aiagents4pharma 1.44.0__py3-none-any.whl → 1.45.1__py3-none-any.whl

aiagents4pharma/talk2knowledgegraphs/docker-compose/cpu/docker-compose.yml

@@ -0,0 +1,93 @@
+version: "1.0.0"
+
+services:
+  # talk2knowledgegraphs with automatic data loading via entrypoint
+  talk2knowledgegraphs:
+    container_name: talk2knowledgegraphs
+    image: vpatientengine/talk2knowledgegraphs:latest
+    platform: linux/amd64
+    ports:
+      - "8501:8501"
+    environment:
+      - MILVUS_HOST=milvus-standalone
+      - MILVUS_PORT=19530
+    env_file:
+      - .env
+    volumes:
+      # Mount external data directory if DATA_DIR is specified in .env
+      - ${DATA_DIR:-./default_data}:/mnt/external_data:ro
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8501/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 120s # Allow time for data loading
+    depends_on:
+      milvus-standalone:
+        condition: service_healthy
+
+  # Milvus Dependencies
+  etcd:
+    container_name: milvus-etcd
+    image: quay.io/coreos/etcd:v3.5.18
+    environment:
+      - ETCD_AUTO_COMPACTION_MODE=revision
+      - ETCD_AUTO_COMPACTION_RETENTION=1000
+      - ETCD_QUOTA_BACKEND_BYTES=4294967296
+      - ETCD_SNAPSHOT_COUNT=50000
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/etcd:/etcd
+    command: etcd -advertise-client-urls=http://etcd:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
+    healthcheck:
+      test: ["CMD", "etcdctl", "endpoint", "health"]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+
+  minio:
+    container_name: milvus-minio
+    image: minio/minio:RELEASE.2024-05-28T17-19-04Z
+    environment:
+      MINIO_ACCESS_KEY: minioadmin
+      MINIO_SECRET_KEY: minioadmin
+    ports:
+      - "9001:9001"
+      - "9000:9000"
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/minio:/minio_data
+    command: minio server /minio_data --console-address ":9001"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+
+  # Milvus Vector Database (CPU-only)
+  milvus-standalone:
+    container_name: milvus-standalone
+    image: milvusdb/milvus:v2.5.14
+    command: ["milvus", "run", "standalone"]
+    security_opt:
+      - seccomp:unconfined
+    environment:
+      MINIO_REGION: us-east-1
+      ETCD_ENDPOINTS: etcd:2379
+      MINIO_ADDRESS: minio:9000
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/milvus:/var/lib/milvus
+    ports:
+      - "19530:19530"
+      - "9091:9091"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
+      interval: 30s
+      start_period: 90s
+      timeout: 20s
+      retries: 3
+    depends_on:
+      - "etcd"
+      - "minio"
+
+networks:
+  milvus:
+    name: milvus

aiagents4pharma/talk2knowledgegraphs/docker-compose/gpu/.env.example

@@ -0,0 +1,23 @@
+# .env.example (DO NOT put actual API keys here, read the README.md)
+
+# OPENAI API KEY
+OPENAI_API_KEY=your_openai_api_key_here
+
+# LangSmith API KEY
+LANGCHAIN_TRACING_V2=true
+LANGCHAIN_API_KEY=your_langchain_api_key_here
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# Set environment variables for data loader
+MILVUS_HOST=localhost
+MILVUS_PORT=19530
+MILVUS_USER=root
+MILVUS_PASSWORD=Milvus
+MILVUS_DATABASE=your_database_name_here
+
+# Specify the data directory for multimodal data to your own data directory
+# DATA_DIR=/your_absolute_path_to_your_data_dir/
+
+BATCH_SIZE=500

aiagents4pharma/talk2knowledgegraphs/docker-compose/gpu/docker-compose.yml

@@ -0,0 +1,108 @@
+version: "1.0.0"
+
+services:
+  # talk2knowledgegraphs with automatic data loading via entrypoint
+  talk2knowledgegraphs:
+    container_name: talk2knowledgegraphs
+    image: vpatientengine/talk2knowledgegraphs:latest
+    platform: linux/amd64
+    ports:
+      - "8501:8501"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              capabilities: ["gpu"]
+              device_ids: ["0"]
+    environment:
+      - MILVUS_HOST=milvus-standalone
+      - MILVUS_PORT=19530
+    env_file:
+      - .env
+    volumes:
+      # Mount external data directory if DATA_DIR is specified in .env
+      - ${DATA_DIR:-./default_data}:/mnt/external_data:ro
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8501/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 120s # Allow time for data loading
+    depends_on:
+      milvus-standalone:
+        condition: service_healthy
+
+  # Milvus Dependencies
+  etcd:
+    container_name: milvus-etcd
+    image: quay.io/coreos/etcd:v3.5.18
+    environment:
+      - ETCD_AUTO_COMPACTION_MODE=revision
+      - ETCD_AUTO_COMPACTION_RETENTION=1000
+      - ETCD_QUOTA_BACKEND_BYTES=4294967296
+      - ETCD_SNAPSHOT_COUNT=50000
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/etcd:/etcd
+    command: etcd -advertise-client-urls=http://etcd:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
+    healthcheck:
+      test: ["CMD", "etcdctl", "endpoint", "health"]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+
+  minio:
+    container_name: milvus-minio
+    image: minio/minio:RELEASE.2023-03-20T20-16-18Z
+    environment:
+      MINIO_ACCESS_KEY: minioadmin
+      MINIO_SECRET_KEY: minioadmin
+    ports:
+      - "9001:9001"
+      - "9000:9000"
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/minio:/minio_data
+    command: minio server /minio_data --console-address ":9001"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+
+  # Milvus Vector Database (GPU-enabled)
+  milvus-standalone:
+    container_name: milvus-standalone
+    image: milvusdb/milvus:v2.6.0-rc1-gpu
+    command: ["milvus", "run", "standalone"]
+    security_opt:
+      - seccomp:unconfined
+    environment:
+      MINIO_REGION: us-east-1
+      ETCD_ENDPOINTS: etcd:2379
+      MINIO_ADDRESS: minio:9000
+      MQ_TYPE: woodpecker
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/volumes/milvus:/var/lib/milvus
+    ports:
+      - "19530:19530"
+      - "9091:9091"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              capabilities: ["gpu"]
+              device_ids: ["0"]