chore/set pdf page splitting to true by default

.speakeasy/gen.lock

@@ -1,12 +1,12 @@
 lockVersion: 2.0.0
 id: f42cb8e6-e2ce-4565-b975-5a9f38b94d5a
 management:
-  docChecksum: f152122a1bb6e932d6eb54355be2da11
+  docChecksum: fd76ef24456d50f23903277067ffaa2e
   docVersion: 1.0.35
   speakeasyVersion: 1.308.1
   generationVersion: 2.342.6
-  releaseVersion: 0.11.1
-  configChecksum: bd8ea9af107b087e7927abd855542414
+  releaseVersion: 0.11.2
+  configChecksum: f5f0ec91134be577b27ca7ca87e4f5fa
   repoURL: https://github.com/Unstructured-IO/unstructured-js-client.git
   repoSubDirectory: .
   installationURL: https://github.com/Unstructured-IO/unstructured-js-client

README.md

@@ -9,12 +9,6 @@
     <a href="https://speakeasyapi.dev/"><img src="https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454" /></a>
 </div>
 
-<h2 align="center">
-  <p>Typescript SDK for the Unstructured API</p>
-</h2>
-
-This is a Typescript client for the [Unstructured API](https://unstructured-io.github.io/unstructured/api.html). 
-
 <div align="center">
 
  <a
@@ -24,6 +18,13 @@ This is a Typescript client for the [Unstructured API](https://unstructured-io.g
 
 </div>
 
+<h2 align="center">
+  <p>Typescript SDK for the Unstructured API</p>
+</h2>
+
+This is a Typescript client for the [Unstructured API](https://unstructured-io.github.io/unstructured/api.html). 
+
+Please refer to the [Unstructured docs](https://docs.unstructured.io/api-reference/api-services/sdk) for a full guide to using the client.
 
 ## SDK Installation
 
@@ -40,45 +41,40 @@ yarn add unstructured-client --dev
 ```
 <!-- No SDK Installation -->
 
+<!-- Start SDK Example Usage [usage] -->
 ## SDK Example Usage
-Only the `files` parameter is required for partition. See the [general partition](docs/sdks/general/README.md) page for all available parameters. 
+
+### Example
 
 ```typescript
+import { openAsBlob } from "node:fs";
 import { UnstructuredClient } from "unstructured-client";
-import { PartitionResponse } from "unstructured-client/dist/sdk/models/operations";
-import * as fs from "fs";
-
-const key = "YOUR-API-KEY";
+import { Strategy } from "unstructured-client/sdk/models/shared";
 
-const client = new UnstructuredClient({
+const unstructuredClient = new UnstructuredClient({
     security: {
-        apiKeyAuth: key,
+        apiKeyAuth: "YOUR_API_KEY",
     },
-    // uncomment and change the URL below depending on which services you use or hosting locally; see below for more details
-    // by default it will make requests againt the url for the freemium (https://unstructured.io/api-key-free) API service
-    // serverURL: "http://localhost:8000",
 });
 
-const filename = "sample-docs/layout-parser-paper.pdf";
-const data = fs.readFileSync(filename);
+async function run() {
+    const result = await unstructuredClient.general.partition({
+        partitionParameters: {
+            files: await openAsBlob("./sample-file"),
+            strategy: Strategy.Auto,
+        },
+    });
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
 
-client.general.partition({
-    // Note that this currently only supports a single file
-    files: {
-        content: data,
-        fileName: filename,
-    },
-    // Other partition params
-    strategy: "fast",
-}).then((res: PartitionResponse) => {
-    if (res.statusCode == 200) {
-        console.log(res.elements);
-    }
-}).catch((e) => {
-    console.log(e.statusCode);
-    console.log(e.body);
-});
 ```
+<!-- End SDK Example Usage [usage] -->
+
+Refer to the [API parameters page](https://docs.unstructured.io/api-reference/api-services/api-parameters) for all available parameters.
 
 ## Change the base URL
 
@@ -103,12 +99,6 @@ const client = new UnstructuredClient({
 ```
 
 
-<!-- No SDK Example Usage -->
-<!-- No SDK Available Operations -->
-<!-- No Pagination -->
-<!-- No Error Handling -->
-<!-- No Server Selection -->
-
 <!-- Start Custom HTTP Client [http-client] -->
 ## Custom HTTP Client
 
