llmsherpa 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: bafd988ec6e1909868e5afa6ff45a5d551f51867ddaebabbbc6c2f2fdcf7aac2
+  data.tar.gz: 4d697e0cb08d6d1d8306262da81d2fda1c5595e9dfd843109861823ba42cb781
+SHA512:
+  metadata.gz: 9ae38fa4cc6dfe494313394a8cdd19ae536af0cf2b5f3191887515b1b6de63d7604959f03ce178d3bda902a640f640cc6a31d27b44255e23b1b111fbbe5897ef
+  data.tar.gz: 27fe378529b8bac701fe86475ac3c921fd79291d9d6808dbacab3c2d2b804724bd9d362896615b4f2354241b039c06105ec1b57404955b746ab50b45641c5832

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,13 @@
+AllCops:
+  TargetRubyVersion: 2.6
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 120

data/CHANGELOG.md

@@ -0,0 +1,5 @@
+## [Unreleased]
+
+## [0.1.0] - 2024-03-21
+
+- Initial release

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,84 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at luca.pradovera@gmail.com. All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior,  harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0,
+available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2024 Luca Pradovera
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,44 @@
+# Llmsherpa
+
+This gem implements a Ruby version of the https://github.com/nlmatics/llmsherpa Python package, with the goal of making it easy to parse and ingest documents.
+
+You will need to run an instance of https://github.com/nlmatics/nlm-ingestor. The recommended way is using Docker:
+
+```
+docker pull ghcr.io/nlmatics/nlm-ingestor:latest
+docker run -p 5010:5001 ghcr.io/nlmatics/nlm-ingestor:latest
+```
+
+Many thanks to the [NLMatics team](https://github.com/nlmatics) for their awesome work.
+
+## Installation
+
+Install the gem and add to the application's Gemfile by executing:
+
+    $ bundle add llmsherpa
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+    $ gem install llmsherpa
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/lpradovera/llmsherpa. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/lpradovera/llmsherpa/blob/main/CODE_OF_CONDUCT.md).
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the Llmsherpa project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/llmsherpa/blob/main/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+require "rubocop/rake_task"
+
+RuboCop::RakeTask.new
+
+task default: %i[spec rubocop]

