Merge pull request #117 from bespokelabsai/mahesh/update_doc

Update README and the poem example.
bespokelabsai · Nov 15, 2024 · 3a88375 · 3a88375
2 parents 4a7ae7f + 1ae2173
commit 3a88375
Show file tree

Hide file tree

Showing 4 changed files with 83 additions and 72 deletions.
diff --git a/README.md b/README.md
@@ -1,8 +1,8 @@
 <p align="center">
   <a href="https://bespokelabs.ai/" target="_blank">
     <picture>
-      <source media="(prefers-color-scheme: light)" width="80" srcset="./docs/Bespoke-Labs-Logomark-Red.png">
-      <img alt="Bespoke Labs Logo" width="80" src="./docs/Bespoke-Labs-Logomark-Red-on-Black.png">
+      <source media="(prefers-color-scheme: light)" width="80" srcset="https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red.png">
+      <img alt="Bespoke Labs Logo" width="80" src="https://raw.githubusercontent.com/bespokelabsai/curator/main/docs/Bespoke-Labs-Logomark-Red-on-Black.png">
     </picture>
   </a>
 </p>
@@ -37,22 +37,57 @@ pip install bespokelabs-curator
 
 ```python
 from bespokelabs import curator
-import os
+from datasets import Dataset
+from pydantic import BaseModel, Field
+from typing import List
 
-os.environ['OPENAI_API_KEY'] = 'sk-...' # Set your OpenAI API key here
+# Create a dataset object for the topics you want to create the poems.
+topics = Dataset.from_dict({"topic": [
+    "Urban loneliness in a bustling city",
+    "Beauty of Bespoke Labs's Curator library"
+]})
 
+# Define a class to encapsulate a list of poems.
+class Poem(BaseModel):
+    poem: str = Field(description="A poem.")
+
+class Poems(BaseModel):
+    poems_list: List[Poem] = Field(description="A list of poems.")
+
+
+# We define a Prompter that generates poems which gets applied to the topics dataset.
 poet = curator.Prompter(
-    prompt_func=lambda: "Write a poem about the beauty of computer science",
+    # `prompt_func` takes a row of the dataset as input.
+    # `row` is a dictionary with a single key 'topic' in this case.
+    prompt_func=lambda row: f"Write two poems about {row['topic']}.",
     model_name="gpt-4o-mini",
+    response_format=Poems,
+    # `row` is the input row, and `poems` is the `Poems` class which 
+    # is parsed from the structured output from the LLM.
+    parse_func=lambda row, poems: [
+        {"topic": row["topic"], "poem": p.poem} for p in poems.poems_list
+    ],
 )
 
-poem = poet()
-print(poem["response"][0])
+poem = poet(topics)
+print(poem.to_pandas())
+# Example output:
+#                                       topic                                               poem
+# 0       Urban loneliness in a bustling city  In the city's heart, where the sirens wail,\nA...
+# 1       Urban loneliness in a bustling city  City streets hum with a bittersweet song,\nHor...
+# 2  Beauty of Bespoke Labs's Curator library  In whispers of design and crafted grace,\nBesp...
+# 3  Beauty of Bespoke Labs's Curator library  In the hushed breath of parchment and ink,\nBe...
 ```
+Note that `topics` can be created with `curator.Prompter` as well,
+and we can scale this up to create tens of thousands of diverse poems.
+You can see a more detailed example in the [examples/poem.py](https://github.com/bespokelabsai/curator/blob/mahesh/update_doc/examples/poem.py) file,
+and other examples in the [examples](https://github.com/bespokelabsai/curator/blob/mahesh/update_doc/examples) directory.
 
-You can see more examples in the [examples](examples) directory.
+To run the examples, make sure to set your OpenAI API key in 
+the environment variable `OPENAI_API_KEY` by running `export OPENAI_API_KEY=sk-...` in your terminal.
 
-To run the examples, make sure to set your OpenAI API key in the environment variable `OPENAI_API_KEY` by running `export OPENAI_API_KEY=sk-...` in your terminal.
+See the [docs](https://docs.bespokelabs.ai/) for more details as well as 
+for troubleshooting information.
 
 ## Bespoke Curator Viewer
 

diff --git a/bespoke-dataset-viewer/components/dataset-viewer/RunsTable.tsx b/bespoke-dataset-viewer/components/dataset-viewer/RunsTable.tsx
@@ -21,22 +21,46 @@ const COLUMNS: Column[] = [
 ]
 
 const EXAMPLE_CODE = `from bespokelabs import curator
-import os
+from datasets import Dataset
+from pydantic import BaseModel, Field
+from typing import List
 
-# Set your OpenAI API key here
-os.environ['OPENAI_API_KEY'] = 'sk-...'
+# Create a dataset object for the topics you want to create the poems.
+topics = Dataset.from_dict({"topic": [
+    "Urban loneliness in a bustling city",
+    "Beauty of Bespoke Labs's Curator library"
+]})
 
