Spaces:
Sleeping
Sleeping
Harshana
commited on
Commit
·
0e197ca
1
Parent(s):
efa9c6c
add .gitignore and aet env for HF
Browse files- .env +2 -2
- .gitignore +115 -0
- retrievers/custom_retriever.py +27 -13
.env
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
LLM_PROVIDER=groq
|
2 |
-
SUPABASE_URL=https://
|
3 |
-
SUPABASE_SERVICE_KEY=
|
4 |
SYSTEM_PROMPT_PATH=system_prompt.txt
|
|
|
1 |
LLM_PROVIDER=groq
|
2 |
+
SUPABASE_URL=https://omwpqmtzmybojocamzvn.supabase.co
|
3 |
+
SUPABASE_SERVICE_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Im9td3BxbXR6bXlib2pvY2FtenZuIiwicm9sZSI6InNlcnZpY2Vfcm9sZSIsImlhdCI6MTc0NzU2MjMwOSwiZXhwIjoyMDYzMTM4MzA5fQ.OuvoIHTPW0PR1TWLDvSdSjGrIGM-cbyRZi1uJSH-T6A
|
4 |
SYSTEM_PROMPT_PATH=system_prompt.txt
|
.gitignore
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Byte-compiled / optimized / DLL files
|
2 |
+
__pycache__/
|
3 |
+
*.py[cod]
|
4 |
+
*$py.class
|
5 |
+
*.so
|
6 |
+
|
7 |
+
# Distribution / packaging
|
8 |
+
.Python
|
9 |
+
build/
|
10 |
+
develop-eggs/
|
11 |
+
dist/
|
12 |
+
downloads/
|
13 |
+
eggs/
|
14 |
+
.eggs/
|
15 |
+
lib/
|
16 |
+
lib64/
|
17 |
+
parts/
|
18 |
+
sdist/
|
19 |
+
var/
|
20 |
+
wheels/
|
21 |
+
*.egg-info/
|
22 |
+
.installed.cfg
|
23 |
+
*.egg
|
24 |
+
|
25 |
+
# Virtual environments
|
26 |
+
venv/
|
27 |
+
ENV/
|
28 |
+
env/
|
29 |
+
.env
|
30 |
+
.venv
|
31 |
+
env.bak/
|
32 |
+
venv.bak/
|
33 |
+
.python-version
|
34 |
+
|
35 |
+
# Unit test / coverage reports
|
36 |
+
htmlcov/
|
37 |
+
.tox/
|
38 |
+
.nox/
|
39 |
+
.coverage
|
40 |
+
.coverage.*
|
41 |
+
.cache
|
42 |
+
nosetests.xml
|
43 |
+
coverage.xml
|
44 |
+
*.cover
|
45 |
+
.hypothesis/
|
46 |
+
.pytest_cache/
|
47 |
+
pytest-*.xml
|
48 |
+
|
49 |
+
# Jupyter Notebook
|
50 |
+
.ipynb_checkpoints
|
51 |
+
|
52 |
+
# IPython
|
53 |
+
profile_default/
|
54 |
+
ipython_config.py
|
55 |
+
|
56 |
+
# Logs
|
57 |
+
*.log
|
58 |
+
logs/
|
59 |
+
log/
|
60 |
+
|
61 |
+
# IDE specific files
|
62 |
+
.idea/
|
63 |
+
.vscode/
|
64 |
+
*.swp
|
65 |
+
*.swo
|
66 |
+
*~
|
67 |
+
.DS_Store
|
68 |
+
.project
|
69 |
+
.pydevproject
|
70 |
+
.settings/
|
71 |
+
.vs/
|
72 |
+
*.sublime-project
|
73 |
+
*.sublime-workspace
|
74 |
+
|
75 |
+
# Database
|
76 |
+
*.db
|
77 |
+
*.rdb
|
78 |
+
*.sqlite
|
79 |
+
*.sqlite3
|
80 |
+
|
81 |
+
# Environment variables
|
82 |
+
.env
|
83 |
+
.env.local
|
84 |
+
.env.development.local
|
85 |
+
.env.test.local
|
86 |
+
.env.production.local
|
87 |
+
|
88 |
+
# macOS specific
|
89 |
+
.DS_Store
|
90 |
+
.AppleDouble
|
91 |
+
.LSOverride
|
92 |
+
Icon
|
93 |
+
._*
|
94 |
+
.DocumentRevisions-V100
|
95 |
+
.fseventsd
|
96 |
+
.Spotlight-V100
|
97 |
+
.TemporaryItems
|
98 |
+
.Trashes
|
99 |
+
.VolumeIcon.icns
|
100 |
+
.com.apple.timemachine.donotpresent
|
101 |
+
|
102 |
+
# AI/model files
|
103 |
+
*.h5
|
104 |
+
*.pb
|
105 |
+
*.onnx
|
106 |
+
*.tflite
|
107 |
+
*.pt
|
108 |
+
*.pth
|
109 |
+
*.weights
|
110 |
+
|
111 |
+
# Temporary files
|
112 |
+
tmp/
|
113 |
+
temp/
|
114 |
+
.tmp
|
115 |
+
*.tmp
|
retrievers/custom_retriever.py
CHANGED
@@ -1,21 +1,35 @@
|
|
|
|
|
|
1 |
import os
|
2 |
from langchain_huggingface import HuggingFaceEmbeddings
|
3 |
from langchain_community.vectorstores import SupabaseVectorStore
|
4 |
from supabase.client import create_client
|
5 |
from config import settings
|
6 |
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
def retrieve(query: str) -> str:
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
|
|
|
|
|
|
|
|
|
1 |
+
# retrievers/custom_retriever.py
|
2 |
+
|
3 |
import os
|
4 |
from langchain_huggingface import HuggingFaceEmbeddings
|
5 |
from langchain_community.vectorstores import SupabaseVectorStore
|
6 |
from supabase.client import create_client
|
7 |
from config import settings
|
8 |
|
9 |
+
def get_vector_store():
|
10 |
+
# Read env variables only when needed
|
11 |
+
supabase_url = settings.supabase_url
|
12 |
+
supabase_key = settings.supabase_key
|
13 |
+
|
14 |
+
if not supabase_url or not supabase_key:
|
15 |
+
raise ValueError("SUPABASE_URL and SUPABASE_SERVICE_KEY must be set in your environment or .env file.")
|
16 |
+
|
17 |
+
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
|
18 |
+
supabase = create_client(supabase_url, supabase_key)
|
19 |
+
return SupabaseVectorStore(
|
20 |
+
client=supabase,
|
21 |
+
embedding=embeddings,
|
22 |
+
table_name="documents",
|
23 |
+
query_name="match_documents_langchain",
|
24 |
+
)
|
25 |
|
26 |
def retrieve(query: str) -> str:
|
27 |
+
try:
|
28 |
+
vector_store = get_vector_store()
|
29 |
+
results = vector_store.similarity_search(query)
|
30 |
+
if results:
|
31 |
+
return results[0].page_content
|
32 |
+
except Exception as e:
|
33 |
+
return f"Retriever is not available (reason: {e})"
|
34 |
+
return "No similar questions found."
|
35 |
+
|