Adding setup.py

.gitignore

@@ -1,3 +1,4 @@
+proxies.py
 outputs/
 research/db/
 *.crt

blendsql/blend-cli.py → blendsql/blend_cli.py

@@ -26,10 +26,10 @@ def cls():
     os.system("cls" if os.name == "nt" else "clear")
 
 
-if __name__ == "__main__":
+def main():
     parser = argparse.ArgumentParser()
     parser.add_argument("db_path", nargs="?")
-    parser.add_argument("--secrets_path", default="./secrets.json")
+    parser.add_argument("secrets_path", nargs="?", default="./secrets.json")
     args = parser.parse_args()
 
     init_secrets(args.secrets_path)
@@ -56,7 +56,7 @@ def cls():
                 ingredients={LLMQA, LLMMap, LLMJoin, DT},
                 overwrite_args={"endpoint": "gpt-4", "long_answer": False},
                 infer_map_constraints=True,
-                verbose=True
+                verbose=True,
             )
             print()
             print(
@@ -70,4 +70,3 @@ def cls():
             print()
         except Exception as error:
             print(error)
-            pass

blendsql/db/sqlite_db_connector.py

@@ -167,4 +167,5 @@ def _create_clause(con, tablename) -> str:
         logging.debug(
             f"Expected create_clause size to be 1, got {create_clause.size}\n{create_clause}"
         )
+        return ""
     return create_clause.values[0][0]

setup.py

@@ -0,0 +1,70 @@
+import os
+import re
+import codecs
+from setuptools import setup, find_packages
+
+here = os.path.abspath(os.path.dirname(__file__))
+
+
+def read(*parts):
+    with codecs.open(os.path.join(here, *parts), "r") as fp:
+        return fp.read()
+
+
+def find_version(*file_paths):
+    version_file = read(*file_paths)
+    version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", version_file, re.M)
+    if version_match:
+        return version_match.group(1)
+    raise RuntimeError("Unable to find version string.")
+
+
+setup(
+    entry_points={
+        "console_scripts": ["blendsql=blendsql.blend_cli:main"],
+    },
+    name="blendsql",
+    version=find_version("blendsql", "__init__.py"),
+    url="https://github.com/parkervg/blendsql",
+    author="Parker Glenn",
+    author_email="[email protected]",
+    description="A scalable SQL dialect for problem decomposition and heterogenous question-answering with LLMs.",
+    license="Apache License 2.0",
+    packages=find_packages(exclude=["examples", "research", "img"]),
+    install_requires=[
+        "openai==0.28.0",
+        "guidance==0.0.64",
+        "pyparsing==3.1.1",
+        "pandas>=2.0.0",
+        "bottleneck>=1.3.6",
+        "sqlglot",
+        "pre-commit",
+        "attrs",
+        "tqdm",
+        "dateparser",
+        "colorama",
+        "fiscalyear",
+        "tabulate",
+        "typeguard",
+        "azure-identity",
+        "nbformat",
+    ],
+    extras_require={
+        "research": [
+            "datasets==2.16.1",
+            "nltk",
+            "wikiextractor",
+            "rouge_score",
+            "rapidfuzz",
+            "records",
+            "SQLAlchemy",
+            "recognizers-text",
+            "recognizers-text-suite",
+            "emoji==1.7.0",
+            "transformers",
+        ],
+        "test": [
+            "pytest",
+        ],
+    },
+)