any other parameters as documented here: https://www.assemblyai.com/docs/api-reference/transcripts/submit
   },
   "srt", // srt or vtt
   {

diff --git a/langchain/package.json b/langchain/package.json
@@ -632,7 +632,7 @@
     "@vercel/kv": "^0.2.3",
     "@xata.io/client": "^0.28.0",
     "apify-client": "^2.7.1",
-    "assemblyai": "^4.0.0",
+    "assemblyai": "^4.6.0",
     "axios": "^0.26.0",
     "cheerio": "^1.0.0-rc.12",
     "chromadb": "^1.5.3",
@@ -701,7 +701,7 @@
     "@vercel/kv": "^0.2.3",
     "@xata.io/client": "^0.28.0",
     "apify-client": "^2.7.1",
-    "assemblyai": "^4.0.0",
+    "assemblyai": "^4.6.0",
     "axios": "*",
     "cheerio": "^1.0.0-rc.12",
     "chromadb": "*",

diff --git a/langchain/src/document_loaders/tests/assemblyai.int.test.ts b/langchain/src/document_loaders/tests/assemblyai.int.test.ts
@@ -9,7 +9,6 @@ import {
 } from "../web/assemblyai.js";
 
 const transcriptId = process.env.ASSEMBLYAI_TRANSCRIPT_ID!;
-console.log(transcriptId);
 
 describe.skip("AssemblyAI", () => {
   test("Invalid API key", async () => {

diff --git a/langchain/src/document_loaders/web/assemblyai.ts b/langchain/src/document_loaders/web/assemblyai.ts
@@ -21,6 +21,12 @@ import { logVersion020MigrationWarning } from "../../util/entrypoint_deprecation
 
 export type * from "../../types/assemblyai-types.js";
 
+const defaultOptions = {
+  userAgent: {
+    integration: { name: "LangChainJS", version: "1.0.1" },
+  },
+};
+
 /**
  * @deprecated
  * Base class for AssemblyAI loaders.
@@ -46,7 +52,10 @@ abstract class AssemblyAILoader extends BaseDocumentLoader {
       throw new Error("No AssemblyAI API key provided");
     }
 
-    this.client = new AssemblyAI(options as BaseServiceParams);
+    this.client = new AssemblyAI({
+      ...defaultOptions,
+      ...options,
+    } as BaseServiceParams);
   }
 }
 

diff --git a/libs/langchain-community/package.json b/libs/langchain-community/package.json
@@ -133,7 +133,7 @@
     "@xenova/transformers": "^2.17.2",
     "@zilliz/milvus2-sdk-node": ">=2.3.5",
     "apify-client": "^2.7.1",
-    "assemblyai": "^4.0.0",
+    "assemblyai": "^4.6.0",
     "better-sqlite3": ">=9.4.0 <12.0.0",
     "cassandra-driver": "^4.7.2",
     "cborg": "^4.1.1",
@@ -274,7 +274,7 @@
     "@xenova/transformers": "^2.17.2",
     "@zilliz/milvus2-sdk-node": ">=2.3.5",
     "apify-client": "^2.7.1",
-    "assemblyai": "^4.0.0",
+    "assemblyai": "^4.6.0",
     "better-sqlite3": ">=9.4.0 <12.0.0",
     "cassandra-driver": "^4.7.2",
     "cborg": "^4.1.1",

diff --git a/libs/langchain-community/src/document_loaders/tests/assemblyai.int.test.ts b/libs/langchain-community/src/document_loaders/tests/assemblyai.int.test.ts
@@ -9,7 +9,6 @@ import {
 } from "../web/assemblyai.js";
 
 const transcriptId = process.env.ASSEMBLYAI_TRANSCRIPT_ID!;
-console.log(transcriptId);
 
 describe.skip("AssemblyAI", () => {
   test("Invalid API key", async () => {

diff --git a/libs/langchain-community/src/document_loaders/web/assemblyai.ts b/libs/langchain-community/src/document_loaders/web/assemblyai.ts
@@ -15,6 +15,12 @@ import { AssemblyAIOptions } from "../../types/assemblyai-types.js";
 
 export type * from "../../types/assemblyai-types.js";
 
