File size: 2,360 Bytes
06e8209 df9d7da 06e8209 df9d7da 06e8209 |
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 |
import json
import logging
import os
import re
import chromadb
from pydantic.v1 import BaseSettings
from dotenv import load_dotenv
from fastapi.encoders import jsonable_encoder
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
load_dotenv()
logging.basicConfig(level=logging.DEBUG)
ABS_PATH = os.path.dirname(os.path.abspath(__file__))
DB_DIR = os.path.join(ABS_PATH, "db")
def replace_newlines_and_spaces(text):
# Replace all newline characters with spaces
text = text.replace("\n", " ")
# Replace multiple spaces with a single space
text = re.sub(r'\s+', ' ', text)
return text
def get_documents():
return PyPDFLoader("fixtures/pdf/MorseVsFrederick.pdf").load()
def init_chromadb():
if not os.path.exists(DB_DIR):
os.mkdir(DB_DIR)
client_settings = chromadb.config.Settings(
chroma_db_impl="duckdb+parquet",
persist_directory=DB_DIR,
anonymized_telemetry=False
)
embeddings = OpenAIEmbeddings()
vectorstore = Chroma(
collection_name="langchain_store",
embedding_function=embeddings,
client_settings=client_settings,
persist_directory=DB_DIR,
)
documents = []
for num, doc in enumerate(get_documents()):
doc.page_content = replace_newlines_and_spaces(doc.page_content)
documents.append(doc)
vectorstore.add_documents(documents=documents, embedding=embeddings)
vectorstore.persist()
print(vectorstore)
def query_chromadb():
if not os.path.exists(DB_DIR):
raise Exception(f"{DB_DIR} does not exist, nothing can be queried")
client_settings = chromadb.config.Settings(
chroma_db_impl="duckdb+parquet",
persist_directory=DB_DIR,
anonymized_telemetry=False
)
embeddings = OpenAIEmbeddings()
vectorstore = Chroma(
collection_name="langchain_store",
embedding_function=embeddings,
client_settings=client_settings,
persist_directory=DB_DIR,
)
result = vectorstore.similarity_search_with_score(query="who is FREDERICK?", k=4)
jsonable_result = jsonable_encoder(result)
print(json.dumps(jsonable_result, indent=2))
def main():
init_chromadb()
query_chromadb()
if __name__ == '__main__':
main() |