nightfury commited on
Commit
df9ff7b
·
verified ·
1 Parent(s): 2b33362

Update appChatbot.py

Browse files
Files changed (1) hide show
  1. appChatbot.py +9 -7
appChatbot.py CHANGED
@@ -6,8 +6,9 @@ import sys
6
  import gradio as gr
7
  from huggingface_hub import InferenceClient
8
 
 
9
  #from chromadb.utils import embedding_functions
10
- from langchain_community.embeddings import SentenceTransformerEmbeddings
11
 
12
  from langchain.text_splitter import CharacterTextSplitter
13
  from langchain.embeddings import OpenAIEmbeddings
@@ -20,6 +21,13 @@ For more information on `huggingface_hub` Inference API support, please check th
20
  """
21
  client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
22
 
 
 
 
 
 
 
 
23
  ABS_PATH = os.path.dirname(os.path.abspath(__file__))
24
  DB_DIR = os.path.join(ABS_PATH, "db")
25
 
@@ -50,9 +58,6 @@ def init_chromadb():
50
  # Split the documents into chunks
51
  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
52
  texts = text_splitter.split_documents(documents)
53
- # Select which embeddings we want to use
54
- #embeddings = OpenAIEmbeddings()
55
- embeddings = SentenceTransformerEmbeddings(model_name="nomic-ai/nomic-embed-text-v1", model_kwargs={"trust_remote_code":True})
56
  #query_chromadb()
57
 
58
  # Create the vectorestore to use as the index
@@ -65,9 +70,6 @@ def query_chromadb(ASK):
65
  if not os.path.exists(DB_DIR):
66
  raise Exception(f"{DB_DIR} does not exist, nothing can be queried")
67
 
68
- # Select which embeddings we want to use
69
- #embeddings = OpenAIEmbeddings()
70
- embeddings = SentenceTransformerEmbeddings(model_name="nomic-ai/nomic-embed-text-v1", model_kwargs={"trust_remote_code":True})
71
  # Load Vector store from local disk
72
  vectorstore = Chroma(persist_directory=DB_DIR, embedding_function=embeddings)
73
 
 
6
  import gradio as gr
7
  from huggingface_hub import InferenceClient
8
 
9
+ from langchain_huggingface import HuggingFaceEmbeddings
10
  #from chromadb.utils import embedding_functions
11
+ #from langchain_community.embeddings import SentenceTransformerEmbeddings
12
 
13
  from langchain.text_splitter import CharacterTextSplitter
14
  from langchain.embeddings import OpenAIEmbeddings
 
21
  """
22
  client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
23
 
24
+ # Select which embeddings we want to use
25
+ #embeddings = OpenAIEmbeddings()
26
+ #embeddings = SentenceTransformerEmbeddings(model_name="nomic-ai/nomic-embed-text-v1", model_kwargs={"trust_remote_code":True})
27
+
28
+ embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
29
+
30
+
31
  ABS_PATH = os.path.dirname(os.path.abspath(__file__))
32
  DB_DIR = os.path.join(ABS_PATH, "db")
33
 
 
58
  # Split the documents into chunks
59
  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
60
  texts = text_splitter.split_documents(documents)
 
 
 
61
  #query_chromadb()
62
 
63
  # Create the vectorestore to use as the index
 
70
  if not os.path.exists(DB_DIR):
71
  raise Exception(f"{DB_DIR} does not exist, nothing can be queried")
72
 
 
 
 
73
  # Load Vector store from local disk
74
  vectorstore = Chroma(persist_directory=DB_DIR, embedding_function=embeddings)
75