push files

.gitattributes

@@ -33,3 +33,15 @@ 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/1cfedb52-a018-45d3-ae4d-7636faa1a650/link_lists.bin filter=lfs diff=lfs merge=lfs -text
+chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/length.bin filter=lfs diff=lfs merge=lfs -text
+chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/index_metadata.pickle filter=lfs diff=lfs merge=lfs -text
+chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/header.bin filter=lfs diff=lfs merge=lfs -text
+chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/data_level0.bin filter=lfs diff=lfs merge=lfs -text
+document/MadhyaPradesh.docx filter=lfs diff=lfs merge=lfs -text
+document/Public_health_engineering_2010.docx filter=lfs diff=lfs merge=lfs -text
+chroma_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+document/UN_SDG_3_Detailed_Solutions.docx filter=lfs diff=lfs merge=lfs -text
+document/IndiaSchemes.docx filter=lfs diff=lfs merge=lfs -text
+document/Uttar_Pradesh_UT_Healthcare_Schemes_.docx filter=lfs diff=lfs merge=lfs -text
+document/HimachalPradesh.docx filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,4 @@
+agent_advance.py
+*.ipynb
+__pycache__/
+hackathon-healthcare-solutions-9e6f46d0a21e.json

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.12
+RUN useradd -m -u 1000 user
+USER user
+WORKDIR /code
+RUN chown -R user:user /code
+ENV HOME=/home/user
+ENV PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY ./requirements.txt ./
+RUN pip install --no-cache-dir -r ./requirements.txt
+COPY --chown=user . $HOME/app
+# COPY --chown=user:user . /code
+# COPY . .
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

