biblicus 0.6.0__py3-none-any.whl

biblicus-0.6.0.dist-info/METADATA

@@ -0,0 +1,533 @@
+Metadata-Version: 2.4
+Name: biblicus
+Version: 0.6.0
+Summary: Command line interface and Python library for corpus ingestion, retrieval, and evaluation.
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: pypdf>=4.0
+Provides-Extra: dev
+Requires-Dist: behave>=1.2.6; extra == "dev"
+Requires-Dist: coverage[toml]>=7.0; extra == "dev"
+Requires-Dist: sphinx>=7.0; extra == "dev"
+Requires-Dist: myst-parser>=2.0; extra == "dev"
+Requires-Dist: sphinx_rtd_theme>=2.0; extra == "dev"
+Requires-Dist: ruff>=0.4.0; extra == "dev"
+Requires-Dist: black>=24.0; extra == "dev"
+Requires-Dist: python-semantic-release>=9.0.0; extra == "dev"
+Provides-Extra: openai
+Requires-Dist: openai>=1.0; extra == "openai"
+Provides-Extra: unstructured
+Requires-Dist: unstructured>=0.12.0; extra == "unstructured"
+Requires-Dist: python-docx>=1.1.0; extra == "unstructured"
+Provides-Extra: ocr
+Requires-Dist: rapidocr-onnxruntime>=1.3.0; extra == "ocr"
+Dynamic: license-file
+
+# Biblicus
+
+![Continuous integration][continuous-integration-badge]
+![Coverage][coverage-badge]
+![Documentation][documentation-badge]
+
+Make your documents usable by your assistant, then decide later how you will search and retrieve them.
+
+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.
+
+This library gives you a corpus, which is a normal folder on disk. It stores each ingested item as a file, with optional metadata stored next to it. You can open and inspect the raw files directly. Any derived catalog or index can be rebuilt from the raw corpus.
+
+It can be used alongside LangGraph, Tactus, Pydantic AI, any agent framework, or your own setup. Use it from Python or from the command line interface.
+
+See [retrieval augmented generation overview] for a short introduction to the idea.
+
+## Start with a knowledge base
+
+If you just want to hand a folder to your assistant and move on, use the high-level knowledge base interface. The folder can be nothing more than a handful of plain text files. You are not choosing a retrieval strategy yet. You are just collecting.
+
+This example assumes a folder called `notes/` with a few `.txt` files. The knowledge base handles sensible defaults and still gives you a clear context pack for your model call.
+
+```python
+from biblicus.knowledge_base import KnowledgeBase
+
+
+kb = KnowledgeBase.from_folder("notes")
+result = kb.query("Primary button style preference")
+context_pack = kb.context_pack(result, max_tokens=800)
+
+print(context_pack.text)
+```
+
+If you want to run a real, executable version of this story, use `scripts/readme_end_to_end_demo.py` from a fresh clone.
+
+This simplified sequence diagram shows the same idea at a high level.
+
+```mermaid
+%%{init: {"theme": "base", "themeVariables": {"primaryColor": "#f3e5f5", "primaryTextColor": "#111111", "primaryBorderColor": "#8e24aa", "lineColor": "#90a4ae", "secondaryColor": "#eceff1", "tertiaryColor": "#ffffff", "noteBkgColor": "#ffffff", "noteTextColor": "#111111", "actorBkg": "#f3e5f5", "actorBorder": "#8e24aa", "actorTextColor": "#111111"}}}%%
+sequenceDiagram
+  participant App as Your assistant code
+  participant KB as Knowledge base
+  participant LLM as Large language model
+
+  App->>KB: query
+  KB-->>App: evidence and context
+  App->>LLM: context plus prompt
+  LLM-->>App: response draft
+```
+
+## A simple mental model
+
+Think in three stages.
+
+- Ingest puts raw items into a corpus. This is file first and human inspectable.
+- Extract turns items into usable text. This is where you would do text extraction from Portable Document Format files, optical character recognition for images, or speech to text for audio. If an item is already text, extraction can simply read it. Extraction outputs are derived artifacts, not edits to the raw files.
+- Retrieve searches extracted text and returns evidence. Evidence is structured so you can turn it into context for your model call in whatever way your project prefers.