@@ -157,24 +147,102 @@ httpClient.addHook("requestError", (error, request) => {
 const sdk = new UnstructuredClient({ httpClient });
 ```
 <!-- End Custom HTTP Client [http-client] -->
-<!-- No Retries -->
-<!-- No Authentication -->
 
-## PartitionParameters
+<!-- Start Retries [retries] -->
+## Retries
 
-See the [general partition](docs/sdk/models/shared/partitionparameters.md) page for all available parameters. 
+Some of the endpoints in this SDK support retries.  If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API.  However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
 
-### Splitting PDF by pages
+To change the default retry strategy for a single API call, simply provide a retryConfig object to the call:
+```typescript
+import { openAsBlob } from "node:fs";
+import { UnstructuredClient } from "unstructured-client";
+import { Strategy } from "unstructured-client/sdk/models/shared";
+
+const unstructuredClient = new UnstructuredClient({
+    security: {
+        apiKeyAuth: "YOUR_API_KEY",
+    },
+});
 
-In order to speed up processing of long PDF files, set `splitPdfPage` parameter to `true`. It will cause the PDF to be split into smaller batches at client side, before sending to API, and combining individual responses as single result. This will work only for PDF files, so don't set it for other types of files. Size of each batch is determined internally and it can vary between 2 and 20 pages per split.
+async function run() {
+    const result = await unstructuredClient.general.partition(
+        {
+            partitionParameters: {
+                files: await openAsBlob("./sample-file"),
+                strategy: Strategy.Auto,
+            },
+        },
+        {
+            retries: {
+                strategy: "backoff",
+                backoff: {
+                    initialInterval: 1,
+                    maxInterval: 50,
+                    exponent: 1.1,
+                    maxElapsedTime: 100,
+                },
+                retryConnectionErrors: false,
+            },
+        }
+    );
 
-The amount of parallel requests is controlled by `splitPdfConcurrencyLevel` parameter. By default it equals to 5. It can't be more than 15, to avoid too high resource usage and costs.
+    // Handle the result
+    console.log(result);
+}
+
+run();
 
+```
+
+If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:
 ```typescript
-import { SplitPdfHook } from "unstructured-client/hooks/custom/SplitPdfHook";
+import { openAsBlob } from "node:fs";
+import { UnstructuredClient } from "unstructured-client";
+import { Strategy } from "unstructured-client/sdk/models/shared";
 
-...
+const unstructuredClient = new UnstructuredClient({
+    retryConfig: {
+        strategy: "backoff",
+        backoff: {
+            initialInterval: 1,
+            maxInterval: 50,
+            exponent: 1.1,
+            maxElapsedTime: 100,
+        },
+        retryConnectionErrors: false,
+    },
+    security: {
+        apiKeyAuth: "YOUR_API_KEY",
+    },
+});
 
+async function run() {
+    const result = await unstructuredClient.general.partition({
+        partitionParameters: {
+            files: await openAsBlob("./sample-file"),
+            strategy: Strategy.Auto,
+        },
+    });
+
+    // Handle the result
+    console.log(result);
+}
+
+run();
+
+```
+<!-- End Retries [retries] -->
+
+### Splitting PDF by pages
+
+See [page splitting](https://docs.unstructured.io/api-reference/api-services/sdk#page-splitting) for more details.
+
+In order to speed up processing of large PDF files, the client splits up PDFs into smaller files, sends these to the API concurrently, and recombines the results. `splitPdfPage` can be set to `false` to disable this.
+
+The amount of parallel requests is controlled by `splitPdfConcurrencyLevel` parameter. By default it equals to 5. It can't be more than 15, to avoid too high resource usage and costs. The size of each batch is determined internally and it can vary between 2 and 20 pages per split.
+
+```typescript
 client.general.partition({
     partitionParameters: {
         files: {
@@ -186,14 +254,7 @@ client.general.partition({
         // Modify splitPdfConcurrencyLevel to change the limit of parallel requests
         splitPdfConcurrencyLevel: 10,
     },
-}).then((res: PartitionResponse) => {
-    if (res.statusCode == 200) {
-        console.log(res.elements);
-    }
-}).catch((e) => {
-    console.log(e.statusCode);
-    console.log(e.body);
-});
+}};
 ```
 
 <!-- Start Requirements [requirements] -->
@@ -244,6 +305,12 @@ run();
 ```
 <!-- End File uploads [file-upload] -->
 
+<!-- No Authentication -->
+<!-- No SDK Available Operations -->
+<!-- No Pagination -->
+<!-- No Error Handling -->
+<!-- No Server Selection -->
+
 <!-- Placeholder for Future Speakeasy SDK Sections -->
 
 ### Maturity

RELEASES.md

@@ -333,4 +333,14 @@ Based on:
 ### Generated
 - [typescript v0.11.1] .
 ### Releases
-- [NPM v0.11.1] https://www.npmjs.com/package/unstructured-client/v/0.11.1 - .
+- [NPM v0.11.1] https://www.npmjs.com/package/unstructured-client/v/0.11.1 - .
+
+## 2024-06-17 17:43:15
+### Changes
+Based on:
+- OpenAPI Doc  
+- Speakeasy CLI 1.308.1 (2.342.6) https://github.com/speakeasy-api/speakeasy
+### Generated
+- [typescript v0.11.1] .
+### Releases
+- [NPM v0.11.2] https://www.npmjs.com/package/unstructured-client/v/0.11.2 - .