agent.py

@@ -0,0 +1,256 @@
+import os
+from dotenv import load_dotenv
+from langchain_community.document_loaders import TextLoader, DirectoryLoader, UnstructuredPDFLoader, UnstructuredWordDocumentLoader
+from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import PGVector
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+import json
+import time
+# import google.generativeai as genai
+from google import genai
+from google.oauth2 import service_account
+load_dotenv()
+# credential_file = os.getenv("GOOGLE_APPLICATION_CREDENTIAL")
+# # Load environment variables
+# os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credential_file
+
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+if GEMINI_API_KEY is None:
+    GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
+
+conf = os.environ.get('GOOGLE_APPLICATION_CREDENTIALS')
+
+service_account_info = json.loads(conf)
+credentials = service_account.Credentials.from_service_account_info(service_account_info)
+
+DOCUMENT_DIR = 'document/'
+COLLECTION_NAME = "health_documents"
+
+llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", GEMINI_API_KEY=GEMINI_API_KEY, temperature=0.7, credentials=credentials)
+
+
+print("Models initialized successfully.")
+def load_documents(directory):
+    loader = DirectoryLoader(
+        directory,
+        glob="**/*.txt",
+        loader_cls=TextLoader
+    )
+    documents = loader.load()
+
+    docx_loader = DirectoryLoader(
+        directory,
+        glob="**/*.docx",
+        loader_cls=UnstructuredWordDocumentLoader,
+        loader_kwargs={"mode": "elements"}
+    )
+    documents.extend(docx_loader.load())
+    print(f"Loaded {len(documents)} documents.")
+    pdf_loader = DirectoryLoader(
+        directory,
+        glob="**/*.pdf",
+        loader_cls=UnstructuredPDFLoader
+    )
+    documents.extend(pdf_loader.load())
+    print(f"Loaded {len(documents)} documents.")
+    return documents
+
+import os
+from dotenv import load_dotenv
+from langchain_community.llms import HuggingFacePipeline
+# from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.document_loaders import TextLoader, DirectoryLoader, UnstructuredPDFLoader, UnstructuredWordDocumentLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+from langchain_community.vectorstores.utils import filter_complex_metadata
+from langchain_community.vectorstores import Chroma
+import torch
+from constants import CHROMA_PATH
+
+# Load environment variables (if needed)
+load_dotenv()
+
+# Define the directory containing the documents
+DOCUMENT_DIR = 'document/'
+
+# Define the path for ChromaDB persistent storage
+
+# Initialize Hugging Face Embeddings
+# You can change the model to any suitable embedding model
+embeddings = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/gtr-t5-large",
+    model_kwargs={'device': 'cpu'}
+)
+
+
+def load_documents(directory):
+    """Load documents from multiple file types."""
+    documents = []
+    
+    # Load text files
+    text_loader = DirectoryLoader(
+        directory,
+        glob="**/*.txt",
+        loader_cls=TextLoader
+    )
+    documents.extend(text_loader.load())
+
+    # Load Word documents
+    docx_loader = DirectoryLoader(
+        directory,
+        glob="**/*.docx",
+        loader_cls=UnstructuredWordDocumentLoader,
+        loader_kwargs={"mode": "elements"}
+    )
+    documents.extend(docx_loader.load())
+
+    # Load PDF files
+    pdf_loader = DirectoryLoader(
+        directory,
+        glob="**/*.pdf",
+        loader_cls=UnstructuredPDFLoader
+    )
+    documents.extend(pdf_loader.load())
+    
+    print(f"Loaded {len(documents)} documents.")
+    return documents
+
+def split_documents(documents, chunk_size=1000, chunk_overlap=200):
+    """Split documents into smaller chunks."""
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=chunk_size, 
+        chunk_overlap=chunk_overlap
+    )
+    chunks = text_splitter.split_documents(documents)
+    return chunks
+
+def create_and_store_embeddings(chunks):
+    """Create or load ChromaDB vector store."""
+    # Ensure the Chroma path exists
+    os.makedirs(CHROMA_PATH, exist_ok=True)
+    print(f"unfiltered chunks: {len(chunks)}")
+    filtered_chunks = []
+    for chunk in chunks:
+        # Create a new document with filtered metadata
+        filtered_metadata = {k: v for k, v in chunk.metadata.items() 
+                             if isinstance(v, (str, int, float, bool))}
+        chunk.metadata = filtered_metadata
+        filtered_chunks.append(chunk)
+
+    print(f"Filtered metadata for {len(filtered_chunks)} chunks.")
+    # Create or load the vector store
+    vector_store = Chroma.from_documents(
+        documents=filtered_chunks,
+        embedding=embeddings,
+        persist_directory=CHROMA_PATH
+    )
+    
+    print("Created ChromaDB vector store.")
+    return vector_store
+
+def load_vectordb(path:str=CHROMA_PATH):
+    if os.path.exists(path):
+        vector_store = Chroma(persist_directory=path, embedding_function=embeddings)
+        print("Loaded ChromaDB vector store.")
+        return vector_store
+    else:
+        raise ValueError(f"ChromaDB path {path} does not exist.")
+
+from langchain.chains import LLMChain
+from langchain.chains.base import Chain
+
+def create_health_agent(vector_store):
+    """Create a custom retrieval QA chain for health-related queries."""
+    prompt_template = """You are a helpful health assistant. Who will talk to the user as human and resolve their queries.
+
+    Use Previous_Conversation to maintain consistency in the conversation.
+    These are Previous_Conversation between you and user.
+    Previous_Conversation: \n{previous_conversation}
+    Thoroughly analyze the Context, and also use context to answer the questions, aside of your knowledge.
+    Keep the answer concise.
+        
+    Context: {context}
+    Question: {question}
+    Answer:"""
+    
+    PROMPT = PromptTemplate(
+        template=prompt_template, 
+        input_variables=["context", "question", "previous_conversation"]
+    )
+
+    if llm is None:
+        raise ValueError("No language model initialized. Please check the model initialization.")
+
+    # Create a retriever
+    retriever = vector_store.as_retriever(search_kwargs={"k": 10})
+
+    class CustomRetrievalQA(Chain):
+        retriever: object
+        llm_chain: LLMChain
+
+        @property
+        def input_keys(self):
+            return ['query', 'previous_conversation']
+
+        @property
+        def output_keys(self):
+            return ['result']
+
+        def _call(self, inputs):
+            query = inputs['query']
+            previous_conversation = inputs.get('previous_conversation', '')
+            
+            # Retrieve relevant documents
+            docs = retriever.get_relevant_documents(query)
+            context = "\n".join([doc.page_content for doc in docs])
+
+            # Prepare inputs for the LLM chain
+            llm_inputs = {
+                'context': context,
+                'question': query,
+                'previous_conversation': previous_conversation
+            }
+
+            # Generate response
+            result = self.llm_chain(llm_inputs)
+            return {'result': result['text']}
+
+    # Create the LLM chain
+    llm_chain = LLMChain(llm=llm, prompt=PROMPT)
+
+    # Create and return the custom chain
+    return CustomRetrievalQA(retriever=retriever, llm_chain=llm_chain)
+
+
+def agent_with_db():
+    # 1. Load documents
+    vector_store = load_vectordb(CHROMA_PATH)
+    UPDATE_DB = os.getenv("UPDATE_DB")
+    if UPDATE_DB.lower()=="true":
+        UPDATE_DB = True
+    if vector_store is None or UPDATE_DB is True:
+        print("Loading documents...")
+        print(vector_store, UPDATE_DB)
+        
+        documents = load_documents(DOCUMENT_DIR)
+
+        print("Splitting documents into chunks...")
+        chunks = split_documents(documents)
+        print(f"Split into {len(chunks)} chunks.")
+
+        print("Creating and storing embeddings in ChromaDB...")
+        try:
+            vector_store = create_and_store_embeddings(chunks)
+            print("Embeddings stored successfully in ChromaDB.")
+        except Exception as e:
+            print(f"An error occurred while creating or storing embeddings: {e}")
+            return
+
+    print("Creating the health agent...")
+    health_agent = create_health_agent(vector_store)
+
+    return health_agent

chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0403ddf49979cb439caddaba3d5d3f94b3fc7f5ff489022c9ce1e4ee1fa03676
+size 19272000

chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3b214402d967712323b30b42de7e0f58436425d88c301e653c7998a07815a8
+size 100

chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d78373234558c5a9d409fc6c5a886f8eca22b82912e45785aa84174f6308fc2
+size 346027

chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c8d34fa33a290d05a10b3918e770eeb71a0f842bde94648bc774b890821655
+size 24000

chroma_db/1cfedb52-a018-45d3-ae4d-7636faa1a650/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61059079438ee819f0494817d2db28129affccf856b43bded4b19b64ae21ea91
+size 51880

chroma_db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9d40639ca308e68a3ab6709959ca7a0c120332434e488848092d3d716a2ba6
+size 50413568

constants.py

@@ -0,0 +1,23 @@
+SYSTEM_PROMPT1 = """You are a helpful assistant. Given a question, you should answer it by first thinking about the reasoning
+process in the mind and then providing the final answer. The output format of reasoning process and final
+answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., "<think>
+reasoning process here </think><answer> final answer here </answer>". You should perform thinking
+with decomposing, reflecting, brainstorming, verifying, refining, and revising. Besides, you can perform
+searching for uncertain knowledge if necessary with the format of "<|begin_of_query|> search query
+(only keywords) here <|end_of_query|>". Then, the search system will provide you with the retrieval
+information with the format of "<|begin_of_documents|> ...search results... <|end_of_documents|>"."""
+
+SYSTEM_PROMPT2 = """The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning
+process in the mind and then provides the User with the final answer. The output format of reasoning
+process and final answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., "<think> reasoning process here </think><answer> final answer here </answer>". During the
+thinking process, **the Assistant can perform searching** for uncertain knowledge if necessary with
+the format of "<|begin_of_query|> search query (only list keywords, such as "keyword_1 keyword_2
+...")<|end_of_query|>". **A query must involve only a single triple**. Then, the search system will
+provide the Assistant with the retrieval information with the format of "<|begin_of_documents|> ...search
+results... <|end_of_documents|>".
+"""
+
+SYSTEM_PROMPT = """Your are a helpful health assistant. Given a query you should answer it.
+"""
+
+CHROMA_PATH = 'chroma_db'

document/HimachalPradesh.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ba9023c7dee42eb0402883afc8d93a7648fde27d6201e6877d668616e5605d
+size 36581

document/IndiaSchemes.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb92146dcec5d999fa01ed6f7426ff578999d440851749ec7aa35bf15d0bce8
+size 33410

document/MadhyaPradesh.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15984a39341005cee1c114d9d13426d1eafbb4c97877138fccb1d6877c47194d
+size 6219668

document/Public_health_engineering_2010.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfd70c623753288bc44d16ab4146a8263e9eb9780a99a2adbfab0d743aa3d20
+size 20458801

document/UN_SDG_3_Detailed_Solutions.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ca1393a81d31fc2508057ba30f4a58e54d1412722fa9594c7351fd32bdc1ef
+size 28818

document/Uttar_Pradesh_UT_Healthcare_Schemes_.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8c8f891c06114b46f034bcc4605e5b9ce6cc15835731671d885d434ca7a0e6
+size 6226144

fetch.py

@@ -0,0 +1,38 @@
+import requests
+import json
+
+"""
+Contains the example code to retrieve response from the server in python-requests"""
+
+## without previous_state
+url = "http://localhost:8000/retrieve"
+headers = {
+    "accept": "application/json",
+    "Content-Type": "application/json"
+}
+data = {
+    "query": "what's my name?"
+}
+
+response = requests.post(url, headers=headers, json=data)
+
+print(response.json())
+
+## with previous_state
+
+url = "http://localhost:8000/retrieve"
+headers = {
+    "accept": "application/json",
+    "Content-Type": "application/json"
+}
+data = {
+    "previous_state": [
+        {"message": "hi", "response": "Hi there! How can I help you today?\n"},
+        {"message": "my name is arpit", "response": "hi arpit.  What's up with you?\n"}
+    ],
+    "query": "what's my name?"
+}
+
+response = requests.post(url, headers=headers, json=data)
+
+print(response.json())

