Spaces:
Running
Running
File size: 4,764 Bytes
0e5c934 d4296c2 0e5c934 66c82c6 0e5c934 d4296c2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
import requests
from pymongo import MongoClient
def google_search(query, api_key, cx):
url = f"https://www.googleapis.com/customsearch/v1?q={query}&key={api_key}&cx={cx}"
response = requests.get(url)
if response.status_code == 200:
search_results = response.json()
print(search_results)
return search_results
else:
print(f"Error: {response.status_code}")
return None
def generate_embedding_for_user_resume(data,user_id):
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
def get_embedding(data, precision="float32"):
return model.encode(data, precision=precision)
from pinecone import Vector
def create_docs_with_vector_embeddings(bson_float32, data):
docs = []
for i, (bson_f32_emb, text) in enumerate(zip(bson_float32, data)):
doc =Vector(
id=f"{i}",
values= bson_f32_emb.tolist(),
metadata={"text":text,"user_id":user_id},
)
docs.append(doc)
return docs
float32_embeddings = get_embedding(data, "float32")
docs = create_docs_with_vector_embeddings(float32_embeddings, data)
return docs
def insert_embeddings_into_pinecone_database(doc,api_key,name_space):
from pinecone import Pinecone
pc = Pinecone(api_key=api_key)
index_name = "resumes"
index = pc.Index(index_name)
upsert_response = index.upsert(namespace=name_space,vectors=doc)
return upsert_response
def query_vector_database(query,api_key,name_space):
from pinecone import Pinecone
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
ret=[]
pc = Pinecone(api_key=api_key)
index_name = "resumes"
index = pc.Index(index_name)
# Define a function to generate embeddings in multiple precisions
def get_embedding(data, precision="float32"):
return model.encode(data, precision=precision)
query_embedding = get_embedding(query, precision="float32")
response = index.query(
namespace=name_space,
vector=query_embedding.tolist(),
top_k=3,
include_metadata=True
)
for doc in response['matches']:
ret.append(doc['metadata']['text'])
return ret
def delete_vector_namespace(name_space,api_key):
from pinecone import Pinecone
pc = Pinecone(api_key=api_key)
index_name = "resumes"
index = pc.Index(index_name)
response = index.delete(delete_all=True,namespace=name_space)
return response
def split_text_into_chunks(text, chunk_size=400):
# Split the text into words using whitespace.
words = text.split()
# Group the words into chunks of size 'chunk_size'.
chunks = [' '.join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
return chunks
def create_user(db_uri: str, db_name: str, collection_name: str, document: dict) -> str:
"""
Inserts a new document into the specified MongoDB collection.
Parameters:
db_uri (str): MongoDB connection URI.
db_name (str): Name of the database.
collection_name (str): Name of the collection.
document (dict): The document to insert.
Returns:
str: The ID of the inserted document.
"""
# Connect to MongoDB
client = MongoClient(db_uri)
db = client[db_name]
collection = db[collection_name]
# Insert the document
s = collection.find_one(document)
if s==None:
result = collection.insert_one(document)
client.close()
return str(result.inserted_id)
else:
client.close()
return str(s['_id'])
# Close the connection
def login_user(db_uri: str, db_name: str, collection_name: str, document: dict) -> str:
"""
Inserts a new document into the specified MongoDB collection.
Parameters:
db_uri (str): MongoDB connection URI.
db_name (str): Name of the database.
collection_name (str): Name of the collection.
document (dict): The document to insert.
Returns:
str: The ID of the inserted document.
"""
# Connect to MongoDB
client = MongoClient(db_uri)
db = client[db_name]
collection = db[collection_name]
# Insert the document
s = collection.find_one(document)
if s==None:
return False
else:
if document['password']==s['password']:
client.close()
return str(s['_id'])
else:
return True
# Close the connection
|