Spaces:
Sleeping
Sleeping
Upload 4 files
Browse files- requirements.txt +152 -0
- secure-connect-temp-db.zip +3 -0
- temp_db-token.json +5 -0
- test.py +109 -0
requirements.txt
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
aenum==3.1.15
|
| 2 |
+
aiohttp==3.9.3
|
| 3 |
+
aiosignal==1.3.1
|
| 4 |
+
aiostream==0.5.2
|
| 5 |
+
altair==4.2.2
|
| 6 |
+
annotated-types==0.6.0
|
| 7 |
+
anyio==4.2.0
|
| 8 |
+
asttokens==2.4.1
|
| 9 |
+
async-timeout==4.0.3
|
| 10 |
+
attrs==23.2.0
|
| 11 |
+
beautifulsoup4==4.12.3
|
| 12 |
+
bleach==6.1.0
|
| 13 |
+
blinker==1.7.0
|
| 14 |
+
cachetools==5.3.2
|
| 15 |
+
cassandra-driver==3.29.0
|
| 16 |
+
certifi==2024.2.2
|
| 17 |
+
charset-normalizer==3.3.2
|
| 18 |
+
click==8.1.7
|
| 19 |
+
colorama==0.4.6
|
| 20 |
+
comm==0.2.1
|
| 21 |
+
contourpy==1.2.0
|
| 22 |
+
cycler==0.12.1
|
| 23 |
+
dataclasses-json==0.5.14
|
| 24 |
+
debugpy==1.8.1
|
| 25 |
+
decorator==5.1.1
|
| 26 |
+
defusedxml==0.7.1
|
| 27 |
+
Deprecated==1.2.14
|
| 28 |
+
distro==1.9.0
|
| 29 |
+
entrypoints==0.4
|
| 30 |
+
exceptiongroup==1.2.0
|
| 31 |
+
executing==2.0.1
|
| 32 |
+
faiss-cpu==1.7.4
|
| 33 |
+
Faker==23.2.1
|
| 34 |
+
fastjsonschema==2.19.1
|
| 35 |
+
favicon==0.7.0
|
| 36 |
+
fonttools==4.49.0
|
| 37 |
+
frozenlist==1.4.1
|
| 38 |
+
fsspec==2024.2.0
|
| 39 |
+
geomet==0.2.1.post1
|
| 40 |
+
gitdb==4.0.11
|
| 41 |
+
GitPython==3.1.41
|
| 42 |
+
gradientai==1.7.0
|
| 43 |
+
greenlet==3.0.3
|
| 44 |
+
h11==0.14.0
|
| 45 |
+
htbuilder==0.6.2
|
| 46 |
+
httpcore==1.0.2
|
| 47 |
+
httpx==0.26.0
|
| 48 |
+
idna==3.6
|
| 49 |
+
importlib-metadata==7.0.1
|
| 50 |
+
ipykernel==6.29.2
|
| 51 |
+
jedi==0.19.1
|
| 52 |
+
Jinja2==3.1.3
|
| 53 |
+
joblib==1.3.2
|
| 54 |
+
jsonschema==4.21.1
|
| 55 |
+
jsonschema-specifications==2023.12.1
|
| 56 |
+
jupyter_client==8.6.0
|
| 57 |
+
jupyter_core==5.7.1
|
| 58 |
+
jupyterlab_pygments==0.3.0
|
| 59 |
+
kiwisolver==1.4.5
|
| 60 |
+
langchain==0.0.154
|
| 61 |
+
llama-index==0.9.12
|
| 62 |
+
lxml==5.1.0
|
| 63 |
+
Markdown==3.5.2
|
| 64 |
+
markdown-it-py==3.0.0
|
| 65 |
+
markdownlit==0.0.7
|
| 66 |
+
MarkupSafe==2.1.5
|
| 67 |
+
marshmallow==3.20.2
|
| 68 |
+
matplotlib==3.8.3
|
| 69 |
+
matplotlib-inline==0.1.6
|
| 70 |
+
mdurl==0.1.2
|
| 71 |
+
mistune==3.0.2
|
| 72 |
+
more-itertools==10.2.0
|
| 73 |
+
multidict==6.0.5
|
| 74 |
+
mypy-extensions==1.0.0
|
| 75 |
+
nbclient==0.9.0
|
| 76 |
+
nbconvert==7.16.0
|
| 77 |
+
nbformat==5.9.2
|
| 78 |
