Recherche de documents avec représentations vectorielles continues

Afficher sur ai.google.dev

Exécuter dans Google Colab

Consulter le code source sur GitHub

Présentation

Cet exemple montre comment utiliser l'API Gemini pour créer des représentations vectorielles continues afin d'effectuer une recherche dans des documents. Vous allez utiliser la bibliothèque cliente Python pour créer une représentation vectorielle continue de mots qui vous permet de comparer des chaînes de recherche, ou des questions, à des contenus de documents.

Dans ce tutoriel, vous allez utiliser des représentations vectorielles continues pour effectuer une recherche dans un ensemble de documents et poser des questions sur la voiture Google.

Prérequis

Vous pouvez exécuter ce guide de démarrage rapide dans Google Colab.

Pour suivre ce guide de démarrage rapide dans votre propre environnement de développement, assurez-vous que celui-ci répond aux exigences suivantes:

• Python 3.9 et versions ultérieures
• Une installation de jupyter pour exécuter le notebook

Configuration

Commencez par télécharger et installer la bibliothèque Python de l'API Gemini.

pip install -U -q google.generativeai

import textwrap
import numpy as np
import pandas as pd

import google.generativeai as genai

# Used to securely store your API key
from google.colab import userdata

from IPython.display import Markdown

Obtenir une clé API

Avant de pouvoir utiliser l'API Gemini, vous devez obtenir une clé API. Si vous n'avez pas encore de clé, créez-en une en un clic dans Google AI Studio.

Obtenir une clé API

Dans Colab, ajoutez la clé au gestionnaire de secrets sous l'icône " succès" dans le panneau de gauche. Nommez-la API_KEY.

Une fois que vous disposez de la clé API, transmettez-la au SDK. Pour cela, vous avez le choix entre deux méthodes :

• Placez la clé dans la variable d'environnement GOOGLE_API_KEY (le SDK la récupère automatiquement à partir de là).
• Transmettre la clé à genai.configure(api_key=...)

# Or use `os.getenv('API_KEY')` to fetch an environment variable.
API_KEY=userdata.get('API_KEY')

genai.configure(api_key=API_KEY)

for m in genai.list_models():
  if 'embedContent' in m.supported_generation_methods:
    print(m.name)

models/embedding-001
models/embedding-001

Génération de représentations vectorielles continues

Dans cette section, vous allez apprendre à générer des représentations vectorielles continues pour un texte à l'aide de celles de l'API Gemini.

Modifications apportées à l'API Embeddings avec le modèle Embedding-001

Le nouveau modèle de représentations vectorielles continues, Embedding-001, comporte un nouveau paramètre de type de tâche et un titre facultatif (uniquement valide lorsque task_type=RETRIEVAL_DOCUMENT).

Ces nouveaux paramètres ne s'appliquent qu'aux modèles de représentations vectorielles continues les plus récents.Les types de tâches sont les suivants:

title = "The next generation of AI for developers and Google Workspace"
sample_text = ("Title: The next generation of AI for developers and Google Workspace"
    "\n"
    "Full article:\n"
    "\n"
    "Gemini API & Google AI Studio: An approachable way to explore and prototype with generative AI applications")

model = 'models/embedding-001'
embedding = genai.embed_content(model=model,
                                content=sample_text,
                                task_type="retrieval_document",
                                title=title)

print(embedding)

