deepsearch-glm
Graph Language Models
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Pretrained models are downloaded on first use; pywin32 is a runtime dependency on Windows systems.
- 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 · maintenance · safety
MIT (permissive) — 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.
last release 2024-12-09 (613 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 92,161 downloads/mo, #13,472 on PyPI
Alternatives
Verify before relying
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.")- 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.
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 on this page. Verify before relying on it.
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
deepsearch-glm on PyPI
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.
Pretrained models are downloaded on first use; pywin32 is a runtime dependency on Windows systems.
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.")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 the current Python release <4.0,>=3.9 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagepywin32 |
| Maintenance | Dormant 613 days since the last release |
| First released | |
| Downloads | 92,161 / month, #13,472 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9 |
Evidence: deepsearch_glm-1.0.0-cp310-cp310-macosx_13_0_x86_64.whl; deepsearch_glm-1.0.0-cp310-cp310-macosx_14_0_arm64.whl; deepsearch_glm-1.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; deepsearch_glm-1.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; deepsearch_glm-1.0.0-cp310-cp310-win_amd64.whl; deepsearch_glm-1.0.0-cp311-cp311-macosx_13_0_x86_64.whl; deepsearch_glm-1.0.0-cp311-cp311-macosx_14_0_arm64.whl; deepsearch_glm-1.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; deepsearch_glm-1.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; deepsearch_glm-1.0.0-cp311-cp311-win_amd64.whl; deepsearch_glm-1.0.0-cp312-cp312-macosx_13_0_x86_64.whl; deepsearch_glm-1.0.0-cp312-cp312-macosx_14_0_arm64.whl; deepsearch_glm-1.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; deepsearch_glm-1.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; deepsearch_glm-1.0.0-cp312-cp312-win_amd64.whl; deepsearch_glm-1.0.0-cp313-cp313-macosx_13_0_x86_64.whl; deepsearch_glm-1.0.0-cp313-cp313-macosx_14_0_arm64.whl; deepsearch_glm-1.0.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; deepsearch_glm-1.0.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; deepsearch_glm-1.0.0-cp313-cp313-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “document relation extraction”
- deepsearch-glmExtracts entities, relations, and linguistic structures from text and…
- gliner2GLiNER2 extracts entities, classifies text, parses structured data,…
- glinerGLiNER is a lightweight framework for named entity recognition that…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also langchain-graph-retriever · textacy · rake-nltk · graphiti-core · nltk · graphrag · minisbd · langextract · recognizers-text-date-time · harvesters