bupa1018 commited on
Commit
ebd0b92
·
1 Parent(s): c606b41

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +7 -44
app.py CHANGED
@@ -5,69 +5,33 @@ import streamlit as st
5
  from huggingface_hub import HfApi, login
6
  from dotenv import load_dotenv
7
 
8
- from download_repo import download_gitlab_repo_to_hfspace
9
- from process_repo import extract_repo_files
10
- from chunking import chunk_pythoncode_and_add_metadata, chunk_text_and_add_metadata
11
- from vectorstore import setup_vectorstore
12
  from llm import get_groq_llm
13
  from vectorstore import get_chroma_vectorstore
14
  from embeddings import get_SFR_Code_embedding_model
15
  from kadi_apy_bot import KadiAPYBot
16
- from repo_versions import store_message_from_json
17
 
18
  # Load environment variables from .env file
19
  load_dotenv()
20
 
21
- # Load configuration from JSON file
22
-
23
- with open("config.json", "r") as file:
24
- config = json.load(file)
25
 
26
  GROQ_API_KEY = os.environ["GROQ_API_KEY"]
27
  HF_TOKEN = os.environ["HF_Token"]
28
 
29
-
30
- VECTORSTORE_DIRECTORY = config["vectorstore_directory"]
31
- CHUNK_SIZE = config["chunking"]["chunk_size"]
32
- CHUNK_OVERLAP = config["chunking"]["chunk_overlap"]
33
-
34
- EMBEDDING_MODEL_NAME = config["embedding_model"]["name"]
35
- EMBEDDING_MODEL_VERSION = config["embedding_model"]["version"]
36
-
37
- LLM_MODEL_NAME = config["llm_model"]["name"]
38
- LLM_MODEL_TEMPERATURE = config["llm_model"]["temperature"]
39
-
40
- GITLAB_API_URL = config["gitlab"]["api_url"]
41
- GITLAB_PROJECT_ID = config["gitlab"]["project id"]
42
- GITLAB_PROJECT_VERSION = config["gitlab"]["project version"]
43
-
44
- DATA_DIR = config["data_dir"]
45
- HF_SPACE_NAME = config["hf_space_name"]
46
 
47
  login(HF_TOKEN)
48
  hf_api = HfApi()
49
 
 
 
 
50
 
51
  def initialize():
52
  global kadiAPY_bot
53
 
54
-
55
-
56
- # download_gitlab_repo_to_hfspace(GITLAB_API_URL, GITLAB_PROJECT_ID, GITLAB_PROJECT_VERSION, DATA_DIR, hf_api, HF_SPACE_NAME)
57
-
58
- # code_texts, code_references = extract_repo_files(DATA_DIR, ['kadi_apy'], [])
59
- # doc_texts, doc_references = extract_repo_files(DATA_DIR, ['docs'], [])
60
-
61
- # print("Length of code_texts: ", len(code_texts))
62
- # print("Length of doc_files: ", len(doc_texts))
63
-
64
- # code_chunks = chunk_pythoncode_and_add_metadata(code_texts, code_references)
65
- # doc_chunks = chunk_text_and_add_metadata(doc_texts, doc_references, CHUNK_SIZE, CHUNK_OVERLAP)
66
-
67
- # print(f"Total number of code_chunks: {len(code_chunks)}")
68
- # print(f"Total number of doc_chunks: {len(doc_chunks)}")
69
-
70
- vectorstore = get_chroma_vectorstore(get_SFR_Code_embedding_model(), "data/vectorstore")
71
  llm = get_groq_llm(LLM_MODEL_NAME, LLM_MODEL_TEMPERATURE, GROQ_API_KEY)
72
 
73
  kadiAPY_bot = KadiAPYBot(llm, vectorstore)
@@ -75,7 +39,6 @@ def initialize():
75
  initialize()
76
 
77
 
78
-
79
  def bot_kadi(history):
80
  user_query = history[-1][0]
81
  response = kadiAPY_bot.process_query(user_query)
 
5
  from huggingface_hub import HfApi, login
6
  from dotenv import load_dotenv
7
 
 
 
 
 
8
  from llm import get_groq_llm
9
  from vectorstore import get_chroma_vectorstore
10
  from embeddings import get_SFR_Code_embedding_model
11
  from kadi_apy_bot import KadiAPYBot
 
12
 
13
  # Load environment variables from .env file
14
  load_dotenv()
15
 
16
+ vectorstore_path = "data/vectorstore"
 
 
 
17
 
18
  GROQ_API_KEY = os.environ["GROQ_API_KEY"]
19
  HF_TOKEN = os.environ["HF_Token"]
20
 
21
+ with open("config.json", "r") as file:
22
+ config = json.load(file)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
 
24
  login(HF_TOKEN)
25
  hf_api = HfApi()
26
 
27
+ # Access the values
28
+ LLM_MODEL_NAME = config["llm_model_name"]
29
+ LLM_MODEL_TEMPERATURE = float(config["llm_model_temperature"])
30
 
31
  def initialize():
32
  global kadiAPY_bot
33
 
34
+ vectorstore = get_chroma_vectorstore(get_SFR_Code_embedding_model(), vectorstore_path)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  llm = get_groq_llm(LLM_MODEL_NAME, LLM_MODEL_TEMPERATURE, GROQ_API_KEY)
36
 
37
  kadiAPY_bot = KadiAPYBot(llm, vectorstore)
 
39
  initialize()
40
 
41
 
 
42
  def bot_kadi(history):
43
  user_query = history[-1][0]
44
  response = kadiAPY_bot.process_query(user_query)