Upload 5 files

.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
+chroma_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+data/Symptom-Based[[:space:]]Medication[[:space:]]Prescribing.pdf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,75 @@
+import streamlit as st
+import random
+from app_config import SYSTEM_PROMPT, NLP_MODEL_NAME, NUMBER_OF_VECTORS_FOR_RAG, NLP_MODEL_TEMPERATURE, NLP_MODEL_MAX_TOKENS, VECTOR_MAX_TOKENS, my_vector_store, chat, tiktoken_len
+from langchain.memory import ConversationSummaryBufferMemory
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+from langchain.chains.summarize import load_summarize_chain
+from langchain.prompts import PromptTemplate
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+from pathlib import Path
+import os
+
+env_path = Path('.') / '.env'
+load_dotenv(dotenv_path=env_path)
+
+# Initialize vector store and LLM outside session state
+retriever = my_vector_store.as_retriever(k=NUMBER_OF_VECTORS_FOR_RAG)
+llm = ChatGroq(temperature=NLP_MODEL_TEMPERATURE, groq_api_key=str(os.getenv('GROQ_API_KEY')), model_name=NLP_MODEL_NAME)
+
+def response_generator(prompt: str) -> str:
+    try:
+        docs = retriever.invoke(prompt)
+        my_context = [doc.page_content for doc in docs]
+        my_context = '\n\n'.join(my_context)
+        system_message = SystemMessage(content=SYSTEM_PROMPT.format(context=my_context, previous_message_summary=st.session_state.rag_memory.moving_summary_buffer))
+        print(system_message)
+        chat_messages = (system_message + st.session_state.rag_memory.chat_memory.messages + HumanMessage(content=prompt)).messages
+        print("total tokens: ", tiktoken_len(str(chat_messages)))
+        response = llm.invoke(chat_messages)
+        return response.content
+    except Exception as error:
+        print(error, "ERROR")
+        return "Oops! something went wrong, please try again."
+
+st.markdown(
+    """
+<style>
+    .st-emotion-cache-janbn0 {
+        flex-direction: row-reverse;
+        text-align: right;
+    }
+</style>
+""",
+    unsafe_allow_html=True,
+)
+
+# Initialize session state
+if "messages" not in st.session_state:
+    st.session_state.messages = [{"role": "system", "content": SYSTEM_PROMPT}]
+if "rag_memory" not in st.session_state:
+    st.session_state.rag_memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=5000)
+if "retriever" not in st.session_state:
+    st.session_state.retriever = retriever
+
+st.title("Call on Doc prescription Recommendation")
+container = st.container(height=600)
+for message in st.session_state.messages:
+    if message["role"] != "system":
+        with container.chat_message(message["role"]):
+            st.write(message["content"])
+
+if prompt := st.chat_input("Enter your query here... "):
+    with container.chat_message("user"):
+        st.write(prompt)
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    
+    with container.chat_message("assistant"):  
+        response = response_generator(prompt=prompt)
+        print("******************************************************** Response ********************************************************")
+        print("MY RESPONSE IS:", response)
+        st.write(response)
+    
+    print("Response is:", response)
+    st.session_state.rag_memory.save_context({'input': prompt}, {'output': response})
+    st.session_state.messages.append({"role": "assistant", "content": response})

app_config.py

@@ -0,0 +1,80 @@
+import tiktoken
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_chroma import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings  # Updated import
+from langchain_community.document_loaders import PyPDFLoader  # Updated import
+from langchain.memory import ConversationSummaryBufferMemory  # Remains the same for now
+from langchain_groq import ChatGroq
+import os
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+tokenizer = tiktoken.get_encoding('cl100k_base')
+FILE_NAMEs = os.listdir('data')
+
+SYSTEM_PROMPT = """
+You are an AI-powered medical assistant trained to provide prescription recommendations based on user symptoms. Your responses should be accurate, safe, and aligned with general medical guidelines.
+When a user provides symptoms, follow these steps:
+    1.Ask clarifying questions if needed to ensure accurate symptom understanding.
+    2.Provide a probable condition or diagnosis based on symptoms.
+    3.Recommend suitable over-the-counter or prescription medications (mentioning that a doctor's consultation is advised for prescriptions).
+    4.Offer general care advice, such as lifestyle changes or home remedies.
+    5.If symptoms indicate a severe or emergency condition, advise the user to seek immediate medical attention.
+    Always be polite, professional, and ensure user safety in your responses. Avoid giving definitive diagnoses or prescriptions without medical consultation.
+context: {context}
+previous message summary: {previous_message_summary}
+"""
+
+human_template = "{question}"
+
+NLP_MODEL_NAME = "llama3-70b-8192"
+REASONING_MODEL_NAME = "mixtral-8x7b-32768"
+REASONING_MODEL_TEMPERATURE = 0
+NLP_MODEL_TEMPERATURE = 0
+NLP_MODEL_MAX_TOKENS = 5400
+VECTOR_MAX_TOKENS = 100
+VECTORS_TOKEN_OVERLAP_SIZE = 20
+NUMBER_OF_VECTORS_FOR_RAG = 7
+
+# Create the length function
+def tiktoken_len(text):
+    tokens = tokenizer.encode(text, disallowed_special=())
+    return len(tokens)
+
+def get_vectorstore():
+    model_name = "BAAI/bge-small-en"
+    model_kwargs = {"device": "cpu"}
+    encode_kwargs = {"normalize_embeddings": True}
+    hf = HuggingFaceEmbeddings(
+        model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
+    )
+    persist_directory = "./chroma_db"  # Directory to save the vector store
+    all_splits = []
+    for file_name in FILE_NAMEs:
+        if file_name.endswith(".pdf"):
+            loader = PyPDFLoader(os.path.join("data", file_name))
+            data = loader.load()[0].page_content
+        else:
+            with open(os.path.join("data", file_name), "r") as f:
+                data = f.read()
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=VECTOR_MAX_TOKENS,
+            chunk_overlap=VECTORS_TOKEN_OVERLAP_SIZE,
+            length_function=tiktoken_len,
+            separators=["\n\n\n", "\n\n", "\n", " ", ""]
+        )
+        all_splits = all_splits + text_splitter.split_text(data)
+
+    # Check if the vector store already exists
+    if os.path.exists(persist_directory):
+        vectorstore = Chroma(persist_directory=persist_directory, embedding_function=hf)
+    else:
+        vectorstore = Chroma.from_texts(
+            texts=all_splits, embedding=hf, persist_directory=persist_directory
+        )
+    return vectorstore
+
+chat = ChatGroq(temperature=0, groq_api_key=os.getenv("GROQ_API_KEY"), model_name="llama3-8b-8192", streaming=True)
+rag_memory = ConversationSummaryBufferMemory(llm=chat, max_token_limit=3000)
+my_vector_store = get_vectorstore()