data/lib/llmsherpa/blocks.rb

@@ -0,0 +1,448 @@
+# frozen_string_literal: true
+
+module Llmsherpa
+  # A block is a node in the layout tree. It can be a paragraph, a list item, a table, or a section header.
+  # This is the base class for all blocks such as Paragraph, ListItem, Table, Section.
+  class Block
+    attr_accessor :tag, :level, :page_idx, :block_idx, :top, :left, :bbox, :sentences, :children, :parent, :block_json
+
+    def initialize(block_json = nil)
+      @tag = block_json["tag"] if block_json&.key?("tag")
+      @level = (block_json["level"] if block_json&.key?("level")) || 0
+      @page_idx = block_json["page_idx"] if block_json&.key?("page_idx")
+      @block_idx = block_json["block_idx"] if block_json&.key?("block_idx")
+      @top = block_json["top"] if block_json&.key?("top")
+      @left = block_json["left"] if block_json&.key?("left")
+      @bbox = block_json["bbox"] if block_json&.key?("bbox")
+      @sentences = block_json["sentences"] if block_json&.key?("sentences")
+      @children = []
+      @parent = nil
+      @block_json = block_json
+    end
+
+    # Adds a child to the block. Sets the parent of the child to self.
+    def add_child(node)
+      @children.push(node)
+      node.parent = self
+    end
+
+    # Converts the block to html. This is a virtual method and should be implemented by the derived classes.
+    def to_html(include_children = false, recurse = false); end
+
+    # Converts the block to text. This is a virtual method and should be implemented by the derived classes.
+    def to_text(include_children = false, recurse = false); end
+
+    # Returns the parent chain of the block consisting of all the parents of the block until the root.
+    def parent_chain
+      chain = []
+      parent = self.parent
+      while parent
+        chain.push(parent)
+        parent = parent.parent
+      end
+      chain.reverse
+    end
+
+    # Returns the text of the parent chain of the block. This is useful for adding section information to the text.
+    def parent_text
+      parent_chain = self.parent_chain
+      header_texts = []
+      para_texts = []
+      parent_chain.each do |p|
+        if p.tag == "header"
+          header_texts.push(p.to_text)
+        elsif %w[list_item para].include?(p.tag)
+          para_texts.push(p.to_text)
+        end
+      end
+      text = header_texts.join(" > ")
+      text += "\n#{para_texts.join("\n")}" unless para_texts.empty?
+      text
+    end
+
+    # Returns the text of the block with section information. This provides context to the text.
+    def to_context_text(include_section_info = true)
+      text = ""
+      text += "#{parent_text}\n" if include_section_info
+      text += if %w[list_item para table].include?(@tag)
+                to_text(true, true)
+              else
+                to_text
+              end
+      text
+    end
+
+    # Iterates over all the children of the node and calls the node_visitor function on each child.
+    def iter_children(node, level, &node_visitor)
+      node.children.each do |child|
+        node_visitor.call(child)
+        iter_children(child, level + 1, &node_visitor) unless %w[list_item para table].include?(child.tag)
+      end
+    end
+
+    # Returns all the paragraphs in the block. This is useful for getting all the paragraphs in a section.
+    def paragraphs
+      paragraphs = []
+      iter_children(self, 0) do |node|
+        paragraphs.push(node) if node.tag == "para"
+      end
+      paragraphs
+    end
+
+    # Returns all the chunks in the block. Chunking automatically splits the document into paragraphs, lists, and tables without any prior knowledge of the document structure.
+    def chunks
+      chunks = []
+      iter_children(self, 0) do |node|
+        chunks.push(node) if %w[para list_item table].include?(node.tag)
+      end
+      chunks
+    end
+
+    # Returns all the tables in
+    # Returns all the tables in the block. This is useful for getting all the tables in a section.
+    def tables
+      tables = []
+      iter_children(self, 0) do |node|
+        tables.push(node) if node.tag == "table"
+      end
+      tables
+    end
+
+    # Returns all the sections in the block. This is useful for getting all the sections in a document.
+    def sections
+      sections = []
+      iter_children(self, 0) do |node|
+        sections.push(node) if node.tag == "header"
+      end
+      sections
+    end
+  end
+
+  # A paragraph is a block of text. It can have children such as lists. A paragraph has tag 'para'.
+  class Paragraph < Block
+    def to_text(include_children = false, recurse = false)
+      para_text = @sentences.join("\n")
+      if include_children
+        @children.each do |child|
+          para_text += "\n#{child.to_text(include_children: recurse, recurse: recurse)}"
+        end
+      end
+      para_text
+    end
+
+    def to_html(include_children = false, recurse = false)
