From 36ddec44afff0569b84c9b38a5456bee6c2aa1eb Mon Sep 17 00:00:00 2001
From: Sacha Bron <me@sachabron.ch>
Date: Mon, 8 Jul 2024 18:27:51 +0200
Subject: [PATCH] fix: typo in custom page separator parameter for LlamaParse
(#1023)
---
.changeset/witty-bats-shave.md | 7 +++++++
.../docs/modules/data_loaders/llama_parse/index.mdx | 10 +++++-----
packages/cloud/openapi.json | 4 ++--
packages/llamaindex/CHANGELOG.md | 2 +-
packages/llamaindex/src/readers/LlamaParseReader.ts | 4 ++--
5 files changed, 17 insertions(+), 10 deletions(-)
create mode 100644 .changeset/witty-bats-shave.md
diff --git a/.changeset/witty-bats-shave.md b/.changeset/witty-bats-shave.md
new file mode 100644
index 000000000..7efd2fb40
--- /dev/null
+++ b/.changeset/witty-bats-shave.md
@@ -0,0 +1,7 @@
+---
+"llamaindex": patch
+"@llamaindex/cloud": patch
+"docs": patch
+---
+
+fix: typo in custom page separator parameter for LlamaParse
diff --git a/apps/docs/docs/modules/data_loaders/llama_parse/index.mdx b/apps/docs/docs/modules/data_loaders/llama_parse/index.mdx
index 830232561..dbb1fcee4 100644
--- a/apps/docs/docs/modules/data_loaders/llama_parse/index.mdx
+++ b/apps/docs/docs/modules/data_loaders/llama_parse/index.mdx
@@ -27,25 +27,25 @@ They can be divided into two groups.
- `apiKey` is required. Can be set as an environment variable `LLAMA_CLOUD_API_KEY`
- `checkInterval` is the interval in seconds to check if the parsing is done. Default is `1`.
-- `maxTimeout` is the maximum timout to wait for parsing to finish. Default is `2000`
+- `maxTimeout` is the maximum timeout to wait for parsing to finish. Default is `2000`
- `verbose` shows progress of the parsing. Default is `true`
- `ignoreErrors` set to false to get errors while parsing. Default is `true` and returns an empty array on error.
#### Advanced params:
- `resultType` can be set to `markdown`, `text` or `json`. Defaults to `text`. More information about `json` mode on the next pages.
-- `language` primarly helps with OCR recognition. Defaults to `en`. Click [here](../../../api/type-aliases/Language.md) for a list of supported languages.
+- `language` primarily helps with OCR recognition. Defaults to `en`. Click [here](../../../api/type-aliases/Language.md) for a list of supported languages.
- `parsingInstructions?` Optional. Can help with complicated document structures. See this [LlamaIndex Blog Post](https://www.llamaindex.ai/blog/launching-the-first-genai-native-document-parsing-platform) for an example.
- `skipDiagonalText?` Optional. Set to true to ignore diagonal text. (Text that is not rotated 0, 90, 180 or 270 degrees)
- `invalidateCache?` Optional. Set to true to ignore the LlamaCloud cache. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice. Can be useful for testing when trying to re-parse the same document with, e.g. different `parsingInstructions`.
- `doNotCache?` Optional. Set to true to not cache the document.
- `fastMode?` Optional. Set to true to use the fast mode. This mode will skip OCR of images, and table/heading reconstruction. Note: Non-compatible with `gpt4oMode`.
-- `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most cases.
-- `pageSeperator?` Optional. The page seperator to use. Defaults is `\\n---\\n`.
+- `doNotUnrollColumns?` Optional. Set to true to keep the text according to document layout. Reduce reconstruction accuracy, and LLMs/embeddings performances in most cases.
+- `pageSeparator?` Optional. The page separator 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`.
+- `targetPages?` Optional. Specify which pages to parse by specifying them as a comma-separated list. First page is `0`.
- `numWorkers` as in the python version, is set in `SimpleDirectoryReader`. Default is 1.
### LlamaParse with SimpleDirectoryReader
diff --git a/packages/cloud/openapi.json b/packages/cloud/openapi.json
index d6993cd5b..c04027685 100644
--- a/packages/cloud/openapi.json
+++ b/packages/cloud/openapi.json
@@ -12113,9 +12113,9 @@
"description": "Template for how metadata is formatted, with {key} and {value} placeholders.",
"default": "{key}: {value}"
},
- "metadata_seperator": {
+ "metadata_separator": {
"type": "string",
- "title": "Metadata Seperator",
+ "title": "Metadata Separator",
"description": "Separator between metadata fields when converting to string.",
"default": "\n"
},
diff --git a/packages/llamaindex/CHANGELOG.md b/packages/llamaindex/CHANGELOG.md
index d6b681979..aa2cf65b5 100644
--- a/packages/llamaindex/CHANGELOG.md
+++ b/packages/llamaindex/CHANGELOG.md
@@ -125,7 +125,7 @@
### Patch Changes
-- 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page seperator to LlamaParseReader
+- 6bc5bdd: feat: add cache disabling, fast mode, do not unroll columns mode and custom page separator to LlamaParseReader
- bf25ff6: fix: polyfill for cloudflare worker
- e6d6576: chore: use `unpdf`
diff --git a/packages/llamaindex/src/readers/LlamaParseReader.ts b/packages/llamaindex/src/readers/LlamaParseReader.ts
index dd2333785..5acaa4431 100644
--- a/packages/llamaindex/src/readers/LlamaParseReader.ts
+++ b/packages/llamaindex/src/readers/LlamaParseReader.ts
@@ -128,7 +128,7 @@ export class LlamaParseReader extends FileReader {
// Wether to keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most cases.
doNotUnrollColumns?: boolean;
// The page separator to use to split the text. Default is None, which means the parser will use the default separator '\\n---\\n'.
- pageSeperator?: string;
+ pageSeparator?: string;
// Whether to use gpt-4o to extract text from documents.
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.
@@ -184,7 +184,7 @@ export class LlamaParseReader extends FileReader {
do_not_cache: this.doNotCache?.toString(),
fast_mode: this.fastMode?.toString(),
do_not_unroll_columns: this.doNotUnrollColumns?.toString(),
- page_seperator: this.pageSeperator,
+ page_separator: this.pageSeparator,
gpt4o_mode: this.gpt4oMode?.toString(),
gpt4o_api_key: this.gpt4oApiKey,
bounding_box: this.boundingBox,
--
GitLab