gen.yaml

@@ -10,7 +10,7 @@ generation:
   auth:
     oAuth2ClientCredentialsEnabled: false
 typescript:
-  version: 0.11.1
+  version: 0.11.2
   additionalDependencies:
     dependencies:
       async: ^3.2.5

jsr.json

@@ -2,7 +2,7 @@
 
 {
   "name": "unstructured-client",
-  "version": "0.11.1",
+  "version": "0.11.2",
   "exports": {
     ".": "./src/index.ts",    
     "./sdk/models/errors": "./src/sdk/models/errors/index.ts",    

overlay_client.yaml

@@ -10,7 +10,7 @@ actions:
           "type": "boolean",
           "title": "Split Pdf Page",
           "description": "Should the pdf file be split at client. Ignored on backend.",
-          "default": false,
+          "default": true,
         }
   - target: $["components"]["schemas"]["partition_parameters"]["properties"]
     update:

package.json

@@ -1,6 +1,6 @@
 {
   "name": "unstructured-client",
-  "version": "0.11.1",
+  "version": "0.11.2",
   "author": "Unstructured",  
   "main": "./index.js",
   "sideEffects": false,

src/hooks/custom/SplitPdfHook.ts

@@ -22,7 +22,7 @@ import {
   prepareResponseHeaders,
   splitPdf,
   stringToBoolean,
-} from "./utils";
+} from "./utils/index";
 import {
   MIN_PAGES_PER_THREAD,
   PARTITION_FORM_FILES_KEY,
@@ -98,12 +98,12 @@ export class SplitPdfHook
 
     const [error, pdf, pagesCount] = await loadPdf(file);
     if (file === null || pdf === null || error) {
-      console.warn("File could not be split. Partitioning without split.")
+      console.info("Partitioning without split.")
       return request;
     }
 
     if (pagesCount < MIN_PAGES_PER_THREAD) {
-      console.warn(
+      console.info(
         `PDF has less than ${MIN_PAGES_PER_THREAD} pages. Partitioning without split.`
       );
       return request;
@@ -119,7 +119,7 @@ export class SplitPdfHook
     console.info("Determined optimal split size of %d pages.", splitSize)
 
     if (splitSize >= pagesCount) {
-      console.warn(
+      console.info(
           "Document has too few pages (%d) to be split efficiently. Partitioning without split.",
           pagesCount,
       )

src/hooks/custom/utils/pdf.ts

@@ -102,7 +102,7 @@ export async function loadPdf(
   file: File | null
 ): Promise<[boolean, PDFDocument | null, number]> {
   if (!file?.name.endsWith(".pdf")) {
-    console.warn("Given file is not a PDF. Continuing without splitting.");
+    console.info("Given file is not a PDF, so splitting is not enabled.");
     return [true, null, 0];
   }
 

src/lib/config.ts

@@ -61,7 +61,7 @@ export function serverURLFromOptions(options: SDKOptions): URL | null {
 export const SDK_METADATA = {
     language: "typescript",
     openapiDocVersion: "1.0.35",
-    sdkVersion: "0.11.1",
+    sdkVersion: "0.11.2",
     genVersion: "2.342.6",
-    userAgent: "speakeasy-sdk/typescript 0.11.1 2.342.6 1.0.35 unstructured-client",
+    userAgent: "speakeasy-sdk/typescript 0.11.2 2.342.6 1.0.35 unstructured-client",
 } as const;

src/sdk/models/shared/partitionparameters.ts

@@ -240,7 +240,7 @@ export namespace PartitionParameters$ {
             similarity_threshold: z.nullable(z.number()).optional(),
             skip_infer_table_types: z.array(z.string()).optional(),
             split_pdf_concurrency_level: z.number().int().default(5),
-            split_pdf_page: z.boolean().default(false),
+            split_pdf_page: z.boolean().default(true),
             starting_page_number: z.nullable(z.number().int()).optional(),
             strategy: Strategy$.inboundSchema.default(Strategy.Auto),
             unique_element_ids: z.boolean().default(false),
@@ -326,7 +326,7 @@ export namespace PartitionParameters$ {
             similarityThreshold: z.nullable(z.number()).optional(),
             skipInferTableTypes: z.array(z.string()).optional(),
             splitPdfConcurrencyLevel: z.number().int().default(5),
-            splitPdfPage: z.boolean().default(false),
+            splitPdfPage: z.boolean().default(true),
             startingPageNumber: z.nullable(z.number().int()).optional(),
             strategy: Strategy$.outboundSchema.default(Strategy.Auto),
             uniqueElementIds: z.boolean().default(false),