---
id: deepsearch-glm
version: "1.0.0"
license: MIT
license_treatment: permissive
maintenance: dormant
---

# deepsearch-glm — Graph Language Models

License: permissive · Maintenance: dormant · Downloads: 92.2K/mo

## What it is and what it does

deepsearch-glm is a Python library for extracting structured linguistic information—entities, relations, terms, and sentences—from unstructured text and documents using pretrained neural language models. It processes raw text or JSON-converted documents to identify and annotate linguistic elements like named entities, expressions, and numeric values, then optionally constructs knowledge graphs from these extracted components across document collections.

The package provides two main workflows: direct NLP analysis on text snippets or full documents (returning pandas DataFrames with entity types, confidence scores, and character offsets), and graph construction from entity and relation annotations across multiple documents. It includes utilities for working with Deep Search document conversion and offers both Python bindings and C++ executables for batch processing.

Use it for:

- Extract named entities, terms, and linguistic structures from research papers or technical documents for downstream analysis.
- Build knowledge graphs from patent or scientific literature collections to map relationships between concepts and entities.
- Analyze document collections to identify and annotate domain-specific terminology and expressions at scale.
- Convert unstructured text into structured, queryable linguistic annotations for information retrieval or semantic search.
- Enrich PDF documents with NLP metadata (entities, relations, confidence scores) for indexing or downstream ML pipelines.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Extracts entities, relations, and linguistic structures from text and documents using pretrained NLP models, then constructs knowledge graphs from the extracted information.

Yes, if you need entity and relation extraction from documents and are comfortable with a dormant package. The library offers broad Python version support and prebuilt wheels for easy installation, but the 613-day gap since the last release and lack of recent maintenance signals suggest limited ongoing support. Install only if the core NLP and graph-building features match your needs and you can tolerate potential staleness.

## Install

pip install deepsearch-glm
uv add deepsearch-glm
poetry add deepsearch-glm

## Installing deepsearch-glm

Before you install: Medium install friction due to prebuilt wheels for Python 3.9–3.13 across macOS, Linux, and Windows, but the package is dormant (613 days since last release) with no recent maintenance signals.

License in practice: MIT license permits commercial and private use with minimal restrictions; you may use, modify, and distribute the package freely provided you include the original license notice.

Quickstart:

pip install deepsearch-glm

from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models
from deepsearch_glm.nlp_utils import init_nlp_model

load_pretrained_nlp_models(force=False, verbose=False)
mdl = init_nlp_model()
result = mdl.apply_on_text("France is a country in Western Europe.")

Pretrained models are downloaded on first use; pywin32 is a runtime dependency on Windows systems.

Verify before relying:

- Whether the dormant status (613 days since release) indicates active maintenance or abandonment.
- Whether pretrained model downloads work reliably or require external configuration.
- Performance characteristics and supported document formats beyond the PDF examples shown.
- Whether the deepsearch-toolkit optional dependency is required for core NLP functionality or only for advanced features.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: medium
- Maintenance: dormant
- Downloads: 92.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

entity extraction from text, NLP named entity recognition, knowledge graph construction, document relation extraction, graph language models, semantic parsing documents, linguistic structure analysis, nlp-extraction, knowledge-graph, entity-recognition

[View on SkillFed](https://skillfed.io/packages/deepsearch-glm) · [View on PyPI](https://pypi.org/project/deepsearch-glm/)