biblicus 0.15.0__tar.gz → 0.15.1__tar.gz

{biblicus-0.15.0/src/biblicus.egg-info → biblicus-0.15.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: biblicus
-Version: 0.15.0
+Version: 0.15.1
 Summary: Command line interface and Python library for corpus ingestion, retrieval, and evaluation.
 License: MIT
 Requires-Python: >=3.9
@@ -57,8 +57,15 @@ Dynamic: license-file
 ![Coverage][coverage-badge]
 ![Documentation][documentation-badge]
 
-Make your documents usable by your assistant, then decide later how you will search and retrieve them.
-
+<p>
+  <img
+    src="docs/_static/Biblicus-logo.png"
+    alt="Biblicus logo"
+    align="right"
+    width="216"
+  />
+  Make your documents usable by your assistant, then decide later how you will search and retrieve them.
+</p>
 If you are building an assistant in Python, you probably have material you want it to use: notes, documents, web pages, and reference files. A common approach is retrieval augmented generation, where a system retrieves relevant material and uses it as evidence when generating a response.
 
 The first practical problem is not retrieval. It is collection and care. You need a stable place to put raw items, you need a small amount of metadata so you can find them again, and you need a way to evolve your retrieval approach over time without rewriting ingestion.
@@ -538,7 +545,7 @@ Three backends are included.
 
 - `scan` is a minimal baseline that scans raw items directly.
 - `sqlite-full-text-search` is a practical baseline that builds a full text search index in SQLite.
-- `vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
+- `tf-vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
 
 For detailed documentation including configuration options, performance characteristics, and usage examples, see the [Backend Reference][backend-reference].
 

{biblicus-0.15.0 → biblicus-0.15.1}/README.md

@@ -4,8 +4,15 @@
 ![Coverage][coverage-badge]
 ![Documentation][documentation-badge]
 
-Make your documents usable by your assistant, then decide later how you will search and retrieve them.
-
+<p>
+  <img
+    src="docs/_static/Biblicus-logo.png"
+    alt="Biblicus logo"
+    align="right"
+    width="216"
+  />
+  Make your documents usable by your assistant, then decide later how you will search and retrieve them.
+</p>
 If you are building an assistant in Python, you probably have material you want it to use: notes, documents, web pages, and reference files. A common approach is retrieval augmented generation, where a system retrieves relevant material and uses it as evidence when generating a response.
 
 The first practical problem is not retrieval. It is collection and care. You need a stable place to put raw items, you need a small amount of metadata so you can find them again, and you need a way to evolve your retrieval approach over time without rewriting ingestion.
@@ -485,7 +492,7 @@ Three backends are included.
 
 - `scan` is a minimal baseline that scans raw items directly.
 - `sqlite-full-text-search` is a practical baseline that builds a full text search index in SQLite.
-- `vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
+- `tf-vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
 
 For detailed documentation including configuration options, performance characteristics, and usage examples, see the [Backend Reference][backend-reference].
 

{biblicus-0.15.0 → biblicus-0.15.1}/docs/ROADMAP.md

@@ -52,13 +52,13 @@ Lightweight analysis utilities summarize corpus themes and guide curation:
 - Topic modeling with BERTopic and optional LLM-assisted labeling.
 - Side-by-side analysis outputs stored under the corpus for reproducible comparison.
 
-## Next: sequence analysis (hidden Markov models)
+### Sequence analysis (Markov analysis)
 
 Goal: provide a sequence-oriented analysis backend for corpora where order matters (conversations, timelines, logs).
 
 Deliverables:
 
-- Hidden Markov modeling analysis for sequence-driven corpora.
+- Markov analysis for sequence-driven corpora (including hidden Markov models where appropriate).
 - A report format that explains state transitions and emissions with evidence.
 - Evaluation guidance for comparing HMM outputs across corpora or snapshots.
 
@@ -67,6 +67,36 @@ Acceptance checks:
 - HMM analysis is reproducible for the same corpus state and extraction run.
 - Reports are exportable and readable without custom tooling.
 
