ArangoDB: Dataprep

comps/dataprep/arango/__init__.py

@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0

comps/dataprep/arango/langchain/Dockerfile

@@ -0,0 +1,38 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+ENV LANG=C.UTF-8
+
+ARG ARCH="cpu"
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    build-essential \
+    default-jre \
+    libgl1-mesa-glx \
+    libjemalloc-dev
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY comps /home/user/comps
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    if [ ${ARCH} = "cpu" ]; then pip install --no-cache-dir torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/user/comps/dataprep/arango/langchain/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+USER root
+
+RUN mkdir -p /home/user/comps/dataprep/arango/langchain/uploaded_files && chown -R user /home/user/comps/dataprep/arango/langchain/uploaded_files
+
+USER user
+
+WORKDIR /home/user/comps/dataprep/arango/langchain
+
+ENTRYPOINT ["python", "prepare_doc_arango.py"]

comps/dataprep/arango/langchain/README.md

@@ -0,0 +1,111 @@
+# Dataprep Microservice with ArangoDB
+
+## 🚀Start Microservice with Python
+
+### Install Requirements
+
+```bash
+pip install -r requirements.txt
+apt-get install libtesseract-dev -y
+apt-get install poppler-utils -y
+```
+
+### Start ArangoDB Server
+
+To launch ArangoDB locally, first ensure you have docker installed. Then, you can launch the database with the following docker command.
+
+```bash
+docker run -d --name arangodb -p 8529:8529 -e ARANGO_ROOT_PASSWORD=password arangodb/arangodb:latest
+```
+
+### Setup Environment Variables
+
+```bash
+export no_proxy=${your_no_proxy}
+export http_proxy=${your_http_proxy}
+export https_proxy=${your_http_proxy}
+export ARANGO_URL=${your_arango_url}
+export ARANGO_USERNAME=${your_arango_username}
+export ARANGO_PASSWORD=${your_arango_password}
+export ARANGO_DB_NAME=${your_db_name}
+export PYTHONPATH=${path_to_comps}
+```
+
+### Start Document Preparation Microservice for ArangoDB with Python Script
+
+Start document preparation microservice for ArangoDB with below command.
+
+```bash
+python prepare_doc_arango.py
+```
+
+## 🚀Start Microservice with Docker
+
+### Build Docker Image
+
+```bash
+cd ../../../../
+docker build -t opea/dataprep-arango:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/arango/langchain/Dockerfile .
+```
+
+### Run Docker with CLI
+
+```bash
+docker run -d --name="dataprep-arango-server" -p 6007:6007 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy opea/dataprep-arango:latest
+```
+
+### Setup Environment Variables
+
+```bash
+export no_proxy=${your_no_proxy}
+export http_proxy=${your_http_proxy}
+export https_proxy=${your_http_proxy}
+export ARANGO_URL=${your_arango_url}
+export ARANGO_USERNAME=${your_arango_username}
+export ARANGO_PASSWORD=${your_arango_password}
+export ARANGO_DB_NAME=${your_db_name}
+```
+
+### Run Docker with Docker Compose
+
+```bash
+cd comps/dataprep/arango/langchain
+docker compose -f docker-compose-dataprep-arango.yaml up -d
+```
+
+## Invoke Microservice
+
+Once document preparation microservice for ArangoDB is started, user can use below command to invoke the microservice to convert the document to embedding and save to the database.
+
+```bash
+curl -X POST \
+    -H "Content-Type: multipart/form-data" \
+    -F "files=@./file1.txt" \
+    http://localhost:6007/v1/dataprep
+```
+
+You can specify chunk_size and chunk_size by the following commands.
+
+```bash
+curl -X POST \
+    -H "Content-Type: multipart/form-data" \
+    -F "files=@./file1.txt" \
+    -F "chunk_size=1500" \
+    -F "chunk_overlap=100" \
+    http://localhost:6007/v1/dataprep
+```
+
+We support table extraction from pdf documents. You can specify process_table and table_strategy by the following commands. "table_strategy" refers to the strategies to understand tables for table retrieval. As the setting progresses from "fast" to "hq" to "llm," the focus shifts towards deeper table understanding at the expense of processing speed. The default strategy is "fast".
+
+Note: If you specify "table_strategy=llm", You should first start TGI Service, please refer to 1.2.1, 1.3.1 in https://github.com/opea-project/GenAIComps/tree/main/comps/llms/README.md, and then `export TGI_LLM_ENDPOINT="http://${your_ip}:8008"`.
+
+For ensure the quality and comprehensiveness of the extracted entities, we recommend to use `gpt-4o` as the default model for parsing the document. To enable the openai service, please `export OPENAI_API_KEY=xxxx` before using this services.
+
+```bash
+curl -X POST \
+    -H "Content-Type: multipart/form-data" \
+    -F "files=@./your_file.pdf" \
+    -F "process_table=true" \
+    -F "table_strategy=hq" \
+    http://localhost:6007/v1/dataprep
+```

comps/dataprep/arango/langchain/__init__.py

@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0

comps/dataprep/arango/langchain/config.py

@@ -0,0 +1,21 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+
+# ArangoDB configuration
+ARANGO_URL = os.getenv("ARANGO_URL", "http://localhost:8529")
+ARANGO_USERNAME = os.getenv("ARANGO_USERNAME", "root")
+ARANGO_PASSWORD = os.getenv("ARANGO_PASSWORD", "test")
+ARANGO_DB_NAME = os.getenv("ARANGO_DB_NAME", "_system")
+
+# Text Generation Inference configuration
+TGI_LLM_ENDPOINT = os.getenv("TGI_LLM_ENDPOINT", "http://localhost:8080")
+
+# Text Embeddings Inference configuration
+TEI_EMBEDDING_ENDPOINT = os.getenv("TEI_EMBEDDING_ENDPOINT")
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+TEI_EMBED_MODEL = os.getenv("TEI_EMBED_MODEL", "BAAI/bge-base-en-v1.5")
+
+# OpenAI configuration (alternative to TGI & TEI)
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

comps/dataprep/arango/langchain/docker-compose-dataprep-arango.yaml

@@ -0,0 +1,51 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+version: "3"
+services:
+  arango-vector-db:
+    image: arangodb/arangodb:latest
+    container_name: arango-graph-db
+    ports:
+      - "8529:8529"
+  tgi_gaudi_service:
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+    container_name: tgi-service
+    ports:
+      - "8088:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HF_TOKEN}
+    command: --model-id ${LLM_MODEL_ID} --auto-truncate --max-input-tokens 1024 --max-total-tokens 2048
+  dataprep-arango:
+    image: opea/gen-ai-comps:dataprep-arango-xeon-server
+    container_name: dataprep-arango-server
+    depends_on:
+      - arango-vector-db
+      - tgi_gaudi_service
+    ports:
+      - "6007:6007"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      ARANGO_URL: ${ARANGO_URL}
+      ARANGO_USERNAME: ${ARANGO_USERNAME}
+      ARANGO_PASSWORD: ${ARANGO_PASSWORD}
+      ARANGO_DB_NAME: ${ARANGO_DB_NAME}
+      TGI_LLM_ENDPOINT: ${TEI_ENDPOINT}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TEI_EMBED_MODEL: ${TEI_EMBED_MODEL}
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+    restart: unless-stopped
+
+networks:
+  default:
+    driver: bridge