+
+If you learn a few project words, the rest of the system becomes predictable.
+
+- Corpus is the folder that holds raw items and their metadata.
+- Item is the raw bytes plus optional metadata and source information.
+- Catalog is the rebuildable index of the corpus.
+- Extraction run is a recorded extraction build that produces text artifacts.
+- Backend is a pluggable retrieval implementation.
+- Run is a recorded retrieval build for a corpus.
+- Evidence is what retrieval returns, with identifiers and source information.
+
+## Where it fits in an assistant
+
+Biblicus does not answer user questions. It is not a language model. It helps your assistant answer them by retrieving relevant material and returning it as structured evidence. Your code decides how to turn evidence into a context pack for the model call, which is then passed to a model you choose.
+
+In a coding assistant, retrieval is often triggered by what the user is doing right now. For example: you are about to propose a user interface change, so you retrieve the user's stated preferences, then you include that as context for the model call.
+
+This diagram shows two sequential Biblicus calls. They are shown separately to make the boundaries explicit: retrieval returns evidence, and context pack building consumes evidence.
+
+```mermaid
+%%{init: {"theme": "base", "themeVariables": {"primaryColor": "#f3e5f5", "primaryTextColor": "#111111", "primaryBorderColor": "#8e24aa", "lineColor": "#90a4ae", "secondaryColor": "#eceff1", "tertiaryColor": "#ffffff", "noteBkgColor": "#ffffff", "noteTextColor": "#111111", "actorBkg": "#f3e5f5", "actorBorder": "#8e24aa", "actorTextColor": "#111111"}}}%%
+sequenceDiagram
+  participant User
+  participant App as Your assistant code
+  participant Bib as Biblicus
+  participant LLM as Large language model
+
+  User->>App: request
+  App->>Bib: query retrieval
+  Bib-->>App: retrieval result evidence JSON
+  App->>Bib: build context pack from evidence
+  Bib-->>App: context pack text
+  App->>LLM: context pack plus prompt
+  LLM-->>App: response draft
+  App-->>User: response
+```
+
+## Practical value
+
+- You can ingest raw material once, then try many retrieval approaches over time.
+- You can keep raw files readable and portable, without locking your data inside a database.
+- You can evaluate retrieval runs against shared datasets and compare backends using the same corpus.
+
+## Typical flow
+
+- Initialize a corpus folder.
+- Ingest items from file paths, web addresses, or text input.
+- Crawl a website section into corpus items when you want a repeatable “import from the web” workflow.
+- Run extraction when you want derived text artifacts from non-text sources.
+- Reindex to refresh the catalog after edits.
+- Build a retrieval run with a backend.
+- Query the run to collect evidence and evaluate it with datasets.
+
+## Install
+
+This repository is a working Python package. Install it into a virtual environment from the repository root.
+
+```
+python3 -m pip install -e .
+```
+
+After the first release, you can install it from Python Package Index.
+
+```
+python3 -m pip install biblicus
+```
+
+### Optional extras
+
+Some extractors are optional so the base install stays small.
+
+- Optical character recognition for images: `python3 -m pip install "biblicus[ocr]"`
+- Speech to text transcription: `python3 -m pip install "biblicus[openai]"` (requires an OpenAI API key in `~/.biblicus/config.yml` or `./.biblicus/config.yml`)
+- Broad document parsing fallback: `python3 -m pip install "biblicus[unstructured]"`
+
+## Quick start
+
+```
+mkdir -p notes
+echo "A small file note" > notes/example.txt
+
+biblicus init corpora/example
+biblicus ingest --corpus corpora/example notes/example.txt
+echo "A short note" | biblicus ingest --corpus corpora/example --stdin --title "First note"
+biblicus list --corpus corpora/example
+biblicus extract build --corpus corpora/example --step pass-through-text --step metadata-text
+biblicus extract list --corpus corpora/example
+biblicus build --corpus corpora/example --backend scan
+biblicus query --corpus corpora/example --query "note"
+```
+
+If you want to turn a website section into corpus items, crawl a root web address while restricting the crawl to an allowed prefix:
+
+```
+biblicus crawl --corpus corpora/example \\
+  --root-url https://example.com/docs/index.html \\
+  --allowed-prefix https://example.com/docs/ \\
+  --max-items 50 \\
+  --tag crawled
+```
+
+## End-to-end example: lower-level control
+
+The command-line interface returns JavaScript Object Notation by default. This makes it easy to use Biblicus in scripts and to treat retrieval as a deterministic, testable step.
