Removing old research directory, adding new

parkervg · Oct 18, 2024 · b341e88 · b341e88
1 parent 230bbab
commit b341e88
Show file tree

Hide file tree

Showing 75 changed files with 222 additions and 12,328 deletions.
diff --git a/README.md b/README.md
@@ -155,10 +155,15 @@ For in-depth descriptions of the above queries, check out our [documentation](ht
 ```python
 import pandas as pd
 
-from blendsql import blend, LLMMap, LLMQA, LLMJoin
+import blendsql
+from blendsql.ingredients import LLMMap, LLMQA, LLMJoin
 from blendsql.db import Pandas
 from blendsql.models import TransformersLLM, OpenaiLLM
 
+# Optionally set how many async calls to allow concurrently
+# This depends on your OpenAI/Anthropic/etc. rate limits
+blendsql.config.set_async_limit(10)
+
 # Load model
 # model = OpenaiLLM("gpt-4o") # If you have a .env present with OpenAI API keys
 model = TransformersLLM('Qwen/Qwen1.5-0.5B')
@@ -190,7 +195,7 @@ db = Pandas(
 )
 
 # Write BlendSQL query
-blendsql = """
+query = """
 SELECT * FROM w
 WHERE city = {{
     LLMQA(
@@ -200,8 +205,8 @@ WHERE city = {{
     )
 }}
 """
-smoothie = blend(
-  query=blendsql,
+smoothie = blendsql.blend(
+  query=query,
   db=db,
   ingredients={LLMMap, LLMQA, LLMJoin},
   default_model=model,

diff --git a/blendsql/__init__.py b/blendsql/__init__.py
@@ -1,2 +1,3 @@
-from .ingredients.builtin import LLMMap, LLMQA, LLMJoin, LLMValidate, ImageCaption
 from .blend import blend
+from .ingredients import LLMQA, LLMMap, LLMJoin, LLMValidate, ImageCaption
+from . import _configure as config
diff --git a/docs/quickstart.md b/docs/quickstart.md
@@ -7,42 +7,47 @@ hide:
 ```python
 import pandas as pd
 
-from blendsql import blend, LLMMap, LLMQA, LLMJoin
+import blendsql
+from blendsql.ingredients import LLMMap, LLMQA, LLMJoin
 from blendsql.db import Pandas
 from blendsql.models import TransformersLLM, OpenaiLLM
 
+# Optionally set how many async calls to allow concurrently
+# This depends on your OpenAI/Anthropic/etc. rate limits
+blendsql.config.set_async_limit(10)
+
 # Load model
 # model = OpenaiLLM("gpt-4o") # If you have a .env present with OpenAI API keys
 model = TransformersLLM('Qwen/Qwen1.5-0.5B')
 
 # Prepare our local database
 db = Pandas(
-    {
-        "w": pd.DataFrame(
-            (
-                ['11 jun', 'western districts', 'bathurst', 'bathurst ground', '11-0'],
-                ['12 jun', 'wallaroo & university nsq', 'sydney', 'cricket ground',
-                 '23-10'],
-                ['5 jun', 'northern districts', 'newcastle', 'sports ground', '29-0']
-            ),
-            columns=['date', 'rival', 'city', 'venue', 'score']
-        ),
-        "documents": pd.DataFrame(
-            (
-                ['bathurst, new south wales',
-                 'bathurst /ˈbæθərst/ is a city in the central tablelands of new south wales , australia . it is about 200 kilometres ( 120 mi ) west-northwest of sydney and is the seat of the bathurst regional council .'],
-                ['sydney',
-                 'sydney ( /ˈsɪdni/ ( listen ) sid-nee ) is the state capital of new south wales and the most populous city in australia and oceania . located on australia s east coast , the metropolis surrounds port jackson.'],
-                ['newcastle, new south wales',
-                 'the newcastle ( /ˈnuːkɑːsəl/ new-kah-səl ) metropolitan area is the second most populated area in the australian state of new south wales and includes the newcastle and lake macquarie local government areas .']
-            ),
-            columns=['title', 'content']
-        )
-    }
+  {
+    "w": pd.DataFrame(
+      (
+        ['11 jun', 'western districts', 'bathurst', 'bathurst ground', '11-0'],
+        ['12 jun', 'wallaroo & university nsq', 'sydney', 'cricket ground',
+         '23-10'],
+        ['5 jun', 'northern districts', 'newcastle', 'sports ground', '29-0']
+      ),
+      columns=['date', 'rival', 'city', 'venue', 'score']
+    ),
+    "documents": pd.DataFrame(
+      (
+        ['bathurst, new south wales',
+         'bathurst /ˈbæθərst/ is a city in the central tablelands of new south wales , australia . it is about 200 kilometres ( 120 mi ) west-northwest of sydney and is the seat of the bathurst regional council .'],
+        ['sydney',
+         'sydney ( /ˈsɪdni/ ( listen ) sid-nee ) is the state capital of new south wales and the most populous city in australia and oceania . located on australia s east coast , the metropolis surrounds port jackson.'],
+        ['newcastle, new south wales',
+         'the newcastle ( /ˈnuːkɑːsəl/ new-kah-səl ) metropolitan area is the second most populated area in the australian state of new south wales and includes the newcastle and lake macquarie local government areas .']
+      ),
+      columns=['title', 'content']
+    )
+  }
 )
 
 # Write BlendSQL query
-blendsql = """
+query = """
 SELECT * FROM w
 WHERE city = {{
     LLMQA(
@@ -52,14 +57,14 @@ WHERE city = {{
     )
 }}
 """
-smoothie = blend(
-    query=blendsql,
-    db=db,
-    ingredients={LLMMap, LLMQA, LLMJoin},
-    default_model=model,
-    # Optional args below
-    infer_gen_constraints=True,
-    verbose=True
+smoothie = blendsql.blend(
+  query=query,
+  db=db,
+  ingredients={LLMMap, LLMQA, LLMJoin},
+  default_model=model,
+  # Optional args below
+  infer_gen_constraints=True,
+  verbose=True
 )
 print(smoothie.df)
 # ┌────────┬───────────────────┬──────────┬─────────────────┬─────────┐

diff --git a/research/.gitignore b/research/.gitignore
@@ -0,0 +1 @@
+data/