Replace PaiEas LLM with LLI-integration and upgrade python to 3.11 (#148

)

* Replace PaiEas LLM with LLI-integration and upgrade python version to 3.11

* Replace MyFCDashScope with OpenAILike class

* Fix pyproject dependency

.github/workflows/ci.yml

@@ -19,12 +19,12 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.10
+      - name: Set up Python 3.11
         # This is the version of the action for setting up Python, not the Python version.
         uses: actions/setup-python@v5
         with:
           # Semantic version range syntax or exact version of a Python version
-          python-version: "3.10"
+          python-version: "3.11"
           # Optional - x64 or x86 architecture, defaults to x64
           architecture: "x64"
 

.github/workflows/main.yml

@@ -19,12 +19,12 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.10
+      - name: Set up Python 3.11
         # This is the version of the action for setting up Python, not the Python version.
         uses: actions/setup-python@v5
         with:
           # Semantic version range syntax or exact version of a Python version
-          python-version: "3.10"
+          python-version: "3.11"
           # Optional - x64 or x86 architecture, defaults to x64
           architecture: "x64"
 

.github/workflows/main_gpu.yml

@@ -19,12 +19,12 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.10
+      - name: Set up Python 3.11
         # This is the version of the action for setting up Python, not the Python version.
         uses: actions/setup-python@v5
         with:
           # Semantic version range syntax or exact version of a Python version
-          python-version: "3.10"
+          python-version: "3.11"
           # Optional - x64 or x86 architecture, defaults to x64
           architecture: "x64"
 

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10-slim AS builder
+FROM python:3.11-slim AS builder
 
 RUN pip3 install poetry
 
@@ -12,7 +12,7 @@ COPY . .
 
 RUN poetry install && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.10-slim AS prod
+FROM python:3.11-slim AS prod
 
 RUN rm -rf /etc/localtime && ln -s /usr/share/zoneinfo/Asia/Harbin  /etc/localtime
 

Dockerfile_gpu

@@ -1,4 +1,4 @@
-FROM python:3.10-slim AS builder
+FROM python:3.11-slim AS builder
 
 RUN pip3 install poetry
 
@@ -14,7 +14,7 @@ RUN mv pyproject_gpu.toml pyproject.toml \
 
 RUN poetry install && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.10-slim AS prod
+FROM python:3.11-slim AS prod
 
 RUN rm -rf /etc/localtime && ln -s /usr/share/zoneinfo/Asia/Harbin  /etc/localtime
 

Dockerfile_ui

@@ -1,4 +1,4 @@
-FROM python:3.10-slim AS builder
+FROM python:3.11-slim AS builder
 
 RUN pip3 install poetry
 
@@ -12,7 +12,7 @@ COPY . .
 
 RUN poetry install && rm -rf $POETRY_CACHE_DIR
 
-FROM python:3.10-slim AS prod
+FROM python:3.11-slim AS prod
 
 RUN rm -rf /etc/localtime && ln -s /usr/share/zoneinfo/Asia/Harbin  /etc/localtime
 

README.md

@@ -48,10 +48,10 @@ PAI-RAG is an easy-to-use opensource framework for modular RAG (Retrieval-Augmen
 
 2. Development Environment Settings
 
-   This project uses poetry for management. To ensure environmental consistency and avoid problems caused by Python version differences, we specify Python version 3.10.
+   This project uses poetry for management. To ensure environmental consistency and avoid problems caused by Python version differences, we specify Python version 3.11.
 
    ```bash
-   conda create -n rag_env python==3.10
+   conda create -n rag_env python==3.11
    conda activate rag_env
    ```
 

README_zh.md

@@ -43,10 +43,10 @@ PAI-RAG 是一个易于使用的模块化 RAG（检索增强生成）开源框
 
 2. 配置开发环境
 
-   本项目使用poetry进行管理，若在本地环境下使用，建议在安装环境之前先创建一个空环境。为了确保环境一致性并避免因Python版本差异造成的问题，我们指定Python版本为3.10。
+   本项目使用poetry进行管理，若在本地环境下使用，建议在安装环境之前先创建一个空环境。为了确保环境一致性并避免因Python版本差异造成的问题，我们指定Python版本为3.11。
 