+
nest-asyncio==1.6.0
|
| 79 |
+
nltk==3.8.1
|
| 80 |
+
numexpr==2.9.0
|
| 81 |
+
numpy==1.26.4
|
| 82 |
+
openai==1.12.0
|
| 83 |
+
openapi-schema-pydantic==1.2.4
|
| 84 |
+
packaging==23.2
|
| 85 |
+
pandas==2.2.0
|
| 86 |
+
pandocfilters==1.5.1
|
| 87 |
+
parso==0.8.3
|
| 88 |
+
pillow==10.2.0
|
| 89 |
+
platformdirs==4.2.0
|
| 90 |
+
prometheus_client==0.20.0
|
| 91 |
+
prompt-toolkit==3.0.43
|
| 92 |
+
protobuf==3.20.3
|
| 93 |
+
psutil==5.9.8
|
| 94 |
+
pure-eval==0.2.2
|
| 95 |
+
pyarrow==15.0.0
|
| 96 |
+
pydantic==1.10.14
|
| 97 |
+
pydantic_core==2.16.2
|
| 98 |
+
pydeck==0.8.1b0
|
| 99 |
+
Pygments==2.17.2
|
| 100 |
+
pymdown-extensions==10.7
|
| 101 |
+
Pympler==1.0.1
|
| 102 |
+
pyparsing==3.1.1
|
| 103 |
+
pypdf==4.0.1
|
| 104 |
+
PyPDF2==3.0.1
|
| 105 |
+
python-dateutil==2.8.2
|
| 106 |
+
python-dotenv==1.0.0
|
| 107 |
+
pytz==2024.1
|
| 108 |
+
PyYAML==6.0.1
|
| 109 |
+
pyzmq==25.1.2
|
| 110 |
+
referencing==0.33.0
|
| 111 |
+
regex==2023.12.25
|
| 112 |
+
requests==2.31.0
|
| 113 |
+
rich==13.7.0
|
| 114 |
+
rpds-py==0.17.1
|
| 115 |
+
semver==3.0.2
|
| 116 |
+
six==1.16.0
|
| 117 |
+
smmap==5.0.1
|
| 118 |
+
sniffio==1.3.0
|
| 119 |
+
soupsieve==2.5
|
| 120 |
+
SQLAlchemy==2.0.27
|
| 121 |
+
st-annotated-text==4.0.1
|
| 122 |
+
stack-data==0.6.3
|
| 123 |
+
streamlit==1.31.1
|
| 124 |
+
streamlit-camera-input-live==0.2.0
|
| 125 |
+
streamlit-card==1.0.0
|
| 126 |
+
streamlit-embedcode==0.1.2
|
| 127 |
+
streamlit-extras==0.4.0
|
| 128 |
+
streamlit-faker==0.0.3
|
| 129 |
+
streamlit-image-coordinates==0.1.6
|
| 130 |
+
streamlit-keyup==0.2.3
|
| 131 |
+
streamlit-toggle-switch==1.0.2
|
| 132 |
+
streamlit-vertical-slider==2.5.5
|
| 133 |
+
tenacity==8.2.3
|
| 134 |
+
tiktoken==0.6.0
|
| 135 |
+
tinycss2==1.2.1
|
| 136 |
+
toml==0.10.2
|
| 137 |
+
toolz==0.12.1
|
| 138 |
+
tornado==6.4
|
| 139 |
+
tqdm==4.66.2
|
| 140 |
+
traitlets==5.14.1
|
| 141 |
+
typing-inspect==0.9.0
|
| 142 |
+
typing_extensions==4.9.0
|
| 143 |
+
tzdata==2024.1
|
| 144 |
+
tzlocal==5.2
|
| 145 |
+
urllib3==2.2.0
|
| 146 |
+
validators==0.22.0
|
| 147 |
+
watchdog==4.0.0
|
| 148 |
+
wcwidth==0.2.13
|
| 149 |
+
webencodings==0.5.1
|
| 150 |
+
wrapt==1.16.0
|
| 151 |
+
yarl==1.9.4
|
| 152 |
+
zipp==3.17.0
|
secure-connect-temp-db.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95aa8a081f163bff17243230a0a82175ec593f0a10e4ace26d3afcf0b2fa19ae
|
| 3 |
+
size 12260
|