generate.py

@@ -0,0 +1,8 @@
+from google import genai
+from dotenv import load_dotenv
+from os import getenv
+
+load_dotenv()
+
+GEMINI_API_KEY = getenv("GEMINI_API_KEY")
+from .constants import GEMINI_API_KEY

main.py

@@ -0,0 +1,32 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+import os
+from agent import agent_with_db
+from schemas import request
+from dotenv import load_dotenv
+load_dotenv()
+
+app = FastAPI()
+allowed_origins = os.getenv("ALLOWED_ORIGINS").split(',')
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=allowed_origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+global agent
+agent = agent_with_db()
+
+@app.post("/retrieve", status_code=200)
+async def retrieve(request:request):
+    prev_conv = request.previous_state
+    print(prev_conv)
+    if prev_conv is None:
+        prev_conv = "No previous conversation available, first time"
+    query = request.query
+    prev_conv = str(prev_conv)
+    response = agent({"query": query, "previous_conversation": prev_conv})
+
+    return {"response": response["result"]}  

requirements.txt

@@ -0,0 +1,206 @@
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+asgiref==3.8.1
+asttokens==3.0.0
+attrs==25.3.0
+backoff==2.2.1
+bcrypt==4.3.0
+beautifulsoup4==4.13.3
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.1.31
+cffi==1.17.1
+chardet==5.2.0
+charset-normalizer==3.4.1
+chroma-hnswlib==0.7.6
+chromadb==0.6.3
+click==8.1.8
+coloredlogs==15.0.1
+comm==0.2.2
+cryptography==44.0.2
+dataclasses-json==0.6.7
+debugpy==1.8.13
+decorator==5.2.1
+Deprecated==1.2.18
+distro==1.9.0
+dnspython==2.7.0
+durationpy==0.9
+email_validator==2.2.0
+emoji==2.14.1
+eval_type_backport==0.2.2
+executing==2.2.0
+fastapi==0.115.12
+fastapi-cli==0.0.7
+filelock==3.18.0
+filetype==1.2.0
+flatbuffers==25.2.10
+frozenlist==1.5.0
+fsspec==2025.3.0
+google-ai-generativelanguage==0.6.17
+google-api-core==2.24.2
+google-auth==2.38.0
+google-genai==1.7.0
+googleapis-common-protos==1.69.2
+greenlet==3.1.1
+grpcio==1.71.0
+grpcio-status==1.71.0
+h11==0.14.0
+html5lib==1.1
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.29.3
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+ipykernel==6.29.5
+ipython==9.0.2
+ipython_pygments_lexers==1.1.1
+itsdangerous==2.2.0
+jedi==0.19.2
+Jinja2==3.1.6
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kubernetes==32.0.1
+langchain==0.3.21
+langchain-community==0.3.20
+langchain-core==0.3.48
+langchain-google-genai==2.1.1
+langchain-huggingface==0.1.2
+langchain-text-splitters==0.3.7
+langdetect==1.0.9
+langsmith==0.3.18
+lxml==5.3.1
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.2.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+numpy==2.2.4
+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
+olefile==0.47
+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
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.1.0
+platformdirs==4.3.7
+posthog==3.21.0
+prompt_toolkit==3.0.50
+propcache==0.3.1
+proto-plus==1.26.1
+protobuf==5.29.4
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.10.6
+pydantic-extra-types==2.10.3
+pydantic-settings==2.8.1
+pydantic_core==2.27.2
+Pygments==2.19.1
+pypdf==5.4.0
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+python-dotenv==1.1.0
+python-iso639==2025.2.18
+python-magic==0.4.27
+python-multipart==0.0.20
+python-oxmsg==0.0.2
+PyYAML==6.0.2
+pyzmq==26.3.0
+RapidFuzz==3.12.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==13.9.4
+rich-toolkit==0.13.2
+rsa==4.9
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+sentence-transformers==3.4.1
+setuptools==78.1.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.39
+stack-data==0.6.3
+starlette==0.46.1
+sympy==1.13.1
+tenacity==9.0.0
+threadpoolctl==3.6.0
+tokenizers==0.21.1
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.50.1
+triton==3.2.0
+typer==0.15.2
+typing-inspect==0.9.0
+typing-inspection==0.4.0
+typing_extensions==4.13.0
+ujson==5.10.0
+unstructured==0.17.2
+unstructured-client==0.31.3
+urllib3==2.3.0
+uvicorn==0.34.0
+uvloop==0.21.0
+watchfiles==1.0.4
+wcwidth==0.2.13
+webencodings==0.5.1
+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

schemas.py

@@ -0,0 +1,6 @@
+from pydantic import BaseModel
+from typing import Optional, Literal, List, Dict, Any
+
+class request(BaseModel):
+    previous_state: Optional[List[Dict]]=None
+    query: str