    ```bash
-   conda create -n rag_env python==3.10
+   conda create -n rag_env python==3.11
    conda activate rag_env
    ```
 

pyproject.toml

@@ -10,14 +10,14 @@ authors = []
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.10.0,<3.12"
+python = ">=3.11.0,<3.12"
 fastapi = "^0.110.1"
 uvicorn = "^0.29.0"
-llama-index-core = ">=0.10.29,<=0.10.39"
+llama-index-core = "0.10.57"
 llama-index-embeddings-openai = "^0.1.7"
 llama-index-embeddings-azure-openai = "^0.1.7"
 llama-index-embeddings-dashscope = "^0.1.3"
-llama-index-llms-openai = "^0.1.15"
+llama-index-llms-openai = "^0.1.27"
 llama-index-llms-azure-openai = "^0.1.6"
 llama-index-llms-dashscope = "^0.1.2"
 llama-index-readers-database = "^0.1.3"
@@ -42,7 +42,7 @@ flagembedding = "^1.2.10"
 sentencepiece = "^0.2.0"
 oss2 = "^2.18.5"
 asgi-correlation-id = "^4.3.1"
-openinference-instrumentation-llama-index = "1.3.0"
+openinference-instrumentation-llama-index = "^1.3.0"
 torch = [
   {version = "2.3.0+cpu", source = "pytorch_cpu", platform = "linux"},
   {version = "2.3.0+cpu", source = "pytorch_cpu", platform = "win32"},
@@ -63,10 +63,10 @@ llama-parse = "0.4.2"
 pypdf2 = "^3.0.1"
 pdfplumber = "^0.11.0"
 pdfminer-six = "^20231228"
-openinference-semantic-conventions = "0.1.6"
+openinference-semantic-conventions = "^0.1.9"
 llama-index-tools-google = "^0.1.5"
 llama-index-tools-duckduckgo = "^0.1.1"
-openinference-instrumentation = "^0.1.7"
+openinference-instrumentation = "^0.1.12"
 llama-index-llms-huggingface = "^0.2.0"
 pytest-asyncio = "^0.23.7"
 pytest-cov = "^5.0.0"
@@ -83,6 +83,7 @@ llama-index-vector-stores-alibabacloud-opensearch = "^0.1.0"
 asyncpg = "^0.29.0"
 pgvector = "^0.3.2"
 pre-commit = "^3.8.0"
+llama-index-llms-paieas = "^0.1.0"
 
 [tool.poetry.scripts]
 pai_rag = "pai_rag.main:main"

pyproject_gpu.toml

@@ -10,14 +10,14 @@ authors = []
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.10.0,<3.12"
+python = ">=3.11.0,<3.12"
 fastapi = "^0.110.1"
 uvicorn = "^0.29.0"
-llama-index-core = ">=0.10.29,<=0.10.39"
+llama-index-core = "0.10.57"
 llama-index-embeddings-openai = "^0.1.7"
 llama-index-embeddings-azure-openai = "^0.1.7"
 llama-index-embeddings-dashscope = "^0.1.3"
-llama-index-llms-openai = "^0.1.15"
+llama-index-llms-openai = "^0.1.27"
 llama-index-llms-azure-openai = "^0.1.6"
 llama-index-llms-dashscope = "^0.1.2"
 llama-index-readers-database = "^0.1.3"
@@ -42,7 +42,7 @@ flagembedding = "^1.2.10"
 sentencepiece = "^0.2.0"
 oss2 = "^2.18.5"
 asgi-correlation-id = "^4.3.1"
-openinference-instrumentation-llama-index = "1.3.0"
+openinference-instrumentation-llama-index = "^1.3.0"
 torch = "2.2.2"
 torchvision = "0.17.2"
 openpyxl = "^3.1.2"
@@ -55,10 +55,10 @@ llama-parse = "0.4.2"
 pypdf2 = "^3.0.1"
 pdfplumber = "^0.11.0"
 pdfminer-six = "^20231228"
-openinference-semantic-conventions = "0.1.6"
+openinference-semantic-conventions = "^0.1.9"
 llama-index-tools-google = "^0.1.5"
 llama-index-tools-duckduckgo = "^0.1.1"
-openinference-instrumentation = "0.1.7"
+openinference-instrumentation = "^0.1.12"
 llama-index-llms-huggingface = "^0.2.0"
 pytest-asyncio = "^0.23.7"
 pytest-cov = "^5.0.0"
@@ -75,6 +75,7 @@ llama-index-vector-stores-alibabacloud-opensearch = "^0.1.0"
 asyncpg = "^0.29.0"
 pgvector = "^0.3.2"
 pre-commit = "^3.8.0"
+llama-index-llms-paieas = "^0.1.0"
 
 [tool.poetry.scripts]
 pai_rag = "pai_rag.main:main"

src/pai_rag/config/settings_fc_demo.toml

@@ -58,6 +58,11 @@ type = "SimpleChatEngine"
 [rag.multi_modal_llm]
 source = ""
 
+[rag.node_enhancement]
+tree_depth = 3
+max_clusters = 52
+proba_threshold = 0.10
+
 [rag.node_parser]
 type = "Sentence"
 chunk_size = 500