citegraph 0.2.0__tar.gz → 0.2.1__tar.gz

{citegraph-0.2.0 → citegraph-0.2.1}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.2.1 — 2026-11-01
+
+- Describe the library as building and analyzing citation and author networks
+  with LLM-assisted extraction.
+- Make the current Gemini-only extraction support explicit in the README and
+  user guide, with additional LLM providers planned. This release changes
+  documentation and package metadata; it does not add another LLM provider.
+
 ## 0.2.0 — 2026-11-01
 
 Public research beta. This release replaces the earlier papers/references model

{citegraph-0.2.0 → citegraph-0.2.1}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.5
 Name: citegraph
-Version: 0.2.0
-Summary: Build a deduplicated citation graph from a folder of academic PDFs using Gemini.
+Version: 0.2.1
+Summary: Build and analyze citation and author networks from academic PDFs with LLM-assisted extraction.
 Project-URL: Homepage, https://github.com/yabramuvdi/citegraph
 Project-URL: Repository, https://github.com/yabramuvdi/citegraph
 Project-URL: Issues, https://github.com/yabramuvdi/citegraph/issues
@@ -56,19 +56,23 @@ Description-Content-Type: text/markdown
 
 # citegraph
 
-Turn a folder of academic PDFs into a citation graph you can query, and then
-ask who the literature reads together.
+Build and analyze citation and author networks from academic PDFs with
+LLM-assisted extraction.
 
 `citegraph` is for a researcher who has a corpus of papers — a literature
 review, a field's working papers, a lab's output — and wants to study it
 bibliometrically without hand-coding bibliographies. It converts each PDF to
-text locally, has a large language model extract the paper's metadata and its
+text locally, uses Google Gemini to extract the paper's metadata and its
 full reference list, resolves every bibliographic record into one canonical
 **work**, and clusters author names across the corpus into canonical
 **authors**. On top of those tables it builds the author co-citation network
 and offers a test for whether a documented relationship between two people
 shows up in how the field cites them.
 
+**Current LLM support:** metadata and reference extraction use Google Gemini.
+Support for additional LLM providers is planned. PDF conversion, graph queries,
+and network analysis run locally.
+
 Everything lands as plain CSVs in one output directory, every stage is
 checkpointed, and nothing is sent anywhere until you have seen a cost estimate.
 
@@ -855,7 +859,7 @@ for the full checklist. To cut a release:
 
 1. Update the version and changelog as described in [docs/RELEASE.md](docs/RELEASE.md).
 2. Commit and push to `main`.
-3. `git tag v0.2.0 && git push origin v0.2.0` — the workflow then builds an
+3. `git tag v0.2.1 && git push origin v0.2.1` — the workflow then builds an
    sdist + wheel and publishes them to PyPI.
 
 To dry-run against TestPyPI first, build locally and upload manually:

{citegraph-0.2.0 → citegraph-0.2.1}/README.md

@@ -1,18 +1,22 @@
 # citegraph
 
-Turn a folder of academic PDFs into a citation graph you can query, and then
-ask who the literature reads together.
+Build and analyze citation and author networks from academic PDFs with
+LLM-assisted extraction.
 
 `citegraph` is for a researcher who has a corpus of papers — a literature
 review, a field's working papers, a lab's output — and wants to study it
 bibliometrically without hand-coding bibliographies. It converts each PDF to
-text locally, has a large language model extract the paper's metadata and its
+text locally, uses Google Gemini to extract the paper's metadata and its
 full reference list, resolves every bibliographic record into one canonical
 **work**, and clusters author names across the corpus into canonical
 **authors**. On top of those tables it builds the author co-citation network
 and offers a test for whether a documented relationship between two people
 shows up in how the field cites them.
 
+**Current LLM support:** metadata and reference extraction use Google Gemini.
+Support for additional LLM providers is planned. PDF conversion, graph queries,
+and network analysis run locally.
+
 Everything lands as plain CSVs in one output directory, every stage is
 checkpointed, and nothing is sent anywhere until you have seen a cost estimate.
 
@@ -799,7 +803,7 @@ for the full checklist. To cut a release:
 
 1. Update the version and changelog as described in [docs/RELEASE.md](docs/RELEASE.md).
 2. Commit and push to `main`.
-3. `git tag v0.2.0 && git push origin v0.2.0` — the workflow then builds an
+3. `git tag v0.2.1 && git push origin v0.2.1` — the workflow then builds an
    sdist + wheel and publishes them to PyPI.
 
 To dry-run against TestPyPI first, build locally and upload manually:

{citegraph-0.2.0 → citegraph-0.2.1}/docs/RELEASE.md

@@ -50,8 +50,8 @@ in the repository.
 Create and push a version tag:
 
 ```bash
-git tag v0.2.0
-git push origin v0.2.0
+git tag v0.2.1
+git push origin v0.2.1
 ```
 
 The `Publish` workflow builds the package, checks metadata, and publishes to

{citegraph-0.2.0 → citegraph-0.2.1}/docs/USER_GUIDE.md

@@ -4,6 +4,10 @@ This guide walks a researcher from a folder of PDFs to a checked, queryable
 citation graph. It also explains which decisions deserve human review and what
 data leaves the computer during a run.
 
+Metadata and reference extraction currently support Google Gemini only.
+Support for additional LLM providers is planned. PDF conversion, graph queries,
+and network analysis run locally.
+
 ## 1. Install
 
 `citegraph` requires Python 3.11 or newer. Upgrade `pip` before installing the

{citegraph-0.2.0 → citegraph-0.2.1}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "hatchling.build"
 
 [project]
 name = "citegraph"
-version = "0.2.0"
-description = "Build a deduplicated citation graph from a folder of academic PDFs using Gemini."
+version = "0.2.1"
+description = "Build and analyze citation and author networks from academic PDFs with LLM-assisted extraction."
 readme = "README.md"
 requires-python = ">=3.11"
 license = { text = "MIT" }

{citegraph-0.2.0 → citegraph-0.2.1}/src/citegraph/__init__.py

@@ -1,4 +1,6 @@
-"""citegraph: build a deduplicated citation graph from a folder of PDFs.
+"""Build and analyze citation and author networks from academic PDFs.
+
+LLM-assisted metadata and reference extraction currently uses Google Gemini.
 
 See :class:`citegraph.Pipeline` for the high-level entry point::
 
@@ -41,4 +43,4 @@ __all__ = [
     "parse_author",
 ]
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"

{citegraph-0.2.0 → citegraph-0.2.1}/src/citegraph/reports.py

@@ -23,7 +23,7 @@ def _package_version() -> str:
     try:
         return version("citegraph")
     except PackageNotFoundError:
-        return "0.2.0"
+        return "0.2.1"
 
 
 def write_artifact_manifest(