From cc18a8f987f9f7b604074b170bc188a02900469c Mon Sep 17 00:00:00 2001
From: parkervg <parkervg5@gmail.com>
Date: Wed, 7 Feb 2024 11:56:42 -0500
Subject: [PATCH] Adding setup.py

---
 .gitignore                              |  1 +
 blend                                   |  1 -
 blendsql/{blend-cli.py => blend_cli.py} |  7 ++-
 blendsql/db/sqlite_db_connector.py      |  1 +
 requirements.txt                        | 32 -----------
 setup.py                                | 70 +++++++++++++++++++++++++
 6 files changed, 75 insertions(+), 37 deletions(-)
 delete mode 100755 blend
 rename blendsql/{blend-cli.py => blend_cli.py} (93%)
 delete mode 100644 requirements.txt
 create mode 100644 setup.py

diff --git a/.gitignore b/.gitignore
index 15ee0cb8..216a49b1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
+proxies.py
 outputs/
 research/db/
 *.crt
diff --git a/blend b/blend
deleted file mode 100755
index d564973b..00000000
--- a/blend
+++ /dev/null
@@ -1 +0,0 @@
-python -m blendsql.blend-cli $1 --secrets_path=$2
\ No newline at end of file
diff --git a/blendsql/blend-cli.py b/blendsql/blend_cli.py
similarity index 93%
rename from blendsql/blend-cli.py
rename to blendsql/blend_cli.py
index 6a8472db..0add8787 100644
--- a/blendsql/blend-cli.py
+++ b/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
diff --git a/blendsql/db/sqlite_db_connector.py b/blendsql/db/sqlite_db_connector.py
index d3ad5f38..01b0217d 100644
--- a/blendsql/db/sqlite_db_connector.py
+++ b/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]
diff --git a/requirements.txt b/requirements.txt
deleted file mode 100644
index de287272..00000000
--- a/requirements.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-pre-commit
-attrs
-tqdm
-dateparser
-colorama
-sql-metadata
-openai==0.28.0
-tiktoken
-guidance==0.0.64
-pyparsing==3.1.1
-fiscalyear
-pandas
-sqlglot
-tabulate
-pytest
-typeguard
-rapidfuzz
-records
-SQLAlchemy
-recognizers-text
-recognizers-text-suite
-emoji==1.7.0
-azure-identity
-transformers
-nbformat
-datasets==2.16.1
-nltk
-sentence-transformers
-wikiextractor
-
-rouge_score
-git+https://github.com/google-research/bleurt.git
\ No newline at end of file
diff --git a/setup.py b/setup.py
new file mode 100644
index 00000000..1425072b
--- /dev/null
+++ b/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="parkervg5@gmail.com",
+    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",
+        ],
+    },
+)