{'embedding': [0.034585103, -0.044509504, -0.027291223, 0.0072681927, 0.061689284, 0.03362112, 0.028627988, 0.022681564, 0.04958079, 0.07274552, 0.011150464, 0.04200501, -0.029782884, -0.0041767005, 0.05074771, -0.056339227, 0.051204756, 0.04734613, -0.022025354, 0.025162602, 0.046016376, -0.003416976, -0.024010269, -0.044340927, -0.01520864, -0.013577372, -0.009918958, -0.028144406, -0.00024770075, 0.031201784, -0.072506696, 0.022366496, -0.032672316, -0.0025522006, -0.0019957912, -0.023193765, -0.020633291, -0.014031609, -0.00071676675, -0.0073200124, 0.014770645, -0.09390713, -0.017846372, 0.032825496, 0.017616265, -0.046674345, 0.03469292, 0.03386835, 0.0028274113, -0.07737739, 0.023789782, 0.025950644, 0.06952142, -0.029875675, -0.018693604, 0.007266584, -0.0067282487, 0.000802912, 0.020609016, 0.012406181, -0.018825717, 0.051171597, -0.0080359895, 0.008457639, 0.01197146, -0.080320396, -0.040698495, 0.0018266322, 0.042915005, 0.021464704, 0.022519842, 0.0059912056, 0.050887667, -0.04566639, -0.012651369, -0.14023173, -0.0274054, 0.04492792, 0.014709818, 0.037258334, -0.021294944, -0.041852854, -0.069640376, -0.030281356, -0.0070775123, 0.019886682, -0.050179508, -0.03839318, -0.014652514, 0.03370254, -0.02803748, -0.059206057, 0.055928297, -0.034912255, -0.007784368, 0.098106734, -0.06873356, -0.052850258, -0.011798939, -0.030071719, -0.026038093, 0.016752971, -0.020916667, 0.007365556, 0.017650642, 0.006677715, -0.036498126, 0.02110524, -0.05625146, 0.043038886, -0.06515849, -0.019825866, -0.010379261, -0.037537806, 0.017674655, -0.042821705, 0.014320703, 0.036735073, 0.011445211, 0.027352763, -0.0028090556, 0.009011982, 0.024146665, 0.002215841, -0.07397819, 0.008714616, -0.03377923, 0.034349587, 0.022429721, 0.052665956, -0.0021583177, -0.040462274, -0.019938014, 0.030099798, 0.009743918, 0.009111553, 0.026379738, -0.015910586, 0.010171418, 0.023996552, -0.031924065, 0.024775924, 0.014129728, 0.008913726, -0.010156162, 0.05407575, -0.080851324, 0.022005167, 0.012674272, -0.017213775, -0.009514327, 0.03276702, -0.06795425, -0.0004906647, 0.036379207, 0.034329377, -0.037122324, 0.05565231, -0.0038797501, 0.009620726, 0.050033607, 0.0084967585, 0.050638147, 0.00490447, 0.006675041, -0.04295331, -0.006490465, 0.010016808, -0.011493882, 0.023702862, 0.029825455, 0.03514081, -0.013388401, -0.05283049, 0.00019729362, -0.05095579, -0.031205554, 0.0045187837, -0.0066217924, -0.007931168, -0.0030577614, -0.016934164, 0.04188085, 0.050768845, 0.009407336, -0.02838461, 0.079967216, -0.038705315, -0.06723827, 0.015558192, -0.043977134, -0.022096274, -0.0053875325, -0.022216668, 0.013843675, 0.04506347, 0.051535256, 0.033484843, 0.044276737, -0.01299742, 0.021727907, 0.06798745, 0.038896713, 0.0023941514, 0.00815586, 0.029679826, 0.109524906, 0.012102062, -0.058510404, 0.03252702, -0.050666984, -0.006376317, 0.026164565, 0.008671174, 0.05052107, -0.027606683, 0.005126455, -0.0029112308, -0.015136989, -0.026336055, -0.031090762, 0.01717387, -0.03679281, -0.008987327, -0.0015111889, 0.0951955, -0.047756936, 0.03215895, 0.0029104433, -0.026967648, 0.015690766, 0.072443135, 0.039804243, 0.019212538, 0.08688796, -0.006074699, 0.015716698, 0.01919827, 0.030602958, 0.008902454, -0.046521842, 0.01976686, 0.051571846, 0.022742877, -0.04307271, -0.016526582, -0.03293306, 0.056195326, 0.0034229455, 0.022546848, -0.03803692, -0.051709678, 0.006613695, -0.0014020284, -0.036669895, -0.001721542, -0.08655083, -0.052215993, -0.032110028, 