Merge branch 'master' into Feature/108-환경변수-및-prompt-경로로-받아-업데이트

Author: ehddnr301

.env.example

@@ -3,18 +3,18 @@
 ###############################################
 
 # LLM_PROVIDER=openai
-# OPEN_AI_LLM_KEY=
-# OPEN_AI_LLM_MODEL=gpt-4o
+# OPEN_AI_KEY=sk-proj-----
+# OPEN_AI_LLM_MODEL=gpt-4.1
 
 # LLM_PROVIDER=gemini
 # GEMINI_API_KEY=
 # GEMINI_LLM_MODEL=gemini-2.0-flash-lite
 
-# LLM_PROVIDER=azure
-# AZURE_OPENAI_LLM_ENDPOINT=
-# AZURE_OPENAI_LLM_KEY=
-# AZURE_OPENAI_LLM_MODEL=
-# AZURE_OPENAI_LLM_API_VERSION=
+LLM_PROVIDER=azure
+AZURE_OPENAI_LLM_ENDPOINT=https://-------.openai.azure.com/
+AZURE_OPENAI_LLM_KEY=-
+AZURE_OPENAI_LLM_MODEL=gpt4o
+AZURE_OPENAI_LLM_API_VERSION=2024-07-01-preview
 
 # LLM_PROVIDER=ollama
 # OLLAMA_LLM_BASE_URL=
@@ -36,31 +36,101 @@
 ########### Embedding API SElECTION ###########
 ###############################################
 # Only used if you are using an LLM that does not natively support embedding (openai or Azure)
-# EMBEDDING_ENGINE='openai'
-# OPEN_AI_KEY=sk-xxxx
-# EMBEDDING_MODEL_PREF='text-embedding-ada-002'
+# EMBEDDING_PROVIDER='openai'
+# OPEN_AI_EMBEDDING_MODEL='text-embedding-ada-002'
 
-# EMBEDDING_ENGINE='azure'
-# AZURE_OPENAI_ENDPOINT=
-# AZURE_OPENAI_KEY=
-# EMBEDDING_MODEL_PREF='my-embedder-model' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002
+# EMBEDDING_PROVIDER=azure
+# AZURE_OPENAI_EMBEDDING_ENDPOINT=https://-------.openai.azure.com/openai/deployments
+# AZURE_OPENAI_EMBEDDING_KEY=-
+# AZURE_OPENAI_EMBEDDING_MODEL='textembeddingada002' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002
+# AZURE_OPENAI_EMBEDDING_API_VERSION=2023-09-15-preview
 
-# EMBEDDING_ENGINE='ollama'
+# EMBEDDING_PROVIDER='ollama'
 # EMBEDDING_BASE_PATH='http://host.docker.internal:11434'
-# EMBEDDING_MODEL_PREF='nomic-embed-text:latest'
+# EMBEDDING_MODEL='nomic-embed-text:latest'
 # EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
 
-# EMBEDDING_ENGINE='bedrock'
-# AWS_BEDROCK_EMBEDDING_ACCESS_KEY_ID=
-# AWS_BEDROCK_EMBEDDING_ACCESS_KEY=
-# AWS_BEDROCK_EMBEDDING_REGION=us-west-2
-# AWS_BEDROCK_EMBEDDING_MODEL_PREF=amazon.embedding-embedding-ada-002:0
+EMBEDDING_PROVIDER='bedrock'
+AWS_BEDROCK_EMBEDDING_ACCESS_KEY_ID=--
+AWS_BEDROCK_EMBEDDING_SECRET_ACCESS_KEY=-/-+-+-
+AWS_BEDROCK_EMBEDDING_REGION=us-west-2
+AWS_BEDROCK_EMBEDDING_MODEL=amazon.titan-embed-text-v2:0
 
-# EMBEDDING_ENGINE='gemini'
+# EMBEDDING_PROVIDER='gemini'
 # GEMINI_EMBEDDING_API_KEY=
-# EMBEDDING_MODEL_PREF='text-embedding-004'
+# EMBEDDING_MODEL='text-embedding-004'
 
-# EMBEDDING_ENGINE='huggingface'
+# EMBEDDING_PROVIDER='huggingface'
 # HUGGING_FACE_EMBEDDING_REPO_ID=
 # HUGGING_FACE_EMBEDDING_MODEL=
+
 # HUGGING_FACE_EMBEDDING_API_TOKEN=
+
+DATAHUB_SERVER = 'http://-.-.-.-:-'
+
+
+###############################################
+######## Database Connector SELECTION #########
+###############################################
+
+# clickhouse
+# DB_TYPE=clickhouse
+# CLICKHOUSE_HOST=_._._._
+# CLICKHOUSE_PORT=9000
+# CLICKHOUSE_USER=_
+# CLICKHOUSE_PASSWORD=_
+# CLICKHOUSE_DATABASE=_
+
+# databricks
+# DB_TYPE=databricks
+# DATABRICKS_HOST=_
+# DATABRICKS_HTTP_PATH=_
+# DATABRICKS_ACCESS_TOKEN=_
+
+# duckdb
+# DB_TYPE=duckdb
+# DUCKDB_PATH=./data/duckdb.db
+
+# mariadb
+# DB_TYPE=mariadb
+# MARIADB_HOST=_
+# MARIADB_PORT=3306
+# MARIADB_USER=_
+# MARIADB_PASSWORD=_
+# MARIADB_DATABASE=_
+
+# mysql
+# DB_TYPE=mysql
+# MYSQL_HOST=_
+# MYSQL_PORT=3306
+# MYSQL_USER=_
+# MYSQL_PASSWORD=_
+# MYSQL_DATABASE=_
+
+# oracle
+# DB_TYPE=oracle
+# ORACLE_HOST=_
+# ORACLE_PORT=1521
+# ORACLE_USER=_
+# ORACLE_PASSWORD=_
+# ORACLE_DATABASE=_
+# ORACLE_SERVICE_NAME=_
+
+# postgres
+# DB_TYPE=postgres
+# POSTGRES_HOST=_
+# POSTGRES_PORT=5432
+# POSTGRES_USER=_
+# POSTGRES_PASSWORD=_
+# POSTGRES_DATABASE=_
+
+# snowflake
+# DB_TYPE=snowflake
+# SNOWFLAKE_USER=_
+# SNOWFLAKE_PASSWORD=_
+# SNOWFLAKE_ACCOUNT=_
+
+# sqlite
+# DB_TYPE=sqlite
+# SQLITE_PATH=./data/sqlite.db
+

.gitignore

@@ -10,4 +10,4 @@ test_lhm/
 .cursorignore
 .vscode
 table_info_db
-ko_reranker_local
+ko_reranker_local

Dockerfile

@@ -0,0 +1,32 @@
+# Python 3.10 slim 이미지 기반
+FROM python:3.12-slim
+
+# 시스템 라이브러리 설치
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    software-properties-common \
+    git \
+    libpq-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# 작업 디렉토리 설정
+WORKDIR /app
+
+# 의존성 파일 복사 및 설치
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 전체 서비스 코드 복사
+COPY . .
+
+# Python 환경 설정
+ENV PYTHONPATH=/app
+ENV PYTHONUNBUFFERED=1
+
+# Streamlit 포트 노출
+EXPOSE 8501
+
+# Streamlit 실행 명령
+CMD ["python", "-c", "from llm_utils.tools import set_gms_server; import os; set_gms_server(os.getenv('DATAHUB_SERVER', 'http://localhost:8080'))"]
+CMD ["streamlit", "run", "./interface/streamlit_app.py", "--server.port=8501"]