temp_db-token.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clientId": "nsJkarPpFtcNCEzGatNGTttm",
|
| 3 |
+
"secret": "x9+CWlAOHuwtWKG6XY1Iv32THHlHSC.ZyB+-g+BaDZdWrAz7ZC01PdjaIzBO7OvIJvaLzglSmcOWjN2PAXbuS4uKT7Gq7kDMY4hwqovANflyA4xgW9ao-0FQqZnN4yG+",
|
| 4 |
+
"token": "AstraCS:nsJkarPpFtcNCEzGatNGTttm:caf63b39a1eab4ba6e6bc99ba7b66ed549a7f0509080f7868140e4c3f472ee40"
|
| 5 |
+
}
|
test.py
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
import os
|
| 3 |
+
import streamlit as st
|
| 4 |
+
from cassandra.auth import PlainTextAuthProvider
|
| 5 |
+
from cassandra.cluster import Cluster
|
| 6 |
+
from llama_index import ServiceContext
|
| 7 |
+
from llama_index import set_global_service_context
|
| 8 |
+
from llama_index import VectorStoreIndex, SimpleDirectoryReader, StorageContext
|
| 9 |
+
from llama_index.embeddings import GradientEmbedding
|
| 10 |
+
from llama_index.llms import GradientBaseModelLLM
|
| 11 |
+
from llama_index.vector_stores import CassandraVectorStore
|
| 12 |
+
from copy import deepcopy
|
| 13 |
+
from tempfile import NamedTemporaryFile
|
| 14 |
+
|
| 15 |
+
os.environ['GRADIENT_ACCESS_TOKEN'] = "sevG6Rqb0ztaquM4xjr83SBNSYj91cux"
|
| 16 |
+
os.environ['GRADIENT_WORKSPACE_ID'] = "4de36c1f-5ee6-41da-8f95-9d2fb1ded33a_workspace"
|
| 17 |
+
|
| 18 |
+
@st.cache_resource
|
| 19 |
+
def create_datastax_connection():
|
| 20 |
+
|
| 21 |
+
cloud_config= {'secure_connect_bundle': 'secure-connect-temp-db.zip'}
|
| 22 |
+
|
| 23 |
+
with open("temp_db-token.json") as f:
|
| 24 |
+
secrets = json.load(f)
|
| 25 |
+
|
| 26 |
+
CLIENT_ID = secrets["clientId"]
|
| 27 |
+
CLIENT_SECRET = secrets["secret"]
|
| 28 |
+
|
| 29 |
+
auth_provider = PlainTextAuthProvider(CLIENT_ID, CLIENT_SECRET)
|
| 30 |
+
cluster = Cluster(cloud=cloud_config, auth_provider=auth_provider)
|
| 31 |
+
astra_session = cluster.connect()
|
| 32 |
+
return astra_session
|
| 33 |
+
|
| 34 |
+
def main():
|
| 35 |
+
|
| 36 |
+
index_placeholder = None
|
| 37 |
+
st.set_page_config(page_title = "NyayMitra", page_icon="π¦")
|
| 38 |
+
st.header('NyayMitra')
|
| 39 |
+
|
| 40 |
+
if "conversation" not in st.session_state:
|
| 41 |
+
st.session_state.conversation = None
|
| 42 |
+
|
| 43 |
+
if "activate_chat" not in st.session_state:
|
| 44 |
+
st.session_state.activate_chat = False
|
| 45 |
+
|
| 46 |
+
if "messages" not in st.session_state:
|
| 47 |
+
st.session_state.messages = []
|
| 48 |
+
|
| 49 |
+
for message in st.session_state.messages:
|
| 50 |
+