+
+This version shows the lower-level pieces explicitly. You are building the corpus, controlling each memory string, choosing the backend, and shaping the context pack yourself.
+
+```python
+from biblicus.backends import get_backend
+from biblicus.context import ContextPackPolicy, TokenBudget, build_context_pack, fit_context_pack_to_token_budget
+from biblicus.corpus import Corpus
+from biblicus.models import QueryBudget
+
+
+corpus = Corpus.init("corpora/story")
+
+notes = [
+    ("User name", "The user's name is Tactus Maximus."),
+    ("Button style preference", "Primary button style preference: the user's favorite color is magenta."),
+    ("Style preference", "The user prefers concise answers."),
+    ("Language preference", "The user dislikes idioms and abbreviations."),
+    ("Engineering preference", "The user likes code that is over-documented and behavior-driven."),
+]
+for note_title, note_text in notes:
+    corpus.ingest_note(note_text, title=note_title, tags=["memory"])
+
+backend = get_backend("scan")
+run = backend.build_run(corpus, recipe_name="Story demo", config={})
+budget = QueryBudget(max_total_items=5, max_total_characters=2000, max_items_per_source=None)
+result = backend.query(
+    corpus,
+    run=run,
+    query_text="Primary button style preference",
+    budget=budget,
+)
+
+policy = ContextPackPolicy(join_with="\n\n")
+context_pack = build_context_pack(result, policy=policy)
+context_pack = fit_context_pack_to_token_budget(
+    context_pack,
+    policy=policy,
+    token_budget=TokenBudget(max_tokens=60),
+)
+print(context_pack.text)
+```
+
+If you want a runnable version of this story, use the script at `scripts/readme_end_to_end_demo.py`.
+
+If you prefer the command-line interface, here is the same flow in compressed form:
+
+```
+biblicus init corpora/story
+biblicus ingest --corpus corpora/story --stdin --title "User name" --tag memory <<< "The user's name is Tactus Maximus."
+biblicus ingest --corpus corpora/story --stdin --title "Button style preference" --tag memory <<< "Primary button style preference: the user's favorite color is magenta."
+biblicus ingest --corpus corpora/story --stdin --title "Style preference" --tag memory <<< "The user prefers concise answers."
+biblicus ingest --corpus corpora/story --stdin --title "Language preference" --tag memory <<< "The user dislikes idioms and abbreviations."
+biblicus ingest --corpus corpora/story --stdin --title "Engineering preference" --tag memory <<< "The user likes code that is over-documented and behavior-driven."
+biblicus build --corpus corpora/story --backend scan
+biblicus query --corpus corpora/story --query "Primary button style preference"
+```
+
+Example output:
+
+```json
+{
+  "query_text": "Primary button style preference",
+  "budget": {
+    "max_total_items": 5,
+    "max_total_characters": 2000,
+    "max_items_per_source": null
+  },
+  "run_id": "RUN_ID",
+  "recipe_id": "RECIPE_ID",
+  "backend_id": "scan",
+  "generated_at": "2026-01-29T00:00:00.000000Z",
+  "evidence": [
+    {
+      "item_id": "ITEM_ID",
+      "source_uri": "text",
+      "media_type": "text/markdown",
+      "score": 1.0,
+      "rank": 1,
+      "text": "Primary button style preference: the user's favorite color is magenta.",
+      "content_ref": null,
+      "span_start": null,
+      "span_end": null,
+      "stage": "scan",
+      "recipe_id": "RECIPE_ID",
+      "run_id": "RUN_ID",
+      "hash": null
+    }
+  ],
+  "stats": {}
+}
+```
+
+Evidence is the output contract. Your code decides how to convert evidence into assistant context.
+
+### Turn evidence into a context pack
+
+A context pack is a readable text block you send to a model. There is no single correct format. Treat it as a policy surface you can iterate on.