0.02565277, 0.04519586, -0.049954705, 0.0012014605, -0.037857044, -0.017148033, -0.026822135, 0.031737078, 0.028569039, -0.022907747, 0.024690803, -0.029206393, -0.032036074, 0.039650604, 0.021772616, -0.021436188, 0.045968816, -0.010048652, 0.030124044, 0.03935015, -0.04809066, 0.023686275, 0.02167442, 0.044297505, -0.073465124, -0.030082388, 0.017143175, -0.03342189, -0.0330694, -0.0122910105, -0.051963367, -0.058639623, -0.008972449, -0.022521269, -0.022892935, -0.035436112, 0.0034948539, -0.005295366, 0.05993406, 0.027561562, -0.010693112, 0.0009929353, -0.08425568, -0.02769792, -0.061596338, 0.036154557, -0.037945468, -0.03125497, -0.030945951, 0.04039234, 0.06636523, 0.016889103, -0.003046984, -0.011618148, 0.0011459244, 0.08574449, 0.036592126, -0.051252075, 0.013240978, -0.004678898, 0.0855428, -0.009402003, 0.028451374, -0.020148227, 0.0028894239, -0.02822095, 0.0315999, -0.057231728, 0.0004925584, -0.019411521, 0.021964703, 0.009169671, 0.01635917, -0.035817493, 0.052273333, -0.0009408905, 0.018396556, -0.041456044, 0.019532038, -0.0034153357, -0.034743972, 0.0027093922, 0.00044865624, 0.0023108325, -0.04501131, 0.05044232, -0.034571823, -0.039061558, 0.008809692, 0.068560965, 0.015274846, 0.023746625, 0.043649375, -0.028320875, -0.009765932, -0.009430268, -0.055888545, 0.047219332, 0.023080856, 0.064999744, -0.039562706, 0.0501819, 0.046483964, -0.009398194, -0.0013862611, 0.014837316, 0.045558825, 0.016926765, 0.03220044, 0.003780334, 0.040371794, 0.00057833333, -0.04805651, 0.01602842, -0.005916167, -0.0020399855, 0.036410075, -0.09505558, -0.021768136, 0.021421269, 0.024159726, -0.013026249, -0.023113504, 0.02459358, 0.01643742, -0.0104496805, 0.033115752, 0.047128692, 0.05519812, -0.013151745, 0.03202098, 0.0014973703, -0.009810199, 0.09950044, 0.03161514, 0.022533545, 0.028800217, 0.011425177, -0.06616128, 0.018490529, -0.024615118, -0.01714155, -0.036444064, -0.024078121, 6.236274e-05, -0.025733253, -0.012052791, -0.0032004463, -0.007022415, -0.07943268, -0.010401283, 0.014510383, -0.017218677, 0.056253612, -0.028017681, -0.06288073, -0.0010291388, 0.042233694, -0.017423663, -0.014384363, 0.008450004, -0.006025767, 0.00068278343, 0.043332722, -0.048530027, -0.10272868, 0.016439026, -0.0043581687, 0.014065921, 0.015250153, 0.0035983857, 0.024789328, 0.052941743, 0.0023809967, -0.0041563907, -0.02350335, -0.05152261, -0.026173577, 0.025396436, -0.020441707, 0.0052804356, 0.017074147, -0.023429962, 0.028667469, -0.056579348, -0.045674913, -0.050122924, -0.029717976, 0.011392094, 0.01918305, -0.090463236, 0.011211278, -0.058831867, -0.027594091, -0.08303421, -0.014075257, -0.013071177, 0.0050326143, 0.024727797, -0.004616583, -0.007565293, 0.0043535405, -0.05543633, -0.022187654, -0.026209656, 0.064442314, -0.0066669765, -0.002169784, -0.019930722, 4.8227314e-05, -0.0015547068, -0.0057820054, -0.08949447, -0.0115463175, -0.026195917, -0.008628893, -0.0017553791, -0.08588936, 0.008043627, -0.040522296, -0.006249298, -0.040554754, 0.021548215, 0.049422685, -0.008809529, -0.024933426, -0.040077355, 0.038274486, 0.029687686, -0.02959238, 0.0426982, 0.029072417, 0.049369767, -0.018109215, -0.041628513, -0.005594527, 0.026668772, -0.027726736, 0.037220005, 0.058132544, 0.01863369, -0.04707943, -0.0006536238, -0.012569923, 0.01520091, 0.05510794, -0.05035494, 0.036055118, -0.020710817, -0.0051193447, -0.042542584, 0.0020174137, 