Docs. OG metadata for Sphinx docs.

SergiiShcherbak · SergiiShcherbak · commit 97f8f29751d9 · 2025-04-01T17:17:36.000+02:00
diff --git a/CITATION.cff b/CITATION.cff
@@ -4,6 +4,6 @@ authors:
   - family-names: Shcherbak
     given-names: Sergii
     email: sergii@shcherbak.ai
-title: "ContextGem: The easiest and fastest way to build LLM extraction workflows through powerful abstractions"
+title: "ContextGem: Easier and faster way to build LLM extraction workflows through powerful abstractions"
 date-released: 2024-04-01
 url: "https://github.com/shcherbak-ai/contextgem"
diff --git a/NOTICE b/NOTICE
@@ -1,4 +1,4 @@
-ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions
+ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions
 =========================================================================================================
 
 Copyright (c) 2025 Shcherbak AI AS
@@ -48,6 +48,7 @@ Development Dependencies:
 - sphinx-book-theme: Book-like theme for Sphinx
 - sphinx-copybutton: Adds copy button to code blocks in Sphinx docs
 - sphinx-design: Component library for Sphinx documentation
+- sphinxext-opengraph: OpenGraph metadata support for Sphinx documentation
 
 Each of these components may have their own licenses. Users should refer to the 
 respective project repositories for detailed license information.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
-![ContextGem](/docs/source/_static/contextgem_poster.png "ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions")
+![ContextGem](/docs/source/_static/contextgem_poster.png "ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions")
 
-# ContextGem: The Easiest and Fastest Way to Build LLM Extraction Workflows
+# ContextGem: Easier and faster way to build LLM extraction workflows
 
 [![tests](https://github.com/shcherbak-ai/contextgem/actions/workflows/ci-tests.yml/badge.svg?branch=main)](https://github.com/shcherbak-ai/contextgem/actions/workflows/ci-tests.yml)
 [![Coverage](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/SergiiShcherbak/daaee00e1dfff7a29ca10a922ec3becd/raw/coverage.json)](https://github.com/shcherbak-ai/contextgem/actions)
@@ -224,7 +224,7 @@ See more examples in the documentation:
 - [Concept Extraction from Document (vision)](https://contextgem.dev/quickstart.html#concept-extraction-from-document-vision)
 
 ### Advanced usage examples
-- [Extracting Aspects with Concepts](https://contextgem.dev/advanced_usage.html#extracting-aspects-with-concepts)
+- [Extracting Aspects Containing Concepts](https://contextgem.dev/advanced_usage.html#extracting-aspects-with-concepts)
 - [Extracting Aspects and Concepts from a Document](https://contextgem.dev/advanced_usage.html#extracting-aspects-and-concepts-from-a-document)
 - [Using a Multi-LLM Pipeline to Extract Data from Several Documents](https://contextgem.dev/advanced_usage.html#using-a-multi-llm-pipeline-to-extract-data-from-several-documents)
 
@@ -236,6 +236,17 @@ ContextGem leverages LLMs' long context windows to deliver superior extraction a
 Read more on [how it works](https://contextgem.dev/how_it_works.html) in the documentation.
 
 
+## ⚡ Optimizations
+
+ContextGem documentation offers guidance on optimization strategies to maximize performance, minimize costs, and enhance extraction accuracy:
+
+- [Optimizing for Accuracy](https://contextgem.dev/optimizations/optimization_accuracy.html)
+- [Optimizing for Speed](https://contextgem.dev/optimizations/optimization_speed.html)
+- [Optimizing for Cost](https://contextgem.dev/optimizations/optimization_cost.html)
+- [Dealing with Long Documents](https://contextgem.dev/optimizations/optimization_long_docs.html)
+- [Choosing the Right LLM(s)](https://contextgem.dev/optimizations/optimization_choosing_llm.html)
+
+
 ## 📚 Documentation
 
 Full documentation is available at [contextgem.dev](https://contextgem.dev).
diff --git a/contextgem/__init__.py b/contextgem/__init__.py
@@ -17,7 +17,7 @@
 #
 
 """
-ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions
+ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions
 """
 
