Init commit

app.py

@@ -0,0 +1,152 @@
+from pathlib import Path
+
+from llama_index.core import(SimpleDirectoryReader,
+                            VectorStoreIndex, StorageContext,
+                            Settings,set_global_tokenizer)
+from llama_index.llms.llama_cpp import LlamaCPP
+from llama_index.llms.llama_cpp.llama_utils import (
+    messages_to_prompt,
+    completion_to_prompt,
+)
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from transformers import AutoTokenizer, BitsAndBytesConfig
+from llama_index.llms.huggingface import HuggingFaceLLM
+import torch
+import logging
+import sys
+import streamlit as st
+
+default_bnb_config = BitsAndBytesConfig(
+                                                load_in_4bit=True,
+                                                bnb_4bit_quant_type='nf4',
+                                                bnb_4bit_use_double_quant=True,
+                                                bnb_4bit_compute_dtype=torch.bfloat16
+                                            )
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
+set_global_tokenizer(
+    AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf").encode
+)
+
+
+def getDocs(doc_path="./data/"):
+    documents = SimpleDirectoryReader(doc_path).load_data()
+    return documents
+
+
+def getVectorIndex(docs):
+    Settings.chunk_size = 512
+    index_set = {}
+
+    storage_context = StorageContext.from_defaults()
+    cur_index = VectorStoreIndex.from_documents(docs, embed_model = getEmbedModel())
+    storage_context.persist(persist_dir=f"./storage/book_data")
+    return cur_index
+
+
+def getLLM():
+
+
+    llm = HuggingFaceLLM(
+    context_window=3900,
+    max_new_tokens=256,
+    # generate_kwargs={"temperature": 0.25, "do_sample": False},
+    tokenizer_name="meta-llama/Llama-2-13b-chat-hf",
+    model_name="meta-llama/Llama-2-13b-chat-hf",
+    device_map=0,
+    tokenizer_kwargs={"max_length": 2048},
+    # uncomment this if using CUDA to reduce memory usage
+    model_kwargs={"torch_dtype": torch.float16,
+    "quantization_config": default_bnb_config,
+    }
+    )
+    return llm
+
+def getQueryEngine(index):
+    query_engine = index.as_chat_engine(llm=getLLM())
+    return query_engine
+
+def getEmbedModel():
+    embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+    return embed_model
+
+
+
+
+
+
+
+
+
+
+
+st.set_page_config(page_title="Chat with the Streamlit docs, powered by LlamaIndex", page_icon="🦙", layout="centered", initial_sidebar_state="auto", menu_items=None)
+st.title("Chat with the Streamlit docs, powered by LlamaIndex 💬🦙")
+st.info("Check out the full tutorial to build this app in our [blog post](https://blog.streamlit.io/build-a-chatbot-with-custom-data-sources-powered-by-llamaindex/)", icon="📃")
+         
+if "messages" not in st.session_state.keys(): # Initialize the chat messages history
+    st.session_state.messages = [
+        {"role": "assistant", "content": "Ask me a question about children's books or movies!"}
+    ]
+
+@st.cache_resource(show_spinner=False)
+def load_data():
+    index = getVectorIndex(getDocs())
+    return index
+    query_engine = getQueryEngine(index)
+
+index = load_data()
+
+if "chat_engine" not in st.session_state.keys(): # Initialize the chat engine
+        st.session_state.chat_engine = index.as_chat_engine(llm=getLLM(),chat_mode="condense_question", verbose=True)
+
+if prompt := st.chat_input("Your question"): # Prompt for user input and save to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+for message in st.session_state.messages: # Display the prior chat messages
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+# If last message is not from assistant, generate a new response
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = st.session_state.chat_engine.chat(prompt)
+            st.write(response.response)
+            message = {"role": "assistant", "content": response.response}
+            st.session_state.messages.append(message) # Add response to message history
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# if __name__ == "__main__":
+
+#     index = getVectorIndex(getDocs())
+#     query_engine = getQueryEngine(index)
+#     while(True):
+#         your_request = input("Your comment: ")
+#         response = query_engine.chat(your_request)
+#         print(response)
+
+
+
+
+
+
+
+
+
+    

