From e3a4916782c3f54d0f2b47302f112b97b8575165 Mon Sep 17 00:00:00 2001
From: Stefano Fiorucci <stefanofiorucci@gmail.com>
Date: Fri, 2 Aug 2024 09:53:12 +0200
Subject: [PATCH] update unstructured (#249)

---
 integrations/unstructured-file-converter.md | 55 +++++++++++++++------
 1 file changed, 41 insertions(+), 14 deletions(-)

diff --git a/integrations/unstructured-file-converter.md b/integrations/unstructured-file-converter.md
index d8eece0d..ef874ff2 100644
--- a/integrations/unstructured-file-converter.md
+++ b/integrations/unstructured-file-converter.md
@@ -14,37 +14,64 @@ type: Data Ingestion
 report_issue: https://github.com/deepset-ai/haystack-core-integrations/issues
 logo: /logos/unstructured.svg
 version: Haystack 2.0
+toc: true
 ---
+- [Overview](#overview)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Connecting to the Unstructured API](#connecting-to-the-unstructured-api)
+    - [Hosted API](#hosted-api)
+    - [Local API (Docker)](#local-api-docker)
+  - [Running Unstructured File Converter](#running-unstructured-file-converter)
+    - [In isolation](#in-isolation)
+    - [In a Haystack Pipeline](#in-a-haystack-pipeline)
 
-Component for the Haystack (2.x) LLM framework to easily convert files and directories into Documents using the Unstructured API.
 
-**[Unstructured](https://unstructured-io.github.io/unstructured/index.html)** provides a series of tools to do **ETL for LLMs**. This component calls the Unstructured API that simply extracts text and other information from a vast range of file formats. See [supported file types](https://docs.unstructured.io/api-reference/api-services/overview#supported-file-types).
+
+## Overview
+Component for the Haystack (2.x) LLM framework to convert files and directories into Documents using the Unstructured API.
+
+**[Unstructured](https://unstructured-io.github.io/unstructured/index.html)** provides ETL tools for LLMs, extracting text and other information from various file formats. See [supported file types](https://docs.unstructured.io/api-reference/api-services/overview#supported-file-types) for more details.
 
 ## Installation
+To install the [Unstructured File Converter](https://docs.haystack.deepset.ai/docs/unstructuredfileconverter), run:
 
 ```bash
 pip install unstructured-fileconverter-haystack
 ```
 
-### Hosted API
-If you plan to use the hosted version of the Unstructured API, you just need the **(free) Unstructured API key**. You can get it by signing up [here](https://unstructured.io/api-key-free).
+## Usage
+
+### Connecting to the Unstructured API
+#### Hosted API
+
+The Unstructured API is available in both free and paid versions: Unstructured Serverless API or Free Unstructured API.
 
-### Local API (Docker)
-If you want to run your own local instance of the Unstructured API, you need Docker and you can find instructions [here](https://unstructured-io.github.io/unstructured/api.html#using-docker-images).
+For the Free Unstructured API, the API URL is `https://api.unstructured.io/general/v0/general`. For the Unstructured Serverless API, find your unique API URL in your Unstructured account.
 
-In short, this should work:
+Note that the API keys for free and paid versions are not interchangeable.
+
+Set the Unstructured API key as an environment variable:
 ```bash
-docker run -p 8000:8000 -d --rm --name unstructured-api quay.io/unstructured-io/unstructured-api:latest --port 8000 --host 0.0.0.0
+export UNSTRUCTURED_API_KEY=your_api_key
 ```
 
-## Usage
+#### Local API (Docker)
+You can run a local instance of the Unstructured API using Docker:
 
-If you plan to use the hosted version of the Unstructured API, set the Unstructured API key as an environment variable `UNSTRUCTURED_API_KEY`:
 ```bash
-export UNSTRUCTURED_API_KEY=your_api_key
+docker run -p 8000:8000 -d --rm --name unstructured-api quay.io/unstructured-io/unstructured-api:latest --port 8000 --host 0.0.0.0
+```
+
+When initializing the component, specify the localhost URL:
+```python
+from haystack_integrations.components.converters.unstructured import UnstructuredFileConverter
+
+converter = UnstructuredFileConverter(api_url="http://localhost:8000/general/v0/general")
 ```
 
-### In isolation
+### Running Unstructured File Converter
+#### In isolation
 ```python
 import os
 from haystack_integrations.components.converters.unstructured import UnstructuredFileConverter
@@ -53,7 +80,7 @@ converter = UnstructuredFileConverter()
 documents = converter.run(paths = ["a/file/path.pdf", "a/directory/path"])["documents"]
 ```
 
-### In a Haystack Pipeline
+#### In a Haystack Pipeline
 ```python
 import os
 from haystack import Pipeline
@@ -69,4 +96,4 @@ indexing.add_component("writer", DocumentWriter(document_store))
 indexing.connect("converter", "writer")
 
 indexing.run({"converter": {"paths": ["a/file/path.pdf", "a/directory/path"]}})
-```
+```
\ No newline at end of file