+
+Here is a minimal example that builds a context pack from evidence:
+
+```python
+from biblicus.context import ContextPackPolicy, build_context_pack
+
+
+policy = ContextPackPolicy(
+    join_with="\n\n",
+)
+context_pack = build_context_pack(result, policy=policy)
+print(context_pack.text)
+```
+
+Example context pack output:
+
+```text
+Primary button style preference: the user's favorite color is magenta.
+```
+
+You can also build a context pack from the command-line interface by piping the retrieval result:
+
+```
+biblicus query --corpus corpora/story --query "Primary button style preference" \\
+  | biblicus context-pack build
+```
+
+Most production systems also apply a budget when building context. If you want a precise token budget, the budgeting logic needs a specific tokenizer and should be treated as its own stage.
+
+## Pipeline diagram
+
+This diagram shows how a corpus becomes evidence for your assistant. Your code decides how to turn evidence into context and how to call a model.
+
+```mermaid
+%%{init: {"theme": "base", "themeVariables": {"primaryColor": "#f3e5f5", "primaryTextColor": "#111111", "primaryBorderColor": "#8e24aa", "lineColor": "#90a4ae", "secondaryColor": "#eceff1", "tertiaryColor": "#ffffff"}, "flowchart": {"useMaxWidth": true, "nodeSpacing": 18, "rankSpacing": 22}}}%%
+flowchart TB
+  subgraph Legend[Legend]
+    direction LR
+    LegendArtifact[Stored artifact or evidence]
+    LegendStep[Step]
+    LegendArtifact --- LegendStep
+  end
+
+  subgraph Main[" "]
+    direction TB
+
+    subgraph Pipeline[" "]
+      direction TB
+
+      subgraph RowStable[Stable core]
+        direction TB
+        Source[Source items] --> Ingest[Ingest] --> Raw[Raw item files] --> Catalog[Catalog file]
+      end
+
+      subgraph RowExtraction[Pluggable: extraction pipeline]
+        direction TB
+        Catalog --> Extract[Extract pipeline] --> ExtractedText[Extracted text artifacts] --> ExtractionRun[Extraction run manifest]
+      end
+
+      subgraph RowRetrieval[Pluggable: retrieval backend]
+        direction TB
+        ExtractionRun --> Build[Build run] --> BackendIndex[Backend index] --> Run[Run manifest] --> Retrieve[Retrieve] --> Rerank[Rerank optional] --> Filter[Filter optional] --> Evidence[Evidence]
+      end
+
+      subgraph RowContext[Context]
+        direction TB
+        Evidence --> ContextPack[Context pack] --> FitTokens[Fit tokens optional] --> Context[Assistant context]
+      end
+
+      subgraph RowYourCode[Your code]
+        direction TB
+        Context --> Model[Large language model call] --> Answer[Answer]
+      end
+    end
+
+    style RowStable fill:#ffffff,stroke:#8e24aa,stroke-width:2px,color:#111111
+    style RowExtraction fill:#ffffff,stroke:#5e35b1,stroke-dasharray:6 3,stroke-width:2px,color:#111111
+    style RowRetrieval fill:#ffffff,stroke:#1e88e5,stroke-dasharray:6 3,stroke-width:2px,color:#111111
+    style RowContext fill:#ffffff,stroke:#7b1fa2,stroke-width:2px,color:#111111
+    style RowYourCode fill:#ffffff,stroke:#d81b60,stroke-width:2px,color:#111111
+
+    style Raw fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Catalog fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style ExtractedText fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style ExtractionRun fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style BackendIndex fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Run fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Evidence fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style ContextPack fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Context fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Answer fill:#f3e5f5,stroke:#8e24aa,color:#111111
+    style Source fill:#f3e5f5,stroke:#8e24aa,color:#111111
+
+    style Ingest fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Extract fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Build fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Retrieve fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Rerank fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Filter fill:#eceff1,stroke:#90a4ae,color:#111111
+    style FitTokens fill:#eceff1,stroke:#90a4ae,color:#111111
+    style Model fill:#eceff1,stroke:#90a4ae,color:#111111
+  end
+
+  style Legend fill:#ffffff,stroke:#ffffff,color:#111111
+  style Main fill:#ffffff,stroke:#ffffff,color:#111111
+  style Pipeline fill:#ffffff,stroke:#ffffff,color:#111111
+  style LegendArtifact fill:#f3e5f5,stroke:#8e24aa,color:#111111
+  style LegendStep fill:#eceff1,stroke:#90a4ae,color:#111111
+```
+
+## Python usage
+
+From Python, the same flow is available through the Corpus class and backend interfaces. The public surface area is small on purpose.