requirements.txt

@@ -0,0 +1,180 @@
+accelerate==0.27.2
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.3.0
+asgiref==3.7.2
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.2
+beautifulsoup4==4.12.3
+bitsandbytes==0.42.0
+blinker==1.7.0
+bs4==0.0.2
+build==1.1.1
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.24
+click==8.1.7
+coloredlogs==15.0.1
+dataclasses-json==0.6.4
+Deprecated==1.2.14
+dirtyjson==1.0.8
+diskcache==5.6.3
+distro==1.9.0
+fastapi==0.110.0
+filelock==3.13.1
+flatbuffers==23.5.26
+frozenlist==1.4.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.42
+google-auth==2.28.1
+googleapis-common-protos==1.62.0
+greenlet==3.0.3
+grpcio==1.62.0
+h11==0.14.0
+httpcore==1.0.4
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.20.3
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib_resources==6.1.2
+install==1.3.5
+Jinja2==3.1.3
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kubernetes==29.0.0
+llama-index==0.10.15
+llama-index-agent-openai==0.1.5
+llama-index-cli==0.1.7
+llama-index-core==0.10.15
+llama-index-embeddings-huggingface==0.1.4
+llama-index-embeddings-openai==0.1.6
+llama-index-indices-managed-llama-cloud==0.1.3
+llama-index-legacy==0.9.48
+llama-index-llms-huggingface==0.1.3
+llama-index-llms-llama-cpp==0.1.3
+llama-index-llms-openai==0.1.7
+llama-index-multi-modal-llms-openai==0.1.4
+llama-index-program-openai==0.1.4
+llama-index-question-gen-openai==0.1.3
+llama-index-readers-file==0.1.6
+llama-index-readers-llama-parse==0.1.3
+llama-index-vector-stores-chroma==0.1.5
+llama-parse==0.3.5
+llama_cpp_python==0.2.55
+llamaindex-py-client==0.1.13
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.0
+mdurl==0.1.2
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.17.1
+openai==1.13.3
+opentelemetry-api==1.23.0
+opentelemetry-exporter-otlp-proto-common==1.23.0
+opentelemetry-exporter-otlp-proto-grpc==1.23.0
+opentelemetry-instrumentation==0.44b0
+opentelemetry-instrumentation-asgi==0.44b0
+opentelemetry-instrumentation-fastapi==0.44b0
+opentelemetry-proto==1.23.0
+opentelemetry-sdk==1.23.0
+opentelemetry-semantic-conventions==0.44b0
+opentelemetry-util-http==0.44b0
+orjson==3.9.15
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.1
+pillow==10.2.0
+posthog==3.4.2
+protobuf==4.25.3
+psutil==5.9.8
+pulsar-client==3.4.0
+pyarrow==15.0.0
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==2.6.3
+pydantic_core==2.16.3
+pydeck==0.8.1b0
+Pygments==2.17.2
+PyMuPDF==1.23.26
+PyMuPDFb==1.23.22
+pypdf==4.1.0
+PyPika==0.48.9
+pyproject_hooks==1.0.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==1.3.1
+rich==13.7.1
+rpds-py==0.18.0
+rsa==4.9
+safetensors==0.4.2
+scipy==1.12.0
+setuptools==68.2.2
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soupsieve==2.5
+SQLAlchemy==2.0.27
+starlette==0.36.3
+streamlit==1.31.1
+sympy==1.12
+tenacity==8.2.3
+tiktoken==0.6.0
+tokenizers==0.15.2
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.1
+tornado==6.4
+tqdm==4.66.2
+transformers==4.38.2
+typer==0.9.0
+typing-inspect==0.9.0
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+urllib3==2.2.1
+uvicorn==0.27.1
+uvloop==0.19.0
+validators==0.22.0
+watchdog==4.0.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==12.0
+wheel==0.41.2
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.17.0