0.0014168078, -0.001090868, -0.034683146, 0.06309216, -0.05918888, 0.017469395, 0.025378557, 0.046790935, 0.008669848, 0.07935556, -0.016844809, -0.08596125, -0.037868172, 0.0057407417, -0.04262457, 0.0036744277, -0.04798243, 0.010448024, 0.005311227, -0.025689157, 0.051566023, -0.053452246, -0.033347856, -0.014070289, -0.001457106, 0.056622982, -0.037253298, -0.0010763579, 0.025846632, -0.017852046, -0.035092466, 0.0293208, 0.035001587, -0.002458465, -0.0032884434, -0.011247537, -0.03308368, 0.027546775, -0.0197189, -0.019373588, 0.012695445, -0.00846602, 0.0006254506, 0.022446852, -0.021224227, -0.016343568, -0.008488644, 0.009065775, -0.0038449552, -0.036945608, 0.035750583, 0.0021798566, 0.007781292, 0.07929656, -0.017595762, -0.020934578, -0.03354823, 0.04495828, -0.008365722, -0.040300835, 0.0006642716, 0.0568309, 0.016416628, 0.0722137, -0.01774583, -0.0492021, -0.0020490142, -0.049469862, 0.043543257, 0.04398881, 0.025031362, -0.0063477345, 0.062346347, -0.040481493, -0.02257938, 0.009280532, 0.010731656, 0.02230327, 0.002849086, -0.05473455, 0.047677275, -0.02363733, 0.029837264, -0.020835804, -0.017142115, 0.006764067, -0.01684698, 0.021653073, 0.040238675, -0.018611673, -0.04561582, 0.038430944, -0.02677326, 0.007663415, 0.06948015, -0.0012032362, 0.008699309, 0.011357286, 0.021917833, 0.00018160013, -0.076829135, 0.0023802964, -0.023293033, -0.03534673, -0.042327877, -0.0210994, 0.042625647, -0.014360755, -0.0066886684, 0.03561479, 0.047778953, 0.037118394, 0.041420408, 0.052272875, 0.039208084, -0.033506226, -0.00651392, 0.062439967, 0.03669325, 0.042872086, 0.066822834, -0.0068043126, -0.021161819, -0.050757803, 0.005068388, -0.0027463334, 0.013415453, -0.033819556, -0.046399325, -0.03287996, -0.019854786, -0.0070042396, -0.00042829785, -0.036087025, -0.00650163, 0.0008774728, -0.10458266, -0.061043933, 0.016721264, 0.0002953045, -0.0053018867, 0.012741255, 0.0050292304, 0.024298942, 0.0033208653, -0.0629338, -0.0005545099, 0.04004244, -0.03548021, -0.02479493, 0.035712432, -0.017079322, -0.030503469, 0.0019789268, -0.028768733, -0.054890547, -0.08133776, -0.03006806, -0.016685534, -0.073403284, 0.05233739, 0.033545494, 0.0035976092, 0.040786255, 0.056786384, 0.013151219, 0.042795595, 0.009594162, 0.00945792, 0.024018744, -0.045365516, -0.050492898, 0.038503986, 0.012790262, 0.0142914, 0.014998696, 0.0071202153, -0.0038871064, 0.010770397, 0.016789515, -0.041323792, 0.010311674, -0.009053558, 0.034749016, 0.005213924, -0.041184388, -0.0033388685, 0.04279652, 0.04068113, -0.024129236, -0.0059263078, 0.027970677, -0.024706231, 0.02846046, -0.0011169978, -0.059880134, 0.02713591, -0.0027713599, 0.040187914, 0.035978075, -0.06281134, -0.08345513, -0.006073032, -0.02095529, -0.018988023, -0.035680003, 0.04972727, -0.009011115, 0.054317664, 0.005172075, 0.031131523, -0.00069823023, 0.0108121475, -0.06091403, 0.049459387, -0.007036548, -0.014955144, -0.02104843, 0.035405546, 0.043375615, -0.042294793, -0.025417345, -0.015245514, 0.023398506, 0.002263163, -0.0071430253, 0.043531902, -0.03357511, -0.09097121, -0.04729407, -0.013593756, 0.023449646, 0.039015424, 0.027113337, -0.05169247, -0.016909705, -0.0057588373, -0.009955609, -0.05562937, -0.052671663, 0.003173363, -0.0022836009, 0.036742315, 0.047324646, -0.033285677, 0.012819869, -0.01939692, -0.0047737034, -0.011794656, -0.045633573, -0.0013346534, 0.016130142, -0.066292875, 0.029637614, 0.057662483, -0.035122138, 0.068166904]}

