chore: rename repo to retrieval.ist

.python-version

@@ -1 +1 @@
-zotero-3.11.0
+retrieval.ist-3.11.0

pyproject.toml

@@ -66,7 +66,7 @@
     description = ""
     include = ["src/**/*.so", "src/**/*.pyd", "src/**/*.dylib"]
     license = "APGL-3.0"
-    name = "zotero-qa"
+    name = "retrieval.ist"
     readme = "README.md"
     version = "0.0.0-post.22+7cefc52"
     packages = [

src/cli/_cache.py

@@ -8,7 +8,7 @@
 import rich
 import rich.progress
 
-import zotero_qa
+import retrievals
 
 
 def cache(zotero_path: str, cache_path: str) -> None:
@@ -34,10 +34,10 @@ def cache(zotero_path: str, cache_path: str) -> None:
         raise ValueError("The path to the vector database directory is required.")
 
     rich.print("Getting the files to process...")
-    paths = zotero_qa.list_files(f"{zotero_path}/storage")
+    paths = retrievals.list_files(f"{zotero_path}/storage")
 
     rich.print("Creating or loading the cache...")
-    cache = zotero_qa.Cache(f"{cache_path}/cache.json")
+    cache = retrievals.Cache(f"{cache_path}/cache.json")
     cache.load()
 
     print("Iterating over the files to cache their page numbers...")
@@ -51,7 +51,7 @@ def cache(zotero_path: str, cache_path: str) -> None:
             continue
 
         # Load the document.
-        doc = zotero_qa.DocLoader(abspath).doc
+        doc = retrievals.DocLoader(abspath).doc
 
         rich.print(f"Caching: {abspath}...")
         cache.set(abspath, {"pages": doc.page_count, "split": 0, "embedded": 0})

src/cli/_split.py

@@ -10,7 +10,7 @@
 import rich
 import rich.progress
 
-import zotero_qa
+import retrievals
 
 
 def split(zotero_path: str, cache_path: str) -> None:
@@ -21,10 +21,10 @@ def split(zotero_path: str, cache_path: str) -> None:
         raise ValueError("The path to the vector database directory is required.")
 
     rich.print("Getting the files to process...")
-    paths = zotero_qa.list_files(f"{zotero_path}/storage")
+    paths = retrievals.list_files(f"{zotero_path}/storage")
 
     rich.print("Creating or loading the cache...")
-    cache = zotero_qa.Cache(f"{cache_path}/cache.json")
+    cache = retrievals.Cache(f"{cache_path}/cache.json")
     cache.load()
 
     print("Iterating over the files to split and store them in chunks...")
@@ -42,10 +42,10 @@ def split(zotero_path: str, cache_path: str) -> None:
             os.makedirs(f"{cache_path}/splits")
 
         rich.print(f"Splitting: {abspath}...")
-        doc = zotero_qa.open_file(abspath)
+        doc = retrievals.open_file(abspath)
 
         # Get the ids.
-        ids = zotero_qa.get_ids(abspath, doc)
+        ids = retrievals.get_ids(abspath, doc)
 
         for i, page in enumerate(doc):
             # Store the chunk in a text file.

src/retrievals/__init__.py

@@ -9,8 +9,8 @@
 
 """Zotero QA allows you to chat with your Zotero PDF collections."""
 
-from zotero_qa._caching import Cache
-from zotero_qa.domain.document_management._document import Document
+from retrievals._caching import Cache
+from retrievals.domain.document_management._document import Document
 
 # from zotero_qa._pdf import DocLoader, Page, PageParser
 # from zotero_qa._text import DocSplitter, TextSplitter

src/retrievals/_text.pxd

@@ -7,7 +7,7 @@
 
 #  cython: language_level=3
 
-from zotero_qa import Page, PageParser
+from retrievals import Page, PageParser
 
 ctypedef object Page_t
 ctypedef object PageParser_t

src/retrievals/_text.pyx

@@ -11,7 +11,7 @@
 
 import re
 
-from zotero_qa import Page, PageParser
+from retrievals import Page, PageParser
 
 ctypedef object Page_t
 ctypedef object PageParser_t

src/retrievals/_utils.pyx

@@ -16,7 +16,7 @@ import os
 import dotenv
 
 from zotero_qa cimport DocSplitter, TextSplitter
-from zotero_qa import DocLoader, PageParser
+from retrievals import DocLoader, PageParser
 
 # It's necessary to call "import_array" if you use any part of the
 # numpy PyArray_* API. From Cython 3, accessing attributes like

src/retrievals/chain.pyx

@@ -17,7 +17,7 @@ from langchain.chains import RetrievalQA
 from langchain.prompts import PromptTemplate
 from langchain_community.llms import Ollama
 
