Upload 10 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
+codebug.pdf filter=lfs diff=lfs merge=lfs -text
+falcon_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,31 @@
+## Use the official python 3.10 image
+FROM python:3.10.9
+
+## Set the working directory to /code
+WORKDIR /code
+
+## Copy the current directory contents into the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+## Install the requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+
+# Set up a new user named "user"
+RUN useradd user
+
+# Switch to the "user" user
+USER user
+
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at the user's home directory
+COPY --chown=user . $HOME/app
+
+## Start the FASTAPI App on port 7869
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,124 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from langchain.chains import create_history_aware_retriever, create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_groq import ChatGroq
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_chroma import Chroma
+import os
+import re
+import firebase_admin
+from firebase_admin import credentials, db
+from datetime import datetime
+
+# Firebase setup
+cred = credentials.Certificate("falcon-86e9e-firebase-adminsdk-fbsvc-6f3352dc87.json")
+firebase_admin.initialize_app(cred, {'databaseURL': 'https://falcon-86e9e-default-rtdb.firebaseio.com/'})
+
+# Load environment variables
+os.environ['HF_TOKEN'] = os.getenv("HF_TOKEN")
+os.environ['GROQ_API_KEY'] = os.getenv("GROQ_API_KEY")
+
+# Initialize FastAPI
+app = FastAPI()
+
+# CORS Middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Initialize global embeddings and retriever
+embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+llm = ChatGroq(model_name="Deepseek-R1-Distill-Llama-70b")
+vectorstore = Chroma(persist_directory="./falcon_db", embedding_function=embeddings)
+retriever = vectorstore.as_retriever()
+
+# Session store (Only chat history, avoids large objects)
+session_store = {}
+
+# Request model
+class QuestionRequest(BaseModel):
+    session_id: str
+    question: str
+
+# Function extraction helper
+def extract_function_call(answer):
+    match = re.search(r"<function>(\w+)\((.*?)\)</function>", answer)
+    if match:
+        function_name, params_str = match.groups()
+        params = dict(param.split("=") for param in params_str.split(","))
+        return function_name, {k.strip(): v.strip().strip('"') for k, v in params.items()}
+    return None, None
+
+# Firebase meeting scheduler
+def schedule_meeting(name: str, phoneNumber: str, availableTime: str, email: str, message: str):
+    meeting_details = {
+        'name': name,
+        'phoneNumber': phoneNumber,
+        'availableTime': availableTime,
+        'email': email,
+        'message': message,
+        'status': 'Scheduled',
+        'timestamp': datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+    }
+    db.reference('meetings').push(meeting_details)
+    return f"Meeting scheduled at {availableTime}. Confirmation sent to {email} & {phoneNumber}."
+
+FUNCTIONS = {"scheduleMeeting": schedule_meeting}
+
+@app.post("/ask_question/")
+async def ask_question(request: QuestionRequest):
+    session_id, question = request.session_id, request.question
+
+    # Use a shared retriever instead of per-session
+    history_aware_retriever = create_history_aware_retriever(llm, retriever, ChatPromptTemplate.from_messages([
+        ("system", "Rephrase user question into a standalone query."),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}")
+    ]))
+
+    # System prompt optimization (removed redundancy)
+    qa_prompt = ChatPromptTemplate.from_messages([
+        ("system", (
+            "You are Falcon, an AI assistant developed by Codebug Technologies. "
+            "Answer questions concisely or call a function when needed.\n\n"
+            "Function Format: <function>FUNCTION_NAME(ARG1=VALUE1, ARG2=VALUE2)</function>\n\n"
+            "Use retrieved context:\n{context}"
+        )),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}"),
+    ])
+
+    question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
+    rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)
+
+    # Store only chat history in session memory
+    if session_id not in session_store:
+        session_store[session_id] = {"history": []}  # Store only message history
+
+    session_history = session_store[session_id]["history"]
+    last_messages = session_history[-10:]  # Reduce stored messages
+
+    response = rag_chain.invoke(
+        {"input": question, "chat_history": last_messages},
+        config={"configurable": {"session_id": session_id}}
+    )
+
+    answer = response["answer"]
+    session_history.append({"role": "user", "content": question})
+    session_history.append({"role": "assistant", "content": answer})
+
+    # Function call execution
+    function_name, params = extract_function_call(answer)
+    if function_name and function_name in FUNCTIONS:
+        return {"answer": FUNCTIONS[function_name](**params)}
+
+    return {"answer": answer, "chat_history": last_messages}

codebug.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbf3eb5a7e0c3a5420fbd1112e43420138dbf1a2049774c30415c83cfe1ee02
+size 3895736

falcon-86e9e-firebase-adminsdk-fbsvc-6f3352dc87.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "falcon-86e9e",
+  "private_key_id": "6f3352dc873de37ae9c9d75ac8e70339ad726973",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\n4pYQv6L2E90tL8l8YiTGDA==\n-----END PRIVATE KEY-----\n",
+  "client_email": "firebase-adminsdk-fbsvc@falcon-86e9e.iam.gserviceaccount.com",
+  "client_id": "103712069535679525334",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-fbsvc%40falcon-86e9e.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

falcon_db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db7cc4f059991a96e01ac64303c23cbaee7621e9947a2c563d32b5816fb30e2
+size 315392