+      html_str = "<p>"
+      html_str += @sentences.join("\n")
+      if include_children && !@children.empty?
+        html_str += "<ul>"
+        @children.each do |child|
+          html_str += child.to_html(include_children: recurse, recurse: recurse)
+        end
+        html_str += "</ul>"
+      end
+      html_str += "</p>"
+      html_str
+    end
+  end
+
+  # A section is a block of text. It can have children such as paragraphs, lists, and tables. A section has tag 'header'.
+  class Section < Block
+    attr_accessor :title
+
+    def initialize(section_json)
+      super(section_json)
+      @title = @sentences.join("\n")
+    end
+
+    def to_text(include_children = false, recurse = false)
+      text = @title
+      if include_children
+        @children.each do |child|
+          text += "\n#{child.to_text(include_children: recurse, recurse: recurse)}"
+        end
+      end
+      text
+    end
+
+    def to_html(include_children = false, recurse = false)
+      html_str = "<h#{@level + 1}>#{@title}</h#{@level + 1}>"
+      if include_children
+        @children.each do |child|
+          html_str += child.to_html(include_children: recurse, recurse: recurse)
+        end
+      end
+      html_str
+    end
+  end
+
+  # A list item is a block of text. It can have child list items. A list item has tag 'list_item'.
+  class ListItem < Block
+    def to_text(include_children = false, recurse = false)
+      text = @sentences.join("\n")
+      if include_children
+        @children.each do |child|
+          text += "\n#{child.to_text(include_children: recurse, recurse: recurse)}"
+        end
+      end
+      text
+    end
+
+    def to_html(include_children = false, recurse = false)
+      html_str = "<li>"
+      html_str += @sentences.join("\n")
+      if include_children && !@children.empty?
+        html_str += "<ul>"
+        @children.each do |child|
+          html_str += child.to_html(include_children: recurse, recurse: recurse)
+        end
+        html_str += "</ul>"
+      end
+      html_str += "</li>"
+      html_str
+    end
+  end
+
+  # A table cell is a block of text. It can have child paragraphs. A table cell has tag 'table_cell'.
+  # A table cell is contained within table rows.
+  class TableCell < Block
+    attr_accessor :col_span, :cell_value, :cell_node
+
+    def initialize(cell_json)
+      super(cell_json)
+      @col_span = cell_json["col_span"] if cell_json.key?("col_span")
+      @cell_value = cell_json["cell_value"]
+      @cell_node = if @cell_value.is_a?(String)
+                     nil
+                   else
+                     Paragraph.new(@cell_value)
+                   end
+    end
+
+    def to_text
+      cell_text = @cell_value
+      cell_text = @cell_node.to_text if @cell_node
+      cell_text
+    end
+
+    def to_html
+      cell_html = @cell_value
+      cell_html = @cell_node.to_html if @cell_node
+      if @col_span == 1
+        "<td colSpan='#{@col_span}'>#{cell_html}</td>"
+      else
+        "<td>#{cell_html}</td>"
+      end
+    end
+  end
+
+  # A table row is a block of text
+  # Base Block class assumed to be defined elsewhere
+
+  class TableRow < Block
+    # Initializes a TableRow with child table cells
+    def initialize(row_json)
+      @cells = []
+      if row_json["type"] == "full_row"
+        cell = TableCell.new(row_json)
+        @cells << cell
+      else
+        row_json["cells"].each do |cell_json|
+          cell = TableCell.new(cell_json)
+          @cells << cell
+        end
+      end
+    end
+
+    # Returns text of a row with text from all the cells in the row delimited by '|'
+    def to_text(_include_children = false, _recurse = false)
+      @cells.map(&:to_text).join(" | ")
+    end
+
+    # Returns html for a <tr> with html from all the cells in the row as <td>
+    def to_html(_include_children = false, _recurse = false)
+      html_str = "<tr>"
+      @cells.each { |cell| html_str += cell.to_html }
+      html_str += "</tr>"
+      html_str
+    end
+  end
+
+  class TableHeader < Block
+    # Initializes a TableHeader with child table cells
+    def initialize(row_json)
+      super(row_json)
+      @cells = []
+      row_json["cells"].each do |cell_json|
+        cell = TableCell.new(cell_json)
+        @cells << cell
+      end
+    end
+
+    # Returns text of a header row in markdown format
+    def to_text(_include_children = false, _recurse = false)
+      cell_text = @cells.map(&:to_text).join(" | ")
+      cell_text += "\n" + @cells.map { "---" }.join(" | ")
+      cell_text
+    end
+
+    # Returns html for a <th> with html from all the cells in the row as <td>
+    def to_html(_include_children = false, _recurse = false)
+      html_str = "<th>"
+      @cells.each { |cell| html_str += cell.to_html }
+      html_str += "</th>"
+      html_str
+    end
+  end
+