+
+- Create a corpus with `Corpus.init` or open one with `Corpus.open`.
+- Ingest notes with `Corpus.ingest_note`.
+- Ingest files or web addresses with `Corpus.ingest_source`.
+- List items with `Corpus.list_items`.
+- Build a retrieval run with `get_backend` and `backend.build_run`.
+- Query a run with `backend.query`.
+- Evaluate with `evaluate_run`.
+
+## Learn more
+
+Full documentation is published on GitHub Pages: https://anthusai.github.io/Biblicus/
+
+The documents below follow the pipeline from raw items to model context:
+
+- [Corpus][corpus]
+- [Text extraction][text-extraction]
+- [Knowledge base][knowledge-base]
+- [Backends][backends]
+- [Context packs][context-packs]
+- [Testing and evaluation][testing]
+
+Reference:
+
+- [Demos][demos]
+- [User configuration][user-configuration]
+
+Design and implementation map:
+
+- [Feature index][feature-index]
+- [Roadmap][roadmap]
+- [Architecture][architecture]
+
+## Metadata and catalog
+
+Raw items are stored as files in the corpus raw directory. Metadata can live in a Markdown front matter block or a sidecar file with the suffix `.biblicus.yml`. The catalog lives in `.biblicus/catalog.json` and can be rebuilt at any time with `biblicus reindex`.
+
+## Corpus layout
+
+```
+corpus/
+  raw/
+    item.bin
+    item.bin.biblicus.yml
+  .biblicus/
+    config.json
+    catalog.json
+    runs/
+      extraction/
+        pipeline/
+          <run id>/
+            manifest.json
+            text/
+              <item id>.txt
+      retrieval/
+        <backend id>/
+          <run id>/
+            manifest.json
+```
+
+## Retrieval backends
+
+Two 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.
+
+## Integration corpus and evaluation dataset
+
+Use `scripts/download_wikipedia.py` to download a small integration corpus from Wikipedia when running tests or demos. The repository does not include that content.
+
+The dataset file `datasets/wikipedia_mini.json` provides a small evaluation set that matches the integration corpus.
+
+Use `scripts/download_pdf_samples.py` to download a small Portable Document Format integration corpus when running tests or demos. The repository does not include that content.
+
+## Tests and coverage
+
+```
+python3 scripts/test.py
+```
+
+To include integration scenarios that download public test data at runtime, run this command.
+
+```
+python3 scripts/test.py --integration
+```
+
+## Releases
+
+Releases are automated from the main branch using semantic versioning and conventional commit messages.
+
+The release pipeline publishes a GitHub release and uploads the package to Python Package Index when continuous integration succeeds.
+
+Publishing uses a Python Package Index token stored in the GitHub secret named PYPI_TOKEN.
+
+## Documentation
+
+Reference documentation is generated from Sphinx style docstrings.
+
+Install development dependencies:
+
+```
+python3 -m pip install -e ".[dev]"
+```
+
+Build the documentation:
+
+```
+python3 -m sphinx -b html docs docs/_build/html
+```
+
+## License
+
+License terms are in `LICENSE`.