 __version__ = "0.1.0"
diff --git a/dev/readme.template.md b/dev/readme.template.md
@@ -1,6 +1,6 @@
-![ContextGem](/docs/source/_static/contextgem_poster.png "ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions")
+![ContextGem](/docs/source/_static/contextgem_poster.png "ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions")
 
-# ContextGem: The Easiest and Fastest Way to Build LLM Extraction Workflows
+# ContextGem: Easier and faster way to build LLM extraction workflows
 
 [![tests](https://github.com/shcherbak-ai/contextgem/actions/workflows/ci-tests.yml/badge.svg?branch=main)](https://github.com/shcherbak-ai/contextgem/actions/workflows/ci-tests.yml)
 [![Coverage](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/SergiiShcherbak/daaee00e1dfff7a29ca10a922ec3becd/raw/coverage.json)](https://github.com/shcherbak-ai/contextgem/actions)
@@ -56,7 +56,7 @@ See more examples in the documentation:
 - [Concept Extraction from Document (vision)](https://contextgem.dev/quickstart.html#concept-extraction-from-document-vision)
 
 ### Advanced usage examples
-- [Extracting Aspects with Concepts](https://contextgem.dev/advanced_usage.html#extracting-aspects-with-concepts)
+- [Extracting Aspects Containing Concepts](https://contextgem.dev/advanced_usage.html#extracting-aspects-with-concepts)
 - [Extracting Aspects and Concepts from a Document](https://contextgem.dev/advanced_usage.html#extracting-aspects-and-concepts-from-a-document)
 - [Using a Multi-LLM Pipeline to Extract Data from Several Documents](https://contextgem.dev/advanced_usage.html#using-a-multi-llm-pipeline-to-extract-data-from-several-documents)
 
@@ -68,6 +68,17 @@ ContextGem leverages LLMs' long context windows to deliver superior extraction a
 Read more on [how it works](https://contextgem.dev/how_it_works.html) in the documentation.
 
 
+## ⚡ Optimizations
+
+ContextGem documentation offers guidance on optimization strategies to maximize performance, minimize costs, and enhance extraction accuracy:
+
+- [Optimizing for Accuracy](https://contextgem.dev/optimizations/optimization_accuracy.html)
+- [Optimizing for Speed](https://contextgem.dev/optimizations/optimization_speed.html)
+- [Optimizing for Cost](https://contextgem.dev/optimizations/optimization_cost.html)
+- [Dealing with Long Documents](https://contextgem.dev/optimizations/optimization_long_docs.html)
+- [Choosing the Right LLM(s)](https://contextgem.dev/optimizations/optimization_choosing_llm.html)
+
+
 ## 📚 Documentation
 
 Full documentation is available at [contextgem.dev](https://contextgem.dev).
diff --git a/dev/usage_examples/docs/optimizations/optimization_accuracy.py b/dev/usage_examples/docs/optimizations/optimization_accuracy.py
@@ -7,15 +7,15 @@
 # Define document
 doc = Document(
     raw_text="Non-Disclosure Agreement...",
-    sat_model_id="sat-6l",  # default is "sat-3l-sm"
+    sat_model_id="sat-6l-sm",  # default is "sat-3l-sm"
     paragraph_segmentation_mode="sat",  # default is "newlines"
     # sentence segmentation mode is always "sat", as other approaches proved to be less accurate
 )
 
 # Define document concepts
 doc.concepts = [
     StringConcept(
-        name="Title",
+        name="Title",  # A very simple concept, just an example for testing purposes
         description="Title of the document",
         add_justifications=True,  # enable justifications
         justification_depth="brief",  # default
@@ -24,7 +24,8 @@
                 content="Supplier Agreement",
             )
         ],
-    )
+    ),
+    # ... add other concepts ...
 ]
 
 # ... attach other aspects/concepts to the document ...
diff --git a/docs/build_raw_docs_for_llm.py b/docs/build_raw_docs_for_llm.py
@@ -139,7 +139,7 @@ def concatenate_docs(doc_paths: list[str], text_dir: str, output_file: str) -> N
     """
     with open(output_file, "w", encoding="utf-8") as outfile:
         outfile.write(
-            "ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions\n"
+            "ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions\n"
         )
         outfile.write("=" * 100 + "\n\n")
         outfile.write("Copyright (c) 2025 Shcherbak AI AS\n")
diff --git a/docs/docs-raw-for-llm.txt b/docs/docs-raw-for-llm.txt
@@ -1,4 +1,4 @@
-ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions
+ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions
 ====================================================================================================
 
 Copyright (c) 2025 Shcherbak AI AS
@@ -3887,8 +3887,8 @@ Below are complete, self-contained examples demonstrating advanced
 usage of ContextGem.
 