-from zotero_qa import Store
+from retrievals import Store
 
 # The name of the Ollama model to use.
 model_name = os.getenv("MODEL_NAME")

src/retrievals/embed.pyx

@@ -13,8 +13,8 @@ import os
 
 import dotenv
 
-from zotero_qa import Cache, helpers
-from zotero_qa.store import Store
+from retrievals import Cache, helpers
+from retrievals.store import Store
 
 # Load the environment variables.
 dotenv.load_dotenv()

src/retrievals/query.pyx

@@ -11,7 +11,7 @@
 
 import warnings
 
-from zotero_qa.chain import Chain
+from retrievals.chain import Chain
 
 # Suppress warnings.
 warnings.filterwarnings("ignore")

src/retrievals/store.pyx

@@ -17,7 +17,7 @@ from chromadb.config import Settings
 from langchain.text_splitter import Document
 from langchain_community.vectorstores import Chroma
 
-from zotero_qa.embeddings import Embeddings
+from retrievals.embeddings import Embeddings
 
 # Load the environment variables.
 dotenv.load_dotenv()

tests/zotero_qa/domain/test_document_management.py → tests/embeds/domain/test_document_management.py

@@ -5,47 +5,47 @@
 #  Licensed under the EUPL-1.2-or-later licence.
 #  For details: https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12
 
-import zotero_qa
+import retrievals
 
 
 def test_a_document_is_a_unique_piece_of_knowledge():
     # Arrange
-    document = zotero_qa.Document(
+    document = retrievals.Document(
         authors=[{"first_name": "Mauko", "last_name": "Quiroga-Alvarado"}],
         title="Practical Domain-Driven Design in the Public Sector",
         date=2024,
         summary="How to use domain-driven design in the public sector",
         content="...",
     )
-    different_author = zotero_qa.Document(
+    different_author = retrievals.Document(
         authors=[{"first_name": "Brunildo", "last_name": "Soto"}],
         title="Practical Domain-Driven Design in the Public Sector",
         date=2024,
         summary="How to use domain-driven design in the public sector",
         content="...",
     )
-    different_title = zotero_qa.Document(
+    different_title = retrievals.Document(
         authors=[{"first_name": "Mauko", "last_name": "Quiroga-Alvarado"}],
         title="Unpractical Feature-Driven Design in the Public Sector",
         date=2024,
         summary="How to use domain-driven design in the public sector",
         content="...",
     )
-    different_date = zotero_qa.Document(
+    different_date = retrievals.Document(
         authors=[{"first_name": "Mauko", "last_name": "Quiroga-Alvarado"}],
         title="Practical Domain-Driven Design in the Public Sector",
         date=2027,
         summary="How to use domain-driven design in the public sector",
         content="...",
     )
-    different_summary = zotero_qa.Document(
+    different_summary = retrievals.Document(
         authors=[{"first_name": "Mauko", "last_name": "Quiroga-Alvarado"}],
         title="Practical Domain-Driven Design in the Public Sector",
         date=2024,
         summary="How not to use feature-driven design in the public sector",
         content="...",
     )
-    different_content = zotero_qa.Document(
+    different_content = retrievals.Document(
         authors=[{"first_name": "Mauko", "last_name": "Quiroga-Alvarado"}],
         title="Practical Domain-Driven Design in the Public Sector",
         date=2024,

tests/zotero_qa/test_caching.py → tests/embeds/test_caching.py

@@ -7,7 +7,7 @@
 
 import pytest
 
-from zotero_qa import Cache
+from retrievals import Cache
 
 
 @pytest.fixture()

tests/zotero_qa/test_pdf.py → tests/embeds/test_pdf.py

@@ -7,7 +7,7 @@
 
 import pytest
 
-from zotero_qa import DocLoader, PageParser
+from retrievals import DocLoader, PageParser
 
 
 @pytest.fixture

tests/zotero_qa/test_text.py → tests/embeds/test_text.py

@@ -7,7 +7,7 @@
 
 import pytest
 
-from zotero_qa import DocLoader, DocSplitter, PageParser, TextSplitter
+from retrievals import DocLoader, DocSplitter, PageParser, TextSplitter
 
 
 @pytest.fixture()

tests/zotero_qa/test_utils.py → tests/embeds/test_utils.py

@@ -5,15 +5,15 @@
 #  Licensed under the EUPL-1.2-or-later licence.
 #  For details: https://joinup.ec.europa.eu/collection/eupl/eupl-text-eupl-12
 
-import zotero_qa
+import retrievals
 
 
 def test_load_files():
     # Arrange
     path = "tests/files"
 
     # Act
-    files = zotero_qa.list_files(path)
+    files = retrievals.list_files(path)
 
     # Assert
     assert len(files) == 4
@@ -25,7 +25,7 @@ def test_open_file():
     path = "tests/files/10mb.pdf"
 
     # Act
-    pages = zotero_qa.open_file(path)
+    pages = retrievals.open_file(path)
 
     # Assert
     assert len(pages) == 9