+
+[retrieval augmented generation overview]: https://en.wikipedia.org/wiki/Retrieval-augmented_generation
+[architecture]: docs/ARCHITECTURE.md
+[roadmap]: docs/ROADMAP.md
+[feature-index]: docs/FEATURE_INDEX.md
+[corpus]: docs/CORPUS.md
+[knowledge-base]: docs/KNOWLEDGE_BASE.md
+[text-extraction]: docs/EXTRACTION.md
+[user-configuration]: docs/USER_CONFIGURATION.md
+[backends]: docs/BACKENDS.md
+[context-packs]: docs/CONTEXT_PACK.md
+[demos]: docs/DEMOS.md
+[testing]: docs/TESTING.md
+
+[continuous-integration-badge]: https://github.com/AnthusAI/Biblicus/actions/workflows/ci.yml/badge.svg?branch=main
+[coverage-badge]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/AnthusAI/Biblicus/main/coverage_badge.json
+[documentation-badge]: https://img.shields.io/badge/docs-GitHub%20Pages-blue

biblicus-0.6.0.dist-info/RECORD

@@ -0,0 +1,48 @@
+biblicus/__init__.py,sha256=jxBNIMVKudpRsbzdiE5CmU6nIjgnNhCRq0OZLSwt_kM,495
+biblicus/__main__.py,sha256=ipfkUoTlocVnrQDM69C7TeBqQxmHVeiWMRaT3G9rtnk,117
+biblicus/cli.py,sha256=hBau464XNdSGdWeOCE2Q7dm0P8I4sR0W-NgVT0wPmh4,27724
+biblicus/constants.py,sha256=R6fZDoLVMCwgKvTaxEx7G0CstwHGaUTlW9MsmNLDZ44,269
+biblicus/context.py,sha256=qnT9CH7_ldoPcg-rxnUOtRhheOmpDAbF8uqhf8OdjC4,5832
+biblicus/corpus.py,sha256=gF1RNl6fdz7wplzpHEIkEBkhYxHgKTKguBR_kD9IgUw,54109
+biblicus/crawl.py,sha256=n8rXBMnziBK9vtKQQCXYOpBzqsPCswj2PzVJUb370KY,6250
+biblicus/errors.py,sha256=uMajd5DvgnJ_-jq5sbeom1GV8DPUc-kojBaECFi6CsY,467
+biblicus/evaluation.py,sha256=5xWpb-8f49Osh9aHzo1ab3AXOmls3Imc5rdnEC0pN-8,8143
+biblicus/evidence_processing.py,sha256=EMv1AkV_Eufk-poBz9nRR1dZgC-QewvI-NrULBUGVGA,6074
+biblicus/extraction.py,sha256=VEjBjIpaBboftGgEcpDj7z7um41e5uDZpP_7acQg7fw,19448
+biblicus/frontmatter.py,sha256=JOGjIDzbbOkebQw2RzA-3WDVMAMtJta2INjS4e7-LMg,2463
+biblicus/hook_logging.py,sha256=IMvde-JhVWrx9tNz3eDJ1CY_rr5Sj7DZ2YNomYCZbz0,5366
+biblicus/hook_manager.py,sha256=ZCAkE5wLvn4lnQz8jho_o0HGEC9KdQd9qitkAEUQRcw,6997
+biblicus/hooks.py,sha256=OHQOmOi7rUcQqYWVeod4oPe8nVLepD7F_SlN7O_-BsE,7863
+biblicus/ignore.py,sha256=fyjt34E6tWNNrm1FseOhgH2MgryyVBQVzxhKL5s4aio,1800
+biblicus/knowledge_base.py,sha256=JmlJw8WD_fgstuq1PyWVzU9kzvVzyv7_xOvhS70xwUw,6654
+biblicus/models.py,sha256=6SWQ2Czg9O3zjuam8a4m8V3LlEgcGLbEctYDB6F1rRs,15317
+biblicus/retrieval.py,sha256=A1SI4WK5cX-WbtN6FJ0QQxqlEOtQhddLrL0LZIuoTC4,4180
+biblicus/sources.py,sha256=EFy8-rQNLsyzz-98mH-z8gEHMYbqigcNFKLaR92KfDE,7241
+biblicus/time.py,sha256=3BSKOSo7R10K-0Dzrbdtl3fh5_yShTYqfdlKvvdkx7M,485
+biblicus/uris.py,sha256=xXD77lqsT9NxbyzI1spX9Y5a3-U6sLYMnpeSAV7g-nM,2013
+biblicus/user_config.py,sha256=DqO08yLn82DhTiFpmIyyLj_J0nMbrtE8xieTj2Cgd6A,4287