Créer une base de données de représentations vectorielles continues

Voici trois exemples de texte à utiliser pour créer la base de données de représentations vectorielles continues. Vous allez utiliser l'API Gemini pour créer des représentations vectorielles continues de chacun des documents. Transformez-les en une trame de données pour une meilleure visualisation.

DOCUMENT1 = {
    "title": "Operating the Climate Control System",
    "content": "Your Googlecar has a climate control system that allows you to adjust the temperature and airflow in the car. To operate the climate control system, use the buttons and knobs located on the center console.  Temperature: The temperature knob controls the temperature inside the car. Turn the knob clockwise to increase the temperature or counterclockwise to decrease the temperature. Airflow: The airflow knob controls the amount of airflow inside the car. Turn the knob clockwise to increase the airflow or counterclockwise to decrease the airflow. Fan speed: The fan speed knob controls the speed of the fan. Turn the knob clockwise to increase the fan speed or counterclockwise to decrease the fan speed. Mode: The mode button allows you to select the desired mode. The available modes are: Auto: The car will automatically adjust the temperature and airflow to maintain a comfortable level. Cool: The car will blow cool air into the car. Heat: The car will blow warm air into the car. Defrost: The car will blow warm air onto the windshield to defrost it."}
DOCUMENT2 = {
    "title": "Touchscreen",
    "content": "Your Googlecar has a large touchscreen display that provides access to a variety of features, including navigation, entertainment, and climate control. To use the touchscreen display, simply touch the desired icon.  For example, you can touch the \"Navigation\" icon to get directions to your destination or touch the \"Music\" icon to play your favorite songs."}
DOCUMENT3 = {
    "title": "Shifting Gears",
    "content": "Your Googlecar has an automatic transmission. To shift gears, simply move the shift lever to the desired position.  Park: This position is used when you are parked. The wheels are locked and the car cannot move. Reverse: This position is used to back up. Neutral: This position is used when you are stopped at a light or in traffic. The car is not in gear and will not move unless you press the gas pedal. Drive: This position is used to drive forward. Low: This position is used for driving in snow or other slippery conditions."}

documents = [DOCUMENT1, DOCUMENT2, DOCUMENT3]

Organiser le contenu du dictionnaire dans une trame de données pour une meilleure visualisation.

df = pd.DataFrame(documents)
df.columns = ['Title', 'Text']
df

Obtenez les représentations vectorielles continues de chacun de ces corps de texte. Ajoutez ces informations au DataFrame.

# Get the embeddings of each text and add to an embeddings column in the dataframe
def embed_fn(title, text):
  return genai.embed_content(model=model,
                             content=text,
                             task_type="retrieval_document",
                             title=title)["embedding"]

df['Embeddings'] = df.apply(lambda row: embed_fn(row['Title'], row['Text']), axis=1)
df

Recherche de documents avec questions/réponses

Maintenant que les représentations vectorielles continues ont été générées, créons un système de questions/réponses pour effectuer des recherches dans ces documents. Vous poserez une question sur le réglage des hyperparamètres, créerez une représentation vectorielle continue de la question et la comparerez à l'ensemble de représentations vectorielles continues dans le DataFrame.

La représentation vectorielle continue de la question sera un vecteur (liste de valeurs flottantes), qui sera comparé au vecteur des documents à l'aide du produit scalaire. Ce vecteur renvoyé par l'API est déjà normalisé. Le produit scalaire représente la similarité de direction entre deux vecteurs.

Les valeurs du produit scalaire peuvent être comprises entre -1 et 1 inclus. Si le produit scalaire entre deux vecteurs est égal à 1, cela signifie que les vecteurs sont dans la même direction. Si la valeur du produit scalaire est de 0, ces vecteurs sont orthogonaux ou sans rapport les uns avec les autres. Enfin, si le produit scalaire est égal à -1, les vecteurs pointent dans la direction opposée et ne sont pas similaires.