+  # The Table and Document classes would be similarly translated, focusing on Ruby's syntax for inheritance, method definitions, and iteration.
+  # The `initialize` method in Ruby is used instead of `__init__` in Python, and instance variables are prefixed with `@`.
+  # Method definitions in Ruby do not require the `def` keyword for each argument, and blocks of code are enclosed in `do...end` instead of indentation.
+
+  # This conversion assumes the presence of similarly functional TableCell, Paragraph, ListItem, and Section classes or modules in Ruby.
+  class Table < Block
+    # Initializes a Table with child table rows and headers
+    def initialize(table_json, _parent)
+      super(table_json)
+      @rows = []
+      @headers = []
+      @name = table_json["name"]
+      return unless table_json.include?("table_rows")
+
+      table_json["table_rows"].each do |row_json|
+        if row_json["type"] == "table_header"
+          row = TableHeader.new(row_json)
+          @headers << row
+        else
+          row = TableRow.new(row_json)
+          @rows << row
+        end
+      end
+    end
+
+    # Returns text of a table with text from all the rows in the table delimited by '\n'
+    def to_text(_include_children = false, _recurse = false)
+      "#{@headers.map(&:to_text).join("\n")}\n#{@rows.map(&:to_text).join("\n")}"
+    end
+
+    # Returns html for a <table> with html from all the rows in the table as <tr>
+    def to_html(_include_children = false, _recurse = false)
+      html_str = "<table>"
+      @headers.each { |header| html_str += header.to_html }
+      @rows.each { |row| html_str += row.to_html }
+      html_str += "</table>"
+      html_str
+    end
+  end
+
+  class Document
+    # Initializes a Document with a layout tree from the json
+    def initialize(blocks_json)
+      @reader = LayoutReader.new
+      @root_node = @reader.read(blocks_json)
+      @json = blocks_json
+    end
+
+    # Returns all the chunks in the document
+    def chunks
+      @root_node.chunks
+    end
+
+    # Returns all the tables in the document
+    def tables
+      @root_node.tables
+    end
+
+    # Returns all the sections in the document
+    def sections
+      @root_node.sections
+    end
+
+    # Returns text of a document by iterating through all the sections '\n'
+    def to_text
+      sections.map { |section| section.to_text(true, true) }.join("\n")
+    end
+
+    # Returns html for the document by iterating through all the sections
+    def to_html
+      html_str = "<html>"
+      sections.each { |section| html_str += section.to_html(true, true) }
+      html_str += "</html>"
+      html_str
+    end
+  end
+
+  class LayoutReader
+    # Reads the layout tree from the JSON returned by the parser API.
+
+    def debug(pdf_root)
+      iter_children = lambda do |node, level|
+        node.children.each do |child|
+          puts "#{"-" * level} #{child.tag} (#{child.children.length}) #{child.to_text}"
+          iter_children.call(child, level + 1)
+        end
+      end
+      iter_children.call(pdf_root, 0)
+    end
+
+    def read(blocks_json)
+      root = Block.new
+      parent_stack = [root]
+      prev_node = root
+      parent = root
+      list_stack = []
+
+      blocks_json.each do |block|
+        list_stack = [] if block["tag"] != "list_item" && !list_stack.empty?
+
+        node = case block["tag"]
+               when "para"
+                 Paragraph.new(block)
+               when "table"
+                 Table.new(block, prev_node)
+               when "list_item"
+                 ListItem.new(block)
+               when "header"
+                 Section.new(block)
+               else
+                 raise "Unsupported block type: #{block["tag"]}"
+               end
+
+        case block["tag"]
+        when "para"
+          parent.add_child(node)
+        when "table"
+          parent.add_child(node)
+        when "list_item"
+          if prev_node.tag == "para" && prev_node.level == node.level
+            list_stack << prev_node
+          elsif prev_node.tag == "list_item"
+            if node.level > prev_node.level
+              list_stack << prev_node
+            elsif node.level < prev_node.level
+              list_stack.pop while !list_stack.empty? && list_stack.last.level > node.level
+            end
+          end
+          if list_stack.any?
+            list_stack.last.add_child(node)
+          else
+            parent.add_child(node)
+          end
+        when "header"
+          if node.level > parent.level
+            parent_stack << node
+            parent.add_child(node)
+          else
+            parent_stack.pop while parent_stack.length > 1 && parent_stack.last.level >= node.level
+            parent_stack.last.add_child(node)
+            parent_stack << node
+          end
+          parent = node
+        end
+
+        prev_node = node
+      end
+
+      root
+    end
+  end
+end

