init

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+chromadb/**/* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,40 @@
+import streamlit as st
+from utils import st_load_retriever, st_load_llm, StreamHandler
+from langchain.chains import RetrievalQAWithSourcesChain
+
+st.title("AIxplorer - A Smarter Google Scholar 🌐📚")
+st.write(
+    "AIxplorer aims to revolutionize academic research by combining the capabilities of traditional search engines like Google Scholar with an advanced retrieval augmented generation (RAG) system. Built on Python and Langchain, this application provides highly relevant and context-aware academic papers, journals, and articles, elevating the standard of academic research."
+)
+
+
+st.divider()
+st.subheader("Settings")
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    use_google = st.checkbox(
+        "Use Google Search",
+        value=True,
+        help="Use Google Search to retrieve papers. If unchecked, will use the vector database.",
+    )
+st.divider()
+
+llm = st_load_llm()
+retriever = st_load_retriever(llm, "vectordb" if not use_google else "google search")
+
+qa_chain = RetrievalQAWithSourcesChain.from_chain_type(llm, retriever=retriever)
+
+user_input = st.text_area(
+    "Enter your query here",
+    help="Query should be on computer science as the RAG system is tuned to that domain.",
+)
+
+
+if st.button("Generate"):
+    st.divider()
+    st.subheader("Answer:")
+    with st.spinner("Generating..."):
+        container = st.empty()
+        stream_handler = StreamHandler(container)
+        response = qa_chain({"question": user_input}, callbacks=[stream_handler])

chromadb/ccdaf353-2f96-4472-a625-909323352d4d/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fccfc026bd403c900c6d79e1a155e0d5c63c8c755d6f3ca371a34d8cfd03c7
+size 946940000

chromadb/ccdaf353-2f96-4472-a625-909323352d4d/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b87ee33bb338a0109cb825f43f7141e3feed200cbbc373fc7668e7795ae669
+size 100

chromadb/ccdaf353-2f96-4472-a625-909323352d4d/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405a464b08d974ed544ca62f07d73f3cd22c605c746bd196ea7914068a24271a
+size 35773057

chromadb/ccdaf353-2f96-4472-a625-909323352d4d/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957a02ed53e8b1db4e5bd8a91a0a2c0fbf08c8988ffa5aac911b2081a81b11e
+size 2260000

chromadb/ccdaf353-2f96-4472-a625-909323352d4d/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b483c64357659a9b0a518dac20566ea4a10212e59b666033df8115e144f405d
+size 4833528

chromadb/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac92ff6eeb03659dbceca7402c8107a3f44084bc753b28e6bac39c817c0712f6
+size 5545873408

config.py

@@ -0,0 +1,19 @@
+vector_db_path = "./chromadb"  # path to the vector database
+
+embeddings_model = "BAAI/bge-small-en"  # embeddings model to use to generate vectors
+
+llm_path = "./mistral-7b-openorca.Q5_K_M.gguf"  # path to the LLM model
+
+device = "cpu"  # device to use for the LLM model, "cuda" or "cpu
+
+n_gpu_layers = 0  # Change this value based on your model and your GPU VRAM pool. Change to 0 if you are using a CPU.
+
+n_batch = 256  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
+
+context_length = 8000  # length of the context to use for the LLM model
+
+temperature = 0.0  # temperature to use for the LLM model
+
+top_p = 1.0  # top_p to use for the LLM model
+
+max_tokens = 2000  # maximum number of tokens to generate from the LLM model

mistral-7b-openorca.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a7c2d08be7c718a28c73115c321d91918a3fdef27de1da9f38b4079056773e
+size 5131421440

requirements.txt

@@ -0,0 +1,161 @@
+aiohttp==3.9.1
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+asgiref==3.7.2
+attrs==23.1.0
+backoff==2.2.1
+bcrypt==4.1.2
+beautifulsoup4==4.12.2
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.20
+click==8.1.7
+coloredlogs==15.0.1
+dataclasses-json==0.6.3
+Deprecated==1.2.14
+diskcache==5.6.3
+fastapi==0.105.0
+filelock==3.13.1
+flatbuffers==23.5.26
+frozenlist==1.4.1
+fsspec==2023.12.2
+gitdb==4.0.11
+GitPython==3.1.40
+google-api-core==2.15.0
+google-api-python-client==2.111.0
+google-auth==2.25.2
+google-auth-httplib2==0.2.0
+googleapis-common-protos==1.62.0
+greenlet==3.0.2
+grpcio==1.60.0
+h11==0.14.0
+html2text==2020.1.16
+httplib2==0.22.0
+httptools==0.6.1
+huggingface-hub==0.20.1
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib-resources==6.1.1
+Jinja2==3.1.2
+joblib==1.3.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kubernetes==28.1.0
+langchain==0.0.352
+langchain-community==0.0.5
+langchain-core==0.1.2
+langsmith==0.0.72
+llama_cpp_python==0.2.24
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+mmh3==4.0.1
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.2
+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==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.16.3
+opentelemetry-api==1.22.0
+opentelemetry-exporter-otlp-proto-common==1.22.0
+opentelemetry-exporter-otlp-proto-grpc==1.22.0
+opentelemetry-instrumentation==0.43b0
+opentelemetry-instrumentation-asgi==0.43b0
+opentelemetry-instrumentation-fastapi==0.43b0
+opentelemetry-proto==1.22.0
+opentelemetry-sdk==1.22.0
+opentelemetry-semantic-conventions==0.43b0
+opentelemetry-util-http==0.43b0
+overrides==7.4.0
+packaging==23.2
+pandas==2.1.4
+Pillow==10.1.0
+posthog==3.1.0
+protobuf==4.25.1
+pulsar-client==3.3.0
+pyarrow==14.0.2
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydeck==0.8.1b0
+Pygments==2.17.2
+pyparsing==3.1.1
+PyPika==0.48.9
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+requests-oauthlib==1.3.1
+rich==13.7.0
+rpds-py==0.15.2
+rsa==4.9
+safetensors==0.4.1
+scikit-learn==1.3.2
+scipy==1.11.4
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.23
+starlette==0.27.0
+streamlit==1.29.0
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.2.0
+tiktoken==0.5.2
+tokenizers==0.15.0
+toml==0.10.2
+toolz==0.12.0
+torch==2.1.2
+torchvision==0.16.2
+tornado==6.4
+tqdm==4.66.1
+transformers==4.36.2
+triton==2.1.0
+typer==0.9.0
+typing-inspect==0.9.0
+typing_extensions==4.9.0
+tzdata==2023.3
+tzlocal==5.2
+uritemplate==4.1.1
+urllib3==1.26.18
+uvicorn==0.24.0.post1
+uvloop==0.19.0
+validators==0.22.0
+watchdog==3.0.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==12.0
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.17.0

utils.py

@@ -0,0 +1,73 @@
+import streamlit as st
+from langchain.llms import LlamaCpp
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.retrievers.web_research import WebResearchRetriever
+from langchain.utilities import GoogleSearchAPIWrapper
+from dotenv import load_dotenv
+import config
+from langchain.callbacks.base import BaseCallbackHandler
+
+
+class StreamHandler(BaseCallbackHandler):
+    def __init__(self, container, initial_text=""):
+        self.container = container
+        self.text = initial_text
+
+    def on_llm_new_token(self, token: str, **kwargs) -> None:
+        self.text += token
+        self.container.markdown(self.text)
+
+
+@st.cache_resource
+def st_load_retriever(_llm, mode):
+    model_kwargs = {"device": "cuda"}
+    embeddings_model = HuggingFaceEmbeddings(
+        model_name=config.embeddings_model,
+        model_kwargs=model_kwargs,
+    )
+
+    vector_store = Chroma(
+        "cs_paper_store",
+        embeddings_model,
+        persist_directory=config.vector_db_path,
+    )
+
+    if mode == "vectordb":
+        # load the vector store
+        return vector_store.as_retriever()
+
+    elif mode == "google search":
+        load_dotenv()
+        search = GoogleSearchAPIWrapper()
+        web_research_retriever = WebResearchRetriever.from_llm(
+            vectorstore=vector_store, llm=_llm, search=search
+        )
+        return web_research_retriever
+
+    else:
+        raise ValueError(f"Unknown retrieval mode: {mode}")
+
+
+@st.cache_resource
+def st_load_llm(
+    temperature=config.temperature,
+    max_tokens=config.max_tokens,
+    top_p=config.top_p,
+    llm_path=config.llm_path,
+    context_length=config.context_length,
+    n_gpu_layers=config.n_gpu_layers,
+    n_batch=config.n_batch,
+):
+    llm = LlamaCpp(
+        model_path=llm_path,
+        temperature=temperature,
+        max_tokens=max_tokens,
+        n_ctx=context_length,
+        n_gpu_layers=n_gpu_layers,
+        n_batch=n_batch,
+        top_p=top_p,
+        verbose=False,
+    )
+
+    return llm