feat: add boundingBox and targetPages to LlamaParseReader (#1017)

.changeset/slimy-bees-yell.md

@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+feat: add boundingBox and targetPages to LlamaParseReader

apps/docs/docs/modules/data_loaders/llama_parse/index.mdx

@@ -44,6 +44,8 @@ They can be divided into two groups.
 - `pageSeperator?` Optional. The page seperator to use. Defaults is `\\n---\\n`.
 - `gpt4oMode` set to true to use GPT-4o to extract content. Default is `false`.
 - `gpt4oApiKey?` Optional. Set the GPT-4o API key. Lowers the cost of parsing by using your own API key. Your OpenAI account will be charged. Can also be set in the environment variable `LLAMA_CLOUD_GPT4O_API_KEY`.
+- `boundingBox?` Optional. Specify an area of the document to parse. Expects the bounding box margins as a string in clockwise order, e.g. `boundingBox = "0.1,0,0,0"` to not parse the top 10% of the document.
+- `targetPages?` Optional. Specify which pages to parse by specifying them as a comma-seperated list. First page is `0`.
 - `numWorkers` as in the python version, is set in `SimpleDirectoryReader`. Default is 1.
 
 ### LlamaParse with SimpleDirectoryReader

apps/docs/docs/modules/data_loaders/llama_parse/json_mode.mdx

@@ -8,7 +8,7 @@ In JSON mode, LlamaParse will return a data structure representing the parsed ob
 
 ## Usage
 
-For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method. Currently it can't be used with `SimpleDirectoryReader`.
+For Json mode, you need to use `loadJson`. The `resultType` is automatically set with this method.
 More information about indexing the results on the next page.
 
 ```ts

packages/llamaindex/src/readers/LlamaParseReader.ts

@@ -133,6 +133,10 @@ export class LlamaParseReader extends FileReader {
   gpt4oMode: boolean = false;
   // The API key for the GPT-4o API. Optional, lowers the cost of parsing. Can be set as an env variable: LLAMA_CLOUD_GPT4O_API_KEY.
   gpt4oApiKey?: string;
+  // The bounding box to use to extract text from documents. Describe as a string containing the bounding box margins.
+  boundingBox?: string;
+  // The target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0
+  targetPages?: string;
   // Whether or not to ignore and skip errors raised during parsing.
   ignoreErrors: boolean = true;
   // numWorkers is implemented in SimpleDirectoryReader
@@ -183,6 +187,8 @@ export class LlamaParseReader extends FileReader {
       page_seperator: this.pageSeperator,
       gpt4o_mode: this.gpt4oMode?.toString(),
       gpt4o_api_key: this.gpt4oApiKey,
+      bounding_box: this.boundingBox,
+      target_pages: this.targetPages,
     };
 
     // Appends body with any defined LlamaParseBodyParams