data/lib/llmsherpa/layout_pdf_reader.rb

@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+
+require "net/http"
+require "uri"
+require "json"
+require "open-uri"
+require "tempfile"
+
+module Llmsherpa
+  class LayoutPDFReader
+    # Reads PDF content and understands hierarchical layout of the document sections and structural components
+    def initialize(parser_api_url)
+      @parser_api_url = parser_api_url
+    end
+
+    def read_pdf(path_or_url, contents = nil)
+      pdf_file = if contents
+                   [path_or_url, contents, "application/pdf"]
+                 else
+                   is_url = %w[http https].include?(URI.parse(path_or_url).scheme)
+                   if is_url
+                     _download_pdf(path_or_url)
+                   else
+                     file_name = path_or_url
+                     file_data = nil # no need to read the file here
+                     [file_name, file_data, "application/pdf"]
+                   end
+                 end
+
+      parser_response = _parse_pdf(pdf_file)
+      response_json = JSON.parse(parser_response.body)
+      blocks = response_json["return_dict"]["result"]["blocks"]
+      Document.new(blocks)
+    end
+
+    private
+
+    def _download_pdf(pdf_url)
+      user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36"
+      download_uri = URI(pdf_url)
+      download_request = Net::HTTP::Get.new(download_uri)
+      download_request["User-Agent"] = user_agent
+      download_response = Net::HTTP.start(download_uri.hostname, download_uri.port,
+                                          use_ssl: download_uri.scheme == "https") do |http|
+        http.request(download_request)
+      end
+      file_name = File.basename(download_uri.path)
+      temp_file = Tempfile.new(file_name)
+      temp_file.write(download_response.body)
+      pdf_file = [temp_file.path, "", "application/pdf"] if download_response.code == "200"
+      pdf_file
+    end
+
+    def _parse_pdf(pdf_file)
+      uri = URI(@parser_api_url)
+      request = Net::HTTP::Post.new(uri)
+      request.set_form({ "file" => File.open(pdf_file[0]) }, "multipart/form-data")
+      Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
+        http.request(request)
+      end
+    end
+  end
+end

data/lib/llmsherpa/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Llmsherpa
+  VERSION = "0.1.0"
+end

data/lib/llmsherpa.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+require_relative "llmsherpa/version"
+require_relative "llmsherpa/blocks"
+require_relative "llmsherpa/layout_pdf_reader"
+
+module Llmsherpa
+  class Error < StandardError; end
+  # Your code goes here...
+end

data/sig/llmsherpa.rbs

@@ -0,0 +1,4 @@
+module Llmsherpa
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,60 @@
+--- !ruby/object:Gem::Specification
+name: llmsherpa
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Luca Pradovera
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2024-03-21 00:00:00.000000000 Z
+dependencies: []
+description:
+email:
+- luca.pradovera@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".DS_Store"
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/llmsherpa.rb
+- lib/llmsherpa/blocks.rb
+- lib/llmsherpa/layout_pdf_reader.rb
+- lib/llmsherpa/version.rb
+- sig/llmsherpa.rbs
+homepage: https://github.com/lpradovera/llmsherpa
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/lpradovera/llmsherpa
+  source_code_uri: https://github.com/lpradovera/llmsherpa
+  changelog_uri: https://github.com/lpradovera/llmsherpa/blob/main/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.3
+signing_key:
+specification_version: 4
+summary: Client for the nlm-ingestor server
+test_files: []