+const defaultOptions = {
+  userAgent: {
+    integration: { name: "LangChainJS", version: "1.0.1" },
+  },
+};
+
 /**
  * Base class for AssemblyAI loaders.
  */
@@ -39,7 +45,10 @@ abstract class AssemblyAILoader extends BaseDocumentLoader {
       throw new Error("No AssemblyAI API key provided");
     }
 
-    this.client = new AssemblyAI(options as BaseServiceParams);
+    this.client = new AssemblyAI({
+      ...defaultOptions,
+      ...options,
+    } as BaseServiceParams);
   }
 }
 

diff --git a/yarn.lock b/yarn.lock
@@ -10551,7 +10551,7 @@ __metadata:
     "@xenova/transformers": ^2.17.2
     "@zilliz/milvus2-sdk-node": ">=2.3.5"
     apify-client: ^2.7.1
-    assemblyai: ^4.0.0
+    assemblyai: ^4.6.0
     better-sqlite3: ">=9.4.0 <12.0.0"
     binary-extensions: ^2.2.0
     cassandra-driver: ^4.7.2
@@ -10700,7 +10700,7 @@ __metadata:
     "@xenova/transformers": ^2.17.2
     "@zilliz/milvus2-sdk-node": ">=2.3.5"
     apify-client: ^2.7.1
-    assemblyai: ^4.0.0
+    assemblyai: ^4.6.0
     better-sqlite3: ">=9.4.0 <12.0.0"
     cassandra-driver: ^4.7.2
     cborg: ^4.1.1
@@ -19431,12 +19431,12 @@ __metadata:
   languageName: node
   linkType: hard
 
-"assemblyai@npm:^4.0.0":
-  version: 4.0.0
-  resolution: "assemblyai@npm:4.0.0"
+"assemblyai@npm:^4.6.0":
+  version: 4.6.0
+  resolution: "assemblyai@npm:4.6.0"
   dependencies:
-    ws: ^8.13.0
-  checksum: 09a2b2ed4c7269b5ef64dbc81a7c83cdcdfff6ec68f9600c702a416f91858b67c76a047f17c3c86701f0157ea64e51a00e77a1beaf790e6212eacc4e4ae3bd44
+    ws: ^8.17.1
+  checksum: de6da06c7a86939033ef9272691eb7f767712cd4ccb6dea84c492df80f510aadcd806081da876948c23dd87b27d3c04e6dfc841dbb403e7ddd52917a591ef142
   languageName: node
   linkType: hard
 
@@ -30286,7 +30286,7 @@ __metadata:
     "@vercel/kv": ^0.2.3
     "@xata.io/client": ^0.28.0
     apify-client: ^2.7.1
-    assemblyai: ^4.0.0
+    assemblyai: ^4.6.0
     axios: ^0.26.0
     binary-extensions: ^2.2.0
     cheerio: ^1.0.0-rc.12
@@ -30367,7 +30367,7 @@ __metadata:
     "@vercel/kv": ^0.2.3
     "@xata.io/client": ^0.28.0
     apify-client: ^2.7.1
-    assemblyai: ^4.0.0
+    assemblyai: ^4.6.0
     axios: "*"
     cheerio: ^1.0.0-rc.12
     chromadb: "*"
@@ -40812,6 +40812,21 @@ __metadata:
   languageName: node
   linkType: hard
 
+"ws@npm:^8.17.1":
+  version: 8.18.0
+  resolution: "ws@npm:8.18.0"
+  peerDependencies:
+    bufferutil: ^4.0.1
+    utf-8-validate: ">=5.0.2"
+  peerDependenciesMeta:
+    bufferutil:
+      optional: true
+    utf-8-validate:
+      optional: true
+  checksum: 91d4d35bc99ff6df483bdf029b9ea4bfd7af1f16fc91231a96777a63d263e1eabf486e13a2353970efc534f9faa43bdbf9ee76525af22f4752cbc5ebda333975
+  languageName: node
+  linkType: hard
+
 "xdg-basedir@npm:^4.0.0":
   version: 4.0.0
   resolution: "xdg-basedir@npm:4.0.0"