with st.chat_message(message["role"], avatar = message['avatar']):
|
| 51 |
+
st.markdown(message["content"])
|
| 52 |
+
|
| 53 |
+
session = create_datastax_connection()
|
| 54 |
+
|
| 55 |
+
os.environ['GRADIENT_ACCESS_TOKEN'] = "sevG6Rqb0ztaquM4xjr83SBNSYj91cux"
|
| 56 |
+
os.environ['GRADIENT_WORKSPACE_ID'] = "4de36c1f-5ee6-41da-8f95-9d2fb1ded33a_workspace"
|
| 57 |
+
|
| 58 |
+
llm = GradientBaseModelLLM(base_model_slug="llama2-7b-chat", max_tokens=400)
|
| 59 |
+
|
| 60 |
+
embed_model = GradientEmbedding(
|
| 61 |
+
gradient_access_token = os.environ["GRADIENT_ACCESS_TOKEN"],
|
| 62 |
+
gradient_workspace_id = os.environ["GRADIENT_WORKSPACE_ID"],
|
| 63 |
+
gradient_model_slug="bge-large")
|
| 64 |
+
|
| 65 |
+
service_context = ServiceContext.from_defaults(
|
| 66 |
+
llm = llm,
|
| 67 |
+
embed_model = embed_model,
|
| 68 |
+
chunk_size=256)
|
| 69 |
+
|
| 70 |
+
set_global_service_context(service_context)
|
| 71 |
+
|
| 72 |
+
with st.sidebar:
|
| 73 |
+
st.subheader('Start your chat here')
|
| 74 |
+
if st.button('Process'):
|
| 75 |
+
with st.spinner('Processing'):
|
| 76 |
+
reader = 'data'
|
| 77 |
+
|
| 78 |
+
documents = SimpleDirectoryReader(reader).load_data()
|
| 79 |
+
index = VectorStoreIndex.from_documents(documents,
|
| 80 |
+
service_context=service_context)
|
| 81 |
+
query_engine = index.as_query_engine()
|
| 82 |
+
if "query_engine" not in st.session_state:
|
| 83 |
+
st.session_state.query_engine = query_engine
|
| 84 |
+
st.session_state.activate_chat = True
|
| 85 |
+
|
| 86 |
+
if st.session_state.activate_chat == True:
|
| 87 |
+
if prompt := st.chat_input("Ask your question"):
|
| 88 |
+
with st.chat_message("user", avatar = 'π¨π»'):
|
| 89 |
+
st.markdown(prompt)
|
| 90 |
+
st.session_state.messages.append({"role": "user",
|
| 91 |
+
"avatar" :'π¨π»',
|
| 92 |
+
"content": prompt})
|
| 93 |
+
|
| 94 |
+
query_index_placeholder = st.session_state.query_engine
|
| 95 |
+
pdf_response = query_index_placeholder.query(prompt)
|
| 96 |
+
cleaned_response = pdf_response.response
|
| 97 |
+
with st.chat_message("assistant", avatar='π€'):
|
| 98 |
+
st.markdown(cleaned_response)
|
| 99 |
+
st.session_state.messages.append({"role": "assistant",
|
| 100 |
+
"avatar" :'π€',
|
| 101 |
+
"content": cleaned_response})
|
| 102 |
+
else:
|
| 103 |
+
st.markdown(
|
| 104 |
+
' '
|
| 105 |
+
)
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
if __name__ == '__main__':
|
| 109 |
+
main()
|