Separate BenchBuilder requirements

BenchBuilder/README.md

@@ -7,6 +7,12 @@ Checkout our [paper](https://arxiv.org/abs/2406.11939) for more details.
 
 BenchBuilder employs a two stage pipeline.
 
+First, install the BenchBuilder dependencies:
+```console
+cd BenchBuilder
+pip install -r requirements.txt
+```
+
 Step 1: annotate the prompt using GPT-3.5-Turbo and filter prompts which either have a score < 5 or belong to a topic cluster with a mean score < 3. This serves as a cheap and first pass through to remove any low quality prompts and clusters before further curation. 
 
 Step 2: use GPT-4-Turbo to annotate the remaining prompts, then extract prompts with quality score of >= 6 and belong to a topic cluster with mean quality score >= 6, ensuring only high-quality prompts are selected with minimal false positives.

BenchBuilder/requirements.txt

@@ -0,0 +1,12 @@
+tiktoken
+openai
+numpy
+pandas
+shortuuid
+tqdm
+gradio==3.40.0
+httpx==0.25.2
+plotly
+scikit-learn
+bertopic[spacy]
+torch

requirements.txt

@@ -7,6 +7,4 @@ tqdm
 gradio==3.40.0
 httpx==0.25.2
 plotly
-scikit-learn
-bertopic[spacy]
-torch
+scikit-learn