Update all_tools.py

all_tools.py

@@ -1,40 +1,63 @@
-from llama_index.core import VectorStoreIndex, Document
+from __future__ import annotations
+from typing import Dict, List, Tuple
 from smolagents import tool
-from langchain_community.embeddings import HuggingFaceEmbeddings
-#from all_datasets import *
-from level_classifier_tool_2 import (
-    classify_levels_phrases,
-    HFEmbeddingBackend,
-    build_phrase_index
-)
+
+# Import only the classifier API; DO NOT construct models here.
+from level_classifier_tool_2 import classify_levels_phrases
 from phrases import BLOOMS_PHRASES, DOK_PHRASES
 
-#Retriever tool
+# ------------------------ Injected state (set from app.py) ------------------------
+_INDEX = None
+_BACKEND = None
+_BLOOM_INDEX = None
+_DOK_INDEX = None
+
+def set_retrieval_index(index) -> None:
+    """Call this from app.py after loading your LlamaIndex index."""
+    global _INDEX
+    _INDEX = index
+
+def set_classifier_state(backend, bloom_index, dok_index) -> None:
+    """Call this from app.py after building the backend and prebuilt indices."""
+    global _BACKEND, _BLOOM_INDEX, _DOK_INDEX
+    _BACKEND = backend
+    _BLOOM_INDEX = bloom_index
+    _DOK_INDEX = dok_index
+
+# ----------------------------- Tools -------------------------------------
+
 @tool
 def QuestionRetrieverTool(subject: str, topic: str, grade: str) -> dict:
-    """ Retrieve up to 5 closely-related example Q&A pairs from the source datasets.
-    description = (
-        "Retrieve up to 5 closely-related example Q&A pairs from the source datasets."
-    )
+    """
+    Retrieve up to 5 closely-related example Q&A pairs from the source datasets.
+
     Args:
-        subject: The subject area (e.g., "Math", "Science"). type: "string",
-        topic: The specific topic within the subject (e.g., "Algebra", "Biology"). type: "string",
-        grade: The grade level (e.g., "5th", "8th"). type: "string"
+        subject: The subject area (e.g., "Math", "Science").
+        topic: The specific topic within the subject (e.g., "Algebra", "Biology").
+        grade: The grade level (e.g., "Grade 5", "Grade 8").
+
     Returns:
-        A dictionary with:
-            closest questions found for: dict with subject, topic, grade
-            questions: List of up to 5 dicts with question text.
-    }"""
+        {
+          "closest questions found for": {"subject": ..., "topic": ..., "grade": ...},
+          "questions": [{"text": "..."} * up to 5]
+        }
+    """
+    if _INDEX is None:
+        return {"error": "Retriever not initialized. Call set_retrieval_index(index) before using this tool."}
+
     query = f"{topic} question for {grade} of the {subject}"
-    results = index.as_retriever(similarity_top_k=5).retrieve(query)
-    question_texts = [r.node.text for r in results]
-    return {"closest questions found for": {
-        "subject": subject,
-        "topic": topic,
-        "grade": grade,},
-        "questions": [{"text": question} for question in question_texts]
+    try:
+        results = _INDEX.as_retriever(similarity_top_k=5).retrieve(query)
+        question_texts = [r.node.text for r in results]
+    except Exception as e:
+        return {"error": f"Retriever error: {e}"}
+
+    return {
+        "closest questions found for": {"subject": subject, "topic": topic, "grade": grade},
+        "questions": [{"text": q} for q in question_texts]
     }
-# Scoring tool
+
+
 @tool
 def classify_and_score(
     question: str,
@@ -42,33 +65,38 @@ def classify_and_score(
     target_dok: str,
     agg: str = "max"
 ) -> dict:
-    """Classify a question against Bloom’s and DOK targets and return guidance.
-    
+    """
+    Classify a question against Bloom’s and DOK targets and return guidance.
+
     Args:
-        question: The question text to evaluate for cognitive demand.
-        target_bloom: Target Bloom’s level or range. Accepts exact (e.g., "Analyze")
-            or plus form (e.g., "Apply+") meaning that level or higher.
-        target_dok: Target DOK level or range. Accepts exact (e.g., "DOK3")
-            or span (e.g., "DOK2-DOK3").
-        agg: Aggregation method over phrase similarities within a level
-            (choices: "mean", "max", "topk_mean").
-    
+        question: Question text to evaluate.
+        target_bloom: Target Bloom’s level (e.g., "Analyze" or "Apply+").
+        target_dok: Target DOK level (e.g., "DOK3" or "DOK2-DOK3").
+        agg: Aggregation over phrase sims ("mean", "max", "topk_mean").
+
     Returns:
-        A dictionary with:
-            ok: True if both Bloom’s and DOK match the targets.
-            measured: Dict with best levels and per-level scores for Bloom’s and DOK.
-            feedback: Brief guidance describing how to adjust the question to hit targets.
+        {
+          "ok": bool,
+          "measured": {"bloom_best": str, "bloom_scores": dict, "dok_best": str, "dok_scores": dict},
+          "feedback": str
+        }
     """
-    res = classify_levels_phrases(
-        question,
-        BLOOMS_PHRASES,
-        DOK_PHRASES,
-        backend=_backend,
-        prebuilt_bloom_index=_BLOOM_INDEX,
-        prebuilt_dok_index=_DOK_INDEX,
-        agg=agg,
-        return_phrase_matches=True
-    )
+    if _BACKEND is None or _BLOOM_INDEX is None or _DOK_INDEX is None:
+        return {"error": "Classifier not initialized. Call set_classifier_state(backend, bloom_index, dok_index) first."}
+
+    try:
+        res = classify_levels_phrases(
+            question,
+            BLOOMS_PHRASES,
+            DOK_PHRASES,
+            backend=_BACKEND,
+            prebuilt_bloom_index=_BLOOM_INDEX,
+            prebuilt_dok_index=_DOK_INDEX,
+            agg=agg,
+            return_phrase_matches=True
+        )
+    except Exception as e:
+        return {"error": f"classify_levels_phrases failed: {e}"}
 
     def _parse_target_bloom(t: str):
         order = ["Remember","Understand","Apply","Analyze","Evaluate","Create"]
@@ -114,4 +142,4 @@ def classify_and_score(
             "dok_scores": res["dok"]["scores"],
         },
         "feedback": " ".join(feedback_parts) if feedback_parts else "On target.",
-    }
+    }