Spaces:
Sleeping
Sleeping
Commit
·
ee043ca
1
Parent(s):
b12ca56
Update app.py
Browse files
app.py
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
from datetime import date, timedelta
|
2 |
from langchain.document_loaders import ArxivLoader
|
3 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
4 |
-
from langchain.vectorstores import
|
5 |
from langchain.embeddings import HuggingFaceEmbeddings
|
6 |
|
7 |
def get_data(user_query: str, load_max_docs: int = 5, chunk_size: int=1000):
|
@@ -13,7 +13,7 @@ def get_data(user_query: str, load_max_docs: int = 5, chunk_size: int=1000):
|
|
13 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size)
|
14 |
texts = text_splitter.split_documents(documents)
|
15 |
embeddings = HuggingFaceEmbeddings()
|
16 |
-
db =
|
17 |
retriever = db.as_retriever()
|
18 |
docs = retriever.get_relevant_documents(user_query)
|
19 |
print(docs[0].metadata)
|
|
|
1 |
from datetime import date, timedelta
|
2 |
from langchain.document_loaders import ArxivLoader
|
3 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
4 |
+
from langchain.vectorstores import Chroma
|
5 |
from langchain.embeddings import HuggingFaceEmbeddings
|
6 |
|
7 |
def get_data(user_query: str, load_max_docs: int = 5, chunk_size: int=1000):
|
|
|
13 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size)
|
14 |
texts = text_splitter.split_documents(documents)
|
15 |
embeddings = HuggingFaceEmbeddings()
|
16 |
+
db = Chroma.from_documents(texts, embeddings)
|
17 |
retriever = db.as_retriever()
|
18 |
docs = retriever.get_relevant_documents(user_query)
|
19 |
print(docs[0].metadata)
|