Update all_tools.py

all_tools.py

@@ -1,42 +1,14 @@
 from llama_index.core import VectorStoreIndex, Document
 from smolagents import tool
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from all_datasets import *
+#from all_datasets import *
 from level_classifier_tool_2 import (
     classify_levels_phrases,
     HFEmbeddingBackend,
     build_phrase_index
 )
 from phrases import BLOOMS_PHRASES, DOK_PHRASES
-D = {
-    "GSM8k": GSM8k['question'],
-    "Olympiad": Olympiad_math['question'],
-    "Olympiad2": Olympiad_math2['question'],
-    "DeepMind Math": clean_math['question'],
-    "MMMLU": MMMLU['question'],
-    "MMMU": MMMU['question'],
-    "ScienceQA": ScienceQA['question'],
-    "PubmedQA": PubmedQA['question']
-}
 
-all_questions = (
-    list(D["GSM8k"]) +
-    list(D["Olympiad"]) +
-    list(D["MMMLU"]) +
-    list(D["MMMU"]) +
-    list(D["DeepMind Math"]) +
-    list(D["Olympiad2"]) +
-    list(D["ScienceQA"]) +
-    list(D["PubmedQA"])
-)
-
-emb = HuggingFaceEmbeddings(
-    model_name="google/embeddinggemma-300m",
-    encode_kwargs={"normalize_embeddings": True},
-)
-
-texts = all_questions
-index = VectorStoreIndex.from_documents([Document(text=t) for t in texts], embed_model=emb)
 #Retriever tool
 @tool
 def QuestionRetrieverTool(subject: str, topic: str, grade: str) -> dict: