{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "66cbbaf8",
   "metadata": {},
   "source": [
    "# Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c01c19dc",
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Dict, List, Union\n",
    "import numpy as np\n",
    "from langchain_ollama import OllamaEmbeddings\n",
    "from beir.datasets.data_loader import GenericDataLoader\n",
    "from beir.retrieval.search.dense import DenseRetrievalExactSearch\n",
    "from beir.retrieval.evaluation import EvaluateRetrieval\n",
    "from beir import util\n",
    "import json\n",
    "from datasets import load_dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac011c1c",
   "metadata": {},
   "source": [
    "# Utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b83e7900",
   "metadata": {},
   "outputs": [],
   "source": [
    "class BEIROllamaEmbeddings:\n",
    "    \"\"\"\n",
    "    Adapter that makes LangChain's OllamaEmbeddings compatible with BEIR.\n",
    "    \"\"\"\n",
    "\n",
    "    def __init__(\n",
    "        self,\n",
    "        base_url: str,\n",
    "        model: str,\n",
    "        batch_size: int = 64,\n",
    "    ) -> None:\n",
    "        self.batch_size = batch_size\n",
    "        self.embeddings = OllamaEmbeddings(\n",
    "            base_url=base_url,\n",
    "            model=model,\n",
    "        )\n",
    "\n",
    "    def _batch_embed(self, texts: List[str]) -> np.ndarray:\n",
    "        vectors = []\n",
    "\n",
    "        for i in range(0, len(texts), self.batch_size):\n",
    "            batch = texts[i : i + self.batch_size]\n",
    "            batch_vectors = self.embeddings.embed_documents(batch)\n",
    "            vectors.extend(batch_vectors)\n",
    "\n",
    "        return np.asarray(vectors, dtype=np.float32)\n",
    "\n",
    "    def encode_queries(self, queries: List[str], **kwargs) -> np.ndarray:\n",
    "        \"\"\"\n",
    "        BEIR query encoder\n",
    "        \"\"\"\n",
    "        return self._batch_embed(queries)\n",
    "\n",
    "    def encode_corpus(\n",
    "        self,\n",
    "        corpus: Union[List[Dict[str, str]], Dict[str, Dict[str, str]]],\n",
    "        **kwargs,\n",
    "    ) -> np.ndarray:\n",
    "        \"\"\"\n",
    "        BEIR corpus encoder\n",
    "        \"\"\"\n",
    "        if isinstance(corpus, dict):\n",
    "            corpus = list(corpus.values())\n",
    "\n",
    "        texts = []\n",
    "        for doc in corpus:\n",
    "            title = (doc.get(\"title\") or \"\").strip()\n",
    "            text = (doc.get(\"text\") or \"\").strip()\n",
    "\n",
    "            if title:\n",
    "                texts.append(f\"{title}\\n{text}\")\n",
    "            else:\n",
    "                texts.append(text)\n",
    "\n",
    "        return self._batch_embed(texts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "af3eb66d",
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert_hf_to_beir(hf_dataset):\n",
    "    corpus, queries, qrels = {}, {}, {}\n",
    "    \n",
    "    for i, data in enumerate(hf_dataset):\n",
    "        docid = f\"doc_{i}\"\n",
    "        queryid = f\"q_{i}\"\n",
    "        \n",
    "        # El código es el documento (lo que el agente debe recuperar)\n",
    "        corpus[docid] = {\"title\": data.get(\"func_name\", \"\"), \"text\": data['code']}\n",
    "        \n",
    "        # El docstring es la consulta (lo que el usuario pide)\n",
    "        queries[queryid] = data['docstring']\n",
    "        \n",
    "        # Relación 1 a 1: la query i busca el código i\n",
    "        qrels[queryid] = {docid: 1}\n",
    "            \n",
    "    return corpus, queries, qrels"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9528fb6",
   "metadata": {},
   "source": [
    "# Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "230aae25",
   "metadata": {},
   "outputs": [],
   "source": [
    "raw_dataset = load_dataset(\"google/code_x_glue_tc_nl_code_search_adv\", split=\"test\")\n",
    "corpus, queries, qrels = convert_hf_to_beir(raw_dataset)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13050d31",
   "metadata": {},
   "source": [
    "# Test qwen3-0.6B-emb:latest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "514540af",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = BEIROllamaEmbeddings(\n",
