Init structure fastapi project

.env.example

@@ -0,0 +1,33 @@
+# General settings
+PROJECT_NAME=
+API_V1_STR=
+SECRET_KEY=
+ACCESS_TOKEN_EXPIRE_MINUTES=
+
+# CORS Origins
+BACKEND_CORS_ORIGINS=["http://localhost", "http://localhost:3000"]
+FRONTEND_HOST=http://localhost:3000
+
+# Environment and logging
+ENVIRONMENT=local               # Options: local, staging, production
+LOG_LEVEL=DEBUG                 # Options: DEBUG, INFO, ERROR, WARNING
+SENTRY_DSN=                     # Add your Sentry DSN if available
+
+# Database configuration
+POSTGRES_SERVER=localhost
+POSTGRES_PORT=5432
+POSTGRES_USER=user
+POSTGRES_PASSWORD=password
+POSTGRES_DB=app_database
+
+# LLM Configuration
+LLM_TEMPERATURE=0.5
+LLM_MAX_TOKENS=
+EMBEDDING_DIM=1024
+
+# OpenAI Configuration
+LLM_OPENAI_MODEL=
+OPENAI_API_KEY=
+
+# Optional Worker Configuration
+UVICORN_WORKER_COUNT=

.gitignore

@@ -160,3 +160,4 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+.python-version

main.py

@@ -0,0 +1,35 @@
+import uvicorn
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from qllm.api.routers import api_router
+
+# from qllm.core.utils import mount_static_files
+from qllm.init_setting import init_openai
+
+app = FastAPI()
+
+init_openai()
+
+origins = [
+    "http://localhost",
+    "http://localhost:8080",
+]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+app.include_router(api_router, prefix="/api/v1")
+
+# Mount the data files to serve the file viewer
+# mount_static_files("data", "/api/files/data")
+# Mount the output files from tools
+# mount_static_files("output", "/api/files/output")
+
+
+if __name__ == "__main__":
+    uvicorn.run(app="main:app", host="127.0.0.1", port=5601, reload=True)

pyproject.toml

@@ -13,10 +13,22 @@ authors = ["LongBaoCoder2 <[email protected]>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = "^3.9"
-pymilvus = "^2.4.9"
+python = ">=3.11,<3.13"
 qdrant-client = "^1.12.1"
-weaviate-client = "^4.9.4"
+pymilvus = "^2.4.9"
+mem0ai = "^0.1.30"
+openai = "^1.55.0"
+llama-index = "^0.12.1"
+llama-index-memory-mem0 = "^0.2.0"
+llama-index-vector-stores-qdrant = "^0.4.0"
+llama-index-readers-file = "^0.4.0"
+llama-index-embeddings-fastembed = "^0.3.0"
+llama-index-llms-openai = "^0.3.1"
+llama-index-agent-openai = "^0.4.0"
+llama-index-core = "^0.12.1"
+fastembed = "^0.4.2"
+pydantic-settings = "^2.6.1"
+psycopg2 = "^2.9.10"
 
 
 [tool.poetry.group.dev.dependencies]

qllm/alembic.ini

@@ -0,0 +1,117 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = postgresql://user:[email protected]:5432/llama_app_db
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

qllm/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

qllm/alembic/env.py

@@ -0,0 +1,80 @@
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from qllm.core.config import settings
+from qllm.models.base import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+db_url = config.get_main_option("sqlalchemy.url")
+if settings.SQLALCHEMY_DATABASE_URI is not None:
+    db_url = settings.SQLALCHEMY_DATABASE_URI
+    print(f"Using DATABASE_URL {db_url} from environment for migrations")
+config.set_main_option("sqlalchemy.url", db_url)
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    context.configure(
+        url=config.get_main_option("sqlalchemy.url"),
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

qllm/alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

qllm/api/deps.py

@@ -0,0 +1,10 @@
+from typing import AsyncGenerator
+
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from qllm.services.db import SessionLocal
+
+
+async def get_db() -> AsyncGenerator[AsyncSession, None, None]:
+    async with SessionLocal() as db:
+        yield db

qllm/api/models/chat_model.py

@@ -0,0 +1,7 @@
+from llama_index.core.llms import MessageRole
+from pydantic import BaseModel
+
+
+class Message(BaseModel):
+    role: MessageRole
+    content: str

qllm/api/routers/__init__.py

@@ -0,0 +1,8 @@
+from fastapi import APIRouter
+
+from .chat import chat_router
+from .upload import upload_router
+
+api_router = APIRouter()
+api_router.include_router(router=chat, prefix="/chat")
+api_router.include_router(router=upload, prefix="/upload")

qllm/api/routers/chat.py

@@ -0,0 +1,33 @@
+from fastapi import APIRouter, HTTPException, status
+
+from qllm.api.schema.chat import ChatRequest, ChatResponse, Message
+from qllm.engine.engine import get_chat_engine
+
+chat_router = APIRouter()
+
+
+@chat_router.post("", response_model=ChatResponse)
+async def chat_controller(chat_request: ChatRequest):
+    chat_engine = get_chat_engine()
+    if chat_engine is None:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail="Cannot set up chat engine.",
+        )
+
+    message = chat_request.message
+    history = chat_request.history or []
+    chat_response = await chat_engine.achat(message, history)
+
+    # Build the updated history including the assistant's response
+    updated_history = history.append(
+        Message(role="assistant", content=chat_response.response)
+    )
+
+    # Construct the response
+    response = ChatResponse(
+        response=chat_response.response,
+        history=updated_history,
+    )
+
+    return response