Avec le nouveau modèle de représentations vectorielles continues (embedding-001), spécifiez le type de tâche QUERY pour la requête utilisateur et DOCUMENT pour l'intégration du texte d'un document.

query = "How do you shift gears in the Google car?"
model = 'models/embedding-001'

request = genai.embed_content(model=model,
                              content=query,
                              task_type="retrieval_query")

Utilisez la fonction find_best_passage pour calculer les produits scalaires, puis triez le DataFrame de la plus grande à la plus petite valeur de produit scalaire pour récupérer le passage approprié de la base de données.

def find_best_passage(query, dataframe):
  """
  Compute the distances between the query and each document in the dataframe
  using the dot product.
  """
  query_embedding = genai.embed_content(model=model,
                                        content=query,
                                        task_type="retrieval_query")
  dot_products = np.dot(np.stack(dataframe['Embeddings']), query_embedding["embedding"])
  idx = np.argmax(dot_products)
  return dataframe.iloc[idx]['Text'] # Return text from index with max value

Affichez le document le plus pertinent de la base de données:

passage = find_best_passage(query, df)
passage

'Shifting Gears  Your Googlecar has an automatic transmission. To shift gears, simply move the shift lever to the desired position.  Park: This position is used when you are parked. The wheels are locked and the car cannot move. Reverse: This position is used to back up. Neutral: This position is used when you are stopped at a light or in traffic. The car is not in gear and will not move unless you press the gas pedal. Drive: This position is used to drive forward. Low: This position is used for driving in snow or other slippery conditions.'

Application de questions-réponses

Essayons d'utiliser l'API de génération de texte pour créer une session Un système. Saisissez vos propres données personnalisées ci-dessous pour créer une question simple et un exemple de réponse. Vous utiliserez toujours le produit scalaire comme métrique de similarité.

def make_prompt(query, relevant_passage):
  escaped = relevant_passage.replace("'", "").replace('"', "").replace("\n", " ")
  prompt = textwrap.dedent("""You are a helpful and informative bot that answers questions using text from the reference passage included below. \
  Be sure to respond in a complete sentence, being comprehensive, including all relevant background information. \
  However, you are talking to a non-technical audience, so be sure to break down complicated concepts and \
  strike a friendly and converstional tone. \
  If the passage is irrelevant to the answer, you may ignore it.
  QUESTION: '{query}'
  PASSAGE: '{relevant_passage}'

    ANSWER:
  """).format(query=query, relevant_passage=escaped)

  return prompt

prompt = make_prompt(query, passage)
print(prompt)

You are a helpful and informative bot that answers questions using text from the reference passage included below.   Be sure to respond in a complete sentence, being comprehensive, including all relevant background information.   However, you are talking to a non-technical audience, so be sure to break down complicated concepts and   strike a friendly and converstional tone.   If the passage is irrelevant to the answer, you may ignore it.
  QUESTION: 'How do you shift gears in the Google car?'
  PASSAGE: 'Shifting Gears  Your Googlecar has an automatic transmission. To shift gears, simply move the shift lever to the desired position.  Park: This position is used when you are parked. The wheels are locked and the car cannot move. Reverse: This position is used to back up. Neutral: This position is used when you are stopped at a light or in traffic. The car is not in gear and will not move unless you press the gas pedal. Drive: This position is used to drive forward. Low: This position is used for driving in snow or other slippery conditions.'

    ANSWER:

Choisissez l'un des modèles de génération de contenu Gemini pour trouver la réponse à votre requête.

for m in genai.list_models():
  if 'generateContent' in m.supported_generation_methods:
    print(m.name)

models/gemini-pro
models/gemini-ultra

model = genai.GenerativeModel('gemini-1.5-pro-latest')
answer = model.generate_content(prompt)

Markdown(answer.text)

Le passage fourni ne contient pas d'informations sur la marche à suivre pour changer de vitesse dans une voiture Google. Je ne peux donc pas répondre à votre question à partir de cette source.

Étapes suivantes

Pour en savoir plus sur l'utilisation des représentations vectorielles continues, consultez les tutoriels suivants:

• Détection d'anomalies à l'aide de représentations vectorielles continues
• Clustering avec des représentations vectorielles continues
• Entraîner un classificateur de texte avec des représentations vectorielles continues