    "    base_url=\"http://localhost:11434\",\n",
    "    model=\"qwen3-0.6B-emb:latest\",\n",
    "    batch_size=64,\n",
    ")\n",
    "\n",
    "# Inicializar buscador y evaluador\n",
    "retriever = DenseRetrievalExactSearch(model, batch_size=64)\n",
    "evaluator = EvaluateRetrieval(retriever, score_function=\"cos_sim\")\n",
    "\n",
    "# Ejecutar recuperación\n",
    "results = evaluator.retrieve(corpus, queries)\n",
    "\n",
    "# Evaluar métricas (NDCG, MAP, Recall, Precision)\n",
    "ndcg, _map, recall, precision = evaluator.evaluate(\n",
    "    qrels, results, [1, 3, 5, 10]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5c0f9845",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resultados para CodeXGLUE:\n",
      "NDCG: {'NDCG@1': 0.94971, 'NDCG@3': 0.96956, 'NDCG@5': 0.97166, 'NDCG@10': 0.97342}\n",
      "MAP: {'MAP@1': 0.94971, 'MAP@3': 0.96504, 'MAP@5': 0.9662, 'MAP@10': 0.96694}\n",
      "Recall: {'Recall@1': 0.94971, 'Recall@3': 0.98251, 'Recall@5': 0.98761, 'Recall@10': 0.99297}\n",
      "Precision: {'P@1': 0.94971, 'P@3': 0.3275, 'P@5': 0.19752, 'P@10': 0.0993}\n"
     ]
    }
   ],
   "source": [
    "print(f\"Resultados para CodeXGLUE:\")\n",
    "print(\"NDCG:\", ndcg)\n",
    "print(\"MAP:\", _map)\n",
    "print(\"Recall:\", recall)\n",
    "print(\"Precision:\", precision)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4e643ca",
   "metadata": {},
   "source": [
    "# Test qwen2.5:1.5b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5ced1c25",
   "metadata": {},
   "outputs": [],
   "source": [
    "model_q2 = BEIROllamaEmbeddings(\n",
    "    base_url=\"http://localhost:11434\",\n",
    "    model=\"qwen2.5:1.5b\",\n",
    "    batch_size=64,\n",
    ")\n",
    "\n",
    "# Inicializar buscador y evaluador\n",
    "retriever_q2 = DenseRetrievalExactSearch(model_q2, batch_size=64)\n",
    "evaluator_q2 = EvaluateRetrieval(retriever_q2, score_function=\"cos_sim\")\n",
    "\n",
    "# Ejecutar recuperación\n",
    "results_q2 = evaluator_q2.retrieve(corpus, queries)\n",
    "\n",
    "# Evaluar métricas (NDCG, MAP, Recall, Precision)\n",
    "ndcg_qwen_2, _map_qwen_2, recall_qwen_2, precision_qwen_2 = evaluator_q2.evaluate(\n",
    "    qrels, results_q2, [1, 3, 5, 10]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6a95189e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resultados para CodeXGLUE:\n",
      "NDCG: {'NDCG@1': 0.00031, 'NDCG@3': 0.00061, 'NDCG@5': 0.00086, 'NDCG@10': 0.00118}\n",
      "MAP: {'MAP@1': 0.00031, 'MAP@3': 0.00051, 'MAP@5': 0.00065, 'MAP@10': 0.00078}\n",
      "Recall: {'Recall@1': 0.00031, 'Recall@3': 0.00088, 'Recall@5': 0.00151, 'Recall@10': 0.0025}\n",
      "Precision: {'P@1': 0.00031, 'P@3': 0.00029, 'P@5': 0.0003, 'P@10': 0.00025}\n"
     ]
    }
   ],
   "source": [
    "print(f\"Resultados para CodeXGLUE:\")\n",
    "print(\"NDCG:\", ndcg_qwen_2)\n",
    "print(\"MAP:\", _map_qwen_2)\n",
    "print(\"Recall:\", recall_qwen_2)\n",
    "print(\"Precision:\", precision_qwen_2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3dad9811",
   "metadata": {},
   "source": [
    "# Save data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f875dd8d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Resultados guardados en /home/pseco/VsCodeProjects/assistance-engine/data/interim/beir_CodeXGlue_results.json\n"
     ]
    }
   ],
   "source": [
    "results_data = {\n",
    "    \"qwen3-0.6B-emb:latest\": {\n",
    "        \"NDCG\": ndcg,\n",
    "        \"MAP\": _map,\n",
    "        \"Recall\": recall,\n",
    "        \"Precision\": precision,\n",
    "    },\n",
    "    \"qwen2.5:1.5b\": {\n",
    "        \"NDCG\": ndcg_qwen_2,\n",
    "        \"MAP\": _map_qwen_2,\n",
    "        \"Recall\": recall_qwen_2,\n",
    "        \"Precision\": precision_qwen_2,\n",
    "    }\n",
    "}\n",
    "\n",
    "output_file = \"/home/pseco/VsCodeProjects/assistance-engine/data/interim/beir_CodeXGlue_results.json\"\n",
    "with open(output_file, \"w\") as f:\n",
    "    json.dump(results_data, f, indent=2)\n",
    "\n",
    "print(f\"Resultados guardados en {output_file}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "assistance-engine",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}