+biblicus/_vendor/dotyaml/__init__.py,sha256=e4zbejeJRwlD4I0q3YvotMypO19lXqmT8iyU1q6SvhY,376
+biblicus/_vendor/dotyaml/interpolation.py,sha256=PfUAEEOTFobv7Ox0E6nAxht6BqhHIDe4hP32fZn5TOs,1992
+biblicus/_vendor/dotyaml/loader.py,sha256=KePkjyhKZSvQZphmlmlzTYZJBQsqL5qhtGV1y7G6wzM,5624
+biblicus/_vendor/dotyaml/transformer.py,sha256=2AKPS8DMOPuYtzmM-dlwIqVbARfbBH5jYV1m5qpR49E,3725
+biblicus/backends/__init__.py,sha256=wLXIumV51l6ZIKzjoKKeU7AgIxGOryG7T7ls3a_Fv98,1212
+biblicus/backends/base.py,sha256=Erfj9dXg0nkRKnEcNjHR9_0Ddb2B1NvbmRksVm_g1dU,1776
+biblicus/backends/scan.py,sha256=hdNnQWqi5IH6j95w30BZHxLJ0W9PTaOkqfWJuxCCEMI,12478
+biblicus/backends/sqlite_full_text_search.py,sha256=KgmwOiKvkA0pv7vD0V7bcOdDx_nZIOfuIN6Z4Ij7I68,16516
+biblicus/extractors/__init__.py,sha256=X3pu18QL85IBpYf56l6_5PUxFPhEN5qLTlOrxYpfGck,1776
+biblicus/extractors/base.py,sha256=ka-nz_1zHPr4TS9sU4JfOoY-PJh7lbHPBOEBrbQFGSc,2171
+biblicus/extractors/metadata_text.py,sha256=7FbEPp0K1mXc7FH1_c0KhPhPexF9U6eLd3TVY1vTp1s,3537
+biblicus/extractors/openai_stt.py,sha256=fggErIu6YN6tXbleNTuROhfYi7zDgMd2vD_ecXZ7eXs,7162
+biblicus/extractors/pass_through_text.py,sha256=DNxkCwpH2bbXjPGPEQwsx8kfqXi6rIxXNY_n3TU2-WI,2777
+biblicus/extractors/pdf_text.py,sha256=YtUphgLVxyWJXew6ZsJ8wBRh67Y5ri4ZTRlMmq3g1Bk,3255
+biblicus/extractors/pipeline.py,sha256=LY6eM3ypw50MDB2cPEQqZrjxkhVvIc6sv4UEhHdNDrE,3208
+biblicus/extractors/rapidocr_text.py,sha256=OMAuZealLSSTFVVmBalT-AFJy2pEpHyyvpuWxlnY-GU,4531
+biblicus/extractors/select_longest_text.py,sha256=wRveXAfYLdj7CpGuo4RoD7zE6SIfylRCbv40z2azO0k,3702
+biblicus/extractors/select_text.py,sha256=w0ATmDy3tWWbOObzW87jGZuHbgXllUhotX5XyySLs-o,3395
+biblicus/extractors/unstructured_text.py,sha256=l2S_wD_htu7ZHoJQNQtP-kGlEgOeKV_w2IzAC93lePE,3564
+biblicus-0.6.0.dist-info/licenses/LICENSE,sha256=lw44GXFG_Q0fS8m5VoEvv_xtdBXK26pBcbSPUCXee_Q,1078
+biblicus-0.6.0.dist-info/METADATA,sha256=NXcMvQZklQCSukUOGcZaLSw_aqUm6wFojy6k_pfZvzc,21311
+biblicus-0.6.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+biblicus-0.6.0.dist-info/entry_points.txt,sha256=BZmO4H8Uz00fyi1RAFryOCGfZgX7eHWkY2NE-G54U5A,47
+biblicus-0.6.0.dist-info/top_level.txt,sha256=sUD_XVZwDxZ29-FBv1MknTGh4mgDXznGuP28KJY_WKc,9
+biblicus-0.6.0.dist-info/RECORD,,

biblicus-0.6.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

biblicus-0.6.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+biblicus = biblicus.cli:main

biblicus-0.6.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Biblicus Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

biblicus-0.6.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+biblicus