 
-🔍 Extracting Aspects with Concepts
-===================================
+🔍 Extracting Aspects Containing Concepts
+=========================================
 
 Tip:
 
@@ -4550,15 +4550,15 @@ Example of optimizing extraction for accuracy
    # Define document
    doc = Document(
        raw_text="Non-Disclosure Agreement...",
-       sat_model_id="sat-6l",  # default is "sat-3l-sm"
+       sat_model_id="sat-6l-sm",  # default is "sat-3l-sm"
        paragraph_segmentation_mode="sat",  # default is "newlines"
        # sentence segmentation mode is always "sat", as other approaches proved to be less accurate
    )
 
    # Define document concepts
    doc.concepts = [
        StringConcept(
-           name="Title",
+           name="Title",  # A very simple concept, just an example for testing purposes
            description="Title of the document",
            add_justifications=True,  # enable justifications
            justification_depth="brief",  # default
@@ -4567,7 +4567,8 @@ Example of optimizing extraction for accuracy
                    content="Supplier Agreement",
                )
            ],
-       )
+       ),
+       # ... add other concepts ...
    ]
 
    # ... attach other aspects/concepts to the document ...
diff --git a/docs/source/_static/contextgem_website_preview_banner.png b/docs/source/_static/contextgem_website_preview_banner.png
diff --git a/docs/source/advanced_usage.rst b/docs/source/advanced_usage.rst
@@ -21,8 +21,8 @@ Advanced usage examples
 Below are complete, self-contained examples demonstrating advanced usage of ContextGem.
 
 
-🔍 Extracting Aspects with Concepts
-------------------------------------
+🔍 Extracting Aspects Containing Concepts
+------------------------------------------
 
 .. tip::
    Concept extraction is useful for extracting specific data points from a document or an aspect. For example, a "Payment terms" aspect in a contract may have multiple concepts:
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -66,6 +66,7 @@ def setup(app):
     "sphinx_copybutton",
     "sphinx.ext.autosectionlabel",
     "sphinx_design",
+    "sphinxext.opengraph",
 ]
 
 # Intersphinx mapping
@@ -108,3 +109,10 @@ def setup(app):
     "show_navbar_depth": 2,
     "pygment_dark_style": "github-dark-high-contrast",
 }
+
+# Open Graph metadata
+ogp_site_url = "https://contextgem.dev/"
+ogp_image = "https://contextgem.dev/_static/contextgem_website_preview_banner.png"
+ogp_description = "ContextGem: Easier and faster way to build LLM extraction workflows through powerful abstractions"
+ogp_description_length = 200
+ogp_type = "website"
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
diff --git a/tests/cassettes/TestAll.test_usage_examples.yaml b/tests/cassettes/TestAll.test_usage_examples.yaml
diff --git a/tests/test_all.py b/tests/test_all.py

Original file line number	Diff line number	Diff line change
`@@ -17,7 +17,7 @@`
`17`	`17`	`#`
`18`	`18`
`19`	`19`	`"""`
`20`		`-ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions`
	`20`	`+ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions`
`21`	`21`	`"""`
`22`	`22`
`23`	`23`	`__version__ = "0.1.0"`
Original file line number	Diff line number	Diff line change
`@@ -139,7 +139,7 @@ def concatenate_docs(doc_paths: list[str], text_dir: str, output_file: str) -> N`
`139`	`139`	`"""`
`140`	`140`	`with open(output_file, "w", encoding="utf-8") as outfile:`
`141`	`141`	`outfile.write(`
`142`		`- "ContextGem - The easiest and fastest way to build LLM extraction workflows through powerful abstractions\n"`
	`142`	`+ "ContextGem - Easier and faster way to build LLM extraction workflows through powerful abstractions\n"`
`143`	`143`	`)`
`144`	`144`	`outfile.write("=" * 100 + "\n\n")`
`145`	`145`	`outfile.write("Copyright (c) 2025 Shcherbak AI AS\n")`