falcon_db/d647c821-3795-4f41-a46d-e2b9a858e73a/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c9fd302f000d7790aa403c2d0d8fec363fe46f30b07d53020b6e33b22435a9
+size 1676000

falcon_db/d647c821-3795-4f41-a46d-e2b9a858e73a/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87a1dc8bcae6f2c4bea6d5dd5005454d4dace8637dae29bff3c037ea771411e
+size 100

falcon_db/d647c821-3795-4f41-a46d-e2b9a858e73a/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f70c0fae47039c7965844a23420e5bc42afc04a516b8803d85b9c94b060f74
+size 4000

falcon_db/d647c821-3795-4f41-a46d-e2b9a858e73a/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
+size 0

requirements.txt

@@ -0,0 +1,211 @@
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.8.0
+arxiv==2.1.3
+asgiref==3.8.1
+asttokens==3.0.0
+async-timeout==4.0.3
+attrs==25.1.0
+backoff==2.2.1
+bcrypt==4.2.1
+beautifulsoup4==4.12.3
+blinker==1.9.0
+bs4==0.0.2
+build==1.2.2.post1
+CacheControl==0.14.2
+cachetools==5.5.1
+certifi==2024.12.14
+cffi==1.17.1
+charset-normalizer==3.4.1
+chroma-hnswlib==0.7.6
+chromadb==0.6.3
+click==8.1.8
+colorama==0.4.6
+coloredlogs==15.0.1
+comm==0.2.2
+cryptography==44.0.0
+dataclasses-json==0.6.7
+debugpy==1.8.12
+decorator==5.1.1
+Deprecated==1.2.18
+distro==1.9.0
+duckdb==1.1.3
+durationpy==0.9
+exceptiongroup==1.2.2
+executing==2.2.0
+faiss-cpu==1.9.0.post1
+fastapi==0.115.7
+feedparser==6.0.11
+filelock==3.17.0
+firebase-admin==6.6.0
+flatbuffers==25.1.24
+frozenlist==1.5.0
+fsspec==2024.12.0
+gitdb==4.0.12
+GitPython==3.1.44
+google-api-core==2.24.1
+google-api-python-client==2.160.0
+google-auth==2.38.0
+google-auth-httplib2==0.2.0
+google-cloud-core==2.4.1
+google-cloud-firestore==2.20.0
+google-cloud-storage==3.0.0
+google-crc32c==1.6.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.66.0
+greenlet==3.1.1
+groq==0.15.0
+grpcio==1.70.0
+grpcio-status==1.70.0
+h11==0.14.0
+httpcore==1.0.7
+httplib2==0.22.0
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.28.0
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.5.0
+importlib_resources==6.5.2
+ipykernel==6.29.5
+ipython==8.31.0
+jedi==0.19.2
+Jinja2==3.1.5
+jiter==0.8.2
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kubernetes==32.0.0
+langchain==0.3.16
+langchain-chroma==0.2.1
+langchain-community==0.3.16
+langchain-core==0.3.32
+langchain-groq==0.2.3
+langchain-huggingface==0.1.2
+langchain-openai==0.3.2
+langchain-text-splitters==0.3.5
+langsmith==0.3.2
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.0
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.24.1
+nest-asyncio==1.6.0
+networkx==3.4.2
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.20.1
+openai==1.60.2
+opentelemetry-api==1.29.0
+opentelemetry-exporter-otlp-proto-common==1.29.0
+opentelemetry-exporter-otlp-proto-grpc==1.29.0
+opentelemetry-instrumentation==0.50b0
+opentelemetry-instrumentation-asgi==0.50b0
+opentelemetry-instrumentation-fastapi==0.50b0
+opentelemetry-proto==1.29.0
+opentelemetry-sdk==1.29.0
+opentelemetry-semantic-conventions==0.50b0
+opentelemetry-util-http==0.50b0
+orjson==3.10.15
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pillow==11.1.0
+platformdirs==4.3.6
+posthog==3.11.0
+prompt_toolkit==3.0.50
+propcache==0.2.1
+proto-plus==1.26.0
+protobuf==5.29.3
+psutil==6.1.1
+pure_eval==0.2.3
+pyarrow==19.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.10.6
+pydantic-settings==2.7.1
+pydantic_core==2.27.2
+pydeck==0.9.1
+Pygments==2.19.1
+PyJWT==2.10.1
+PyMuPDF==1.25.2
+pyparsing==3.2.1
+pypdf==5.2.0
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+pyreadline3==3.5.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.20
+pytz==2024.2
+
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==13.9.4
+rpds-py==0.22.3
+rsa==4.9
+safetensors==0.5.2
+scikit-learn==1.6.1
+scipy==1.15.1
+sentence-transformers==3.4.0
+sgmllib3k==1.0.0
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.37
+stack-data==0.6.3
+starlette==0.45.3
+streamlit==1.41.1
+sympy==1.13.1
+tenacity==9.0.0
+threadpoolctl==3.5.0
+tiktoken==0.8.0
+tokenizers==0.21.0
+toml==0.10.2
+tomli==2.2.1
+torch==2.5.1
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.48.1
+typer==0.15.1
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2025.1
+uritemplate==4.1.1
+urllib3==2.3.0
+uvicorn==0.34.0
+watchdog==6.0.0
+watchfiles==1.0.4
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==14.2
+wikipedia==1.4.0
+wrapt==1.17.2
+yarl==1.18.3
+zipp==3.21.0
+zstandard==0.23.0