-# Create a prompter instance
+# Define a class to encapsulate a list of poems.
+class Poem(BaseModel):
+    poem: str = Field(description="A poem.")
+
+class Poems(BaseModel):
+    poems_list: List[Poem] = Field(description="A list of poems.")
+
+
+# We define a Prompter that generates poems which gets applied to the topics dataset.
 poet = curator.Prompter(
-    prompt_func=lambda: {
-        "user_prompt": "Write a poem about the beauty of computer science"
-    },
+    # prompt_func takes a row of the dataset as input.
+    # row is a dictionary with a single key 'topic' in this case.
+    prompt_func=lambda row: f"Write two poems about {row['topic']}.",
     model_name="gpt-4o-mini",
+    response_format=Poems,
+    # row is the input row, and poems is the Poems class which 
+    # is parsed from the structured output from the LLM.
+    parse_func=lambda row, poems: [
+        {"topic": row["topic"], "poem": p.poem} for p in poems.poems_list
+    ],
 )
 
-# Generate and print the poem
-poem = poet()
-print(poem.to_list()[0])`
+poem = poet(topics)
+print(poem.to_pandas())
+# Example output:
+#                                       topic                                               poem
+# 0       Urban loneliness in a bustling city  In the city's heart, where the sirens wail,\\nA...
+# 1       Urban loneliness in a bustling city  City streets hum with a bittersweet song,\\nHor...
+# 2  Beauty of Bespoke Labs's Curator library  In whispers of design and crafted grace,\\nBesp...
+# 3  Beauty of Bespoke Labs's Curator library  In the hushed breath of parchment and ink,\\nBe...`
 
 export function RunsTable() {
   const [runs, setRuns] = useState<Run[]>([])

diff --git a/bespoke-dataset-viewer/components/ui/python-highlighter.tsx b/bespoke-dataset-viewer/components/ui/python-highlighter.tsx
@@ -1,9 +1,9 @@
+import { Button } from "@/components/ui/button";
+import { Check, Copy } from "lucide-react";
 import Prism from 'prismjs';
 import 'prismjs/components/prism-python';
 import 'prismjs/themes/prism-tomorrow.css';
 import React from 'react';
-import { Button } from "@/components/ui/button"
-import { Check, Copy } from "lucide-react"
 
 interface PythonHighlighterProps {
     code: string;
@@ -38,7 +38,7 @@ export const PythonHighlighter: React.FC<PythonHighlighterProps> = ({ code }) =>
                     )}
                 </Button>
             </div>
-            <pre className="text-sm bg-gray-900 p-4 m-0">
+            <pre className="bg-gray-900 p-4 m-0" style={{ fontSize: '12px' }}>
                 <code className="language-python">
                     {code}
                 </code>

diff --git a/examples/poem.py b/examples/poem.py
@@ -1,54 +1,6 @@
 """Example of using the curator library to generate diverse poems.
 
-We generate 10 diverse topics and then generate 2 poems for each topic.
-
-You can do this in a loop, but that is inefficient and breaks when requests fail.
-When you need to do this thousands of times (or more), you need a better abstraction.
-
-curator.Prompter takes care of this heavy lifting.
-
-# Key Components of Prompter
-
-## prompt_func
-
-Calls an LLM on each row of the input dataset in parallel. 
-
-1. Takes a dataset row as input
-2. Returns the prompt for the LLM
-
-## parse_func
-
-Converts LLM output into structured data by adding it back to the dataset.
-
-1. Takes two arguments:
-    - Input row
-    - LLM response (in response_format)
-2. Returns new rows (in list of dictionaries)
-
-
-# Data Flow Example
-Input Dataset: 
-    Row A
-    Row B
-Processing by Prompter:
-    Row A    →    prompt_func(A)    →    Response R1    →    parse_func(A, R1)    →    [C, D]
-    Row B    →    prompt_func(B)    →    Response R2    →    parse_func(B, R2)    →    [E, F]
-
-Output Dataset: 
-    Row C
-    Row D
-    Row E
-    Row F
-
-In this example:
-
-- The two input rows (A and B) are processed in parallel to prompt the LLM
-- Each generates a response (R1 and R2)
-- The parse function converts each response into (multiple) new rows (C, D, E, F)
-- The final dataset contains all generated rows
-
-You can chain prompters together to iteratively build up a dataset.
-"""
+We generate 10 diverse topics and then generate 2 poems for each topic."""
 
 from bespokelabs import curator
 from datasets import Dataset
@@ -103,4 +55,4 @@ class Poems(BaseModel):
 # 0                            Dreams vs. reality  In the realm where dreams take flight,\nWhere ...
 # 1                            Dreams vs. reality  Reality stands with open eyes,\nA weighty thro...
 # 2           Urban loneliness in a bustling city  In the city's heart where shadows blend,\nAmon...
-# 3           Urban loneliness in a bustling city  Among the crowds, I walk alone,\nA sea of face...
+# 3           Urban loneliness in a bustling city  Among the crowds, I walk alone,\nA sea of face...