chroma_db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1051e43ac0d6482edc4f0f8acf3c8663b49b6a65607665bb621ccfe549fae19
+size 167936

data/Symptom-Based Medication Prescribing.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cd17d1bdd348afcfc033468df5e8a2a16a0ebe38e8bc184b5fc4f3be9cc4a6
+size 169001

requirements.txt

@@ -0,0 +1,169 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.16
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.9.0
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==25.3.0
+backoff==2.2.1
+bcrypt==4.3.0
+blinker==1.9.0
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.1.31
+charset-normalizer==3.4.1
+chroma-hnswlib==0.7.6
+chromadb==0.6.3
+click==8.1.8
+coloredlogs==15.0.1
+dataclasses-json==0.6.7
+Deprecated==1.2.18
+distro==1.9.0
+durationpy==0.9
+exceptiongroup==1.2.2
+fastapi==0.115.12
+filelock==3.18.0
+flatbuffers==25.2.10
+frozenlist==1.5.0
+fsspec==2025.3.2
+gitdb==4.0.12
+GitPython==3.1.44
+google-auth==2.38.0
+googleapis-common-protos==1.69.2
+greenlet==3.1.1
+groq==0.21.0
+grpcio==1.71.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.30.1
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+Jinja2==3.1.6
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+kubernetes==32.0.1
+langchain==0.3.22
+langchain-chroma==0.2.2
+langchain-community==0.3.20
+langchain-core==0.3.49
+langchain-groq==0.3.2
+langchain-huggingface==0.1.2
+langchain-text-splitters==0.3.7
+langsmith==0.3.22
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.3.1
+mypy-extensions==1.0.0
+narwhals==1.33.0
+networkx==3.4.2
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+oauthlib==3.2.2
+onnxruntime==1.21.0
+opentelemetry-api==1.31.1
+opentelemetry-exporter-otlp-proto-common==1.31.1
+opentelemetry-exporter-otlp-proto-grpc==1.31.1
+opentelemetry-instrumentation==0.52b1
+opentelemetry-instrumentation-asgi==0.52b1
+opentelemetry-instrumentation-fastapi==0.52b1
+opentelemetry-proto==1.31.1
+opentelemetry-sdk==1.31.1
+opentelemetry-semantic-conventions==0.52b1
+opentelemetry-util-http==0.52b1
+orjson==3.10.16
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pillow==11.2.0
+posthog==3.23.0
+propcache==0.3.1
+protobuf==5.29.4
+pyarrow==19.0.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pydantic==2.11.1
+pydantic-settings==2.8.1
+pydantic_core==2.33.0
+pydeck==0.9.1
+Pygments==2.19.1
+pypdf==5.4.0
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==14.0.0
+rpds-py==0.24.0
+rsa==4.9
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+sentence-transformers==4.0.1
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+SQLAlchemy==2.0.40
+starlette==0.46.1
+streamlit==1.44.1
+sympy==1.13.1
+tenacity==9.0.0
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+toml==0.10.2
+tomli==2.2.1
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.50.3
+triton==3.2.0
+typer==0.15.2
+typing-inspect==0.9.0
+typing-inspection==0.4.0
+typing_extensions==4.13.0
+tzdata==2025.2
+urllib3==2.3.0
+uvicorn==0.34.0
+uvloop==0.21.0
+watchdog==6.0.0
+watchfiles==1.0.4
+websocket-client==1.8.0
+websockets==15.0.1
+wrapt==1.17.2
+yarl==1.18.3
+zipp==3.21.0
+zstandard==0.23.0