+### Text utilities
+
+Small, reusable building blocks for transforming text in ways that are hard to do reliably with one-shot generation.
+
+Deliverables:
+
+- Text extraction and slicing utilities that operate via a virtual file editing tool loop.
+- Optional higher-level utilities built on the same pattern (annotation, linking, redaction).
+- Documentation and runnable demos that show the mechanism and how to use each utility.
+
+Acceptance checks:
+
+- Utilities have end-to-end behavior specifications and are fully covered by tests.
+- Integration tests can be run against real model APIs when configured.
+
+## Next: Tactus integration
+
+Goal: make Biblicus usable from durable agent workflows without baking assistant logic into Biblicus itself.
+
+Deliverables:
+
+- A Model Context Protocol (MCP) toolset surface for Biblicus (ingest, query, stats, and evidence retrieval).
+- Clear dependency wiring for secrets and network access (in-sandbox vs brokered).
+- One reference procedure demonstrating retrieval-augmented generation built on Biblicus evidence outputs.
+
+Acceptance checks:
+
+- Tools expose evidence-first outputs with stable schemas.
+- Procedures remain in control of prompting and context budgeting policy.
+
 ## Later: alternate backends and hosting modes
 
 Goal: broaden the backend surface while keeping the core predictable.

{biblicus-0.15.0 → biblicus-0.15.1}/docs/index.rst

@@ -1,6 +1,12 @@
 Biblicus
 ========
 
+.. image:: _static/Biblicus-logo.png
+   :alt: Biblicus logo
+   :align: right
+   :width: 216
+   :class: docs-logo
+
 You have a folder full of files. Nobody knows what is in it. Someone wants answers anyway.
 
 Biblicus is a Python toolkit that turns unstructured data into something you can manage, search,
@@ -146,6 +152,8 @@ cover baseline retrieval, hybrid strategies, and how to evaluate retrieval quali
    RETRIEVAL
    RETRIEVAL_QUALITY
    RETRIEVAL_EVALUATION
+   EMBEDDING_RETRIEVAL
+   CHUNKING
 
 Analysis and Modeling
 ---------------------
@@ -210,4 +218,5 @@ implementation details or when you want a catalog of features.
    ARCHITECTURE
    ARCHITECTURE_DETAIL
    PR_FAQ_TEXT_ANNOTATE
+   PR_FAQ_EMBEDDING_RETRIEVAL
    api

{biblicus-0.15.0 → biblicus-0.15.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biblicus"
-version = "0.15.0"
+version = "0.15.1"
 description = "Command line interface and Python library for corpus ingestion, retrieval, and evaluation."
 readme = "README.md"
 requires-python = ">=3.9"

{biblicus-0.15.0 → biblicus-0.15.1}/src/biblicus/__init__.py

@@ -27,4 +27,4 @@ __all__ = [
     "RetrievalRun",
 ]
 
-__version__ = "0.15.0"
+__version__ = "0.15.1"

{biblicus-0.15.0 → biblicus-0.15.1/src/biblicus.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: biblicus
-Version: 0.15.0
+Version: 0.15.1
 Summary: Command line interface and Python library for corpus ingestion, retrieval, and evaluation.
 License: MIT
 Requires-Python: >=3.9
@@ -57,8 +57,15 @@ Dynamic: license-file
 ![Coverage][coverage-badge]
 ![Documentation][documentation-badge]
 
-Make your documents usable by your assistant, then decide later how you will search and retrieve them.
-
+<p>
+  <img
+    src="docs/_static/Biblicus-logo.png"
+    alt="Biblicus logo"
+    align="right"
+    width="216"
+  />
+  Make your documents usable by your assistant, then decide later how you will search and retrieve them.
+</p>
 If you are building an assistant in Python, you probably have material you want it to use: notes, documents, web pages, and reference files. A common approach is retrieval augmented generation, where a system retrieves relevant material and uses it as evidence when generating a response.
 
 The first practical problem is not retrieval. It is collection and care. You need a stable place to put raw items, you need a small amount of metadata so you can find them again, and you need a way to evolve your retrieval approach over time without rewriting ingestion.
@@ -538,7 +545,7 @@ Three backends are included.
 
 - `scan` is a minimal baseline that scans raw items directly.
 - `sqlite-full-text-search` is a practical baseline that builds a full text search index in SQLite.
-- `vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
+- `tf-vector` is a deterministic term-frequency vector baseline with cosine similarity scoring.
 
 For detailed documentation including configuration options, performance characteristics, and usage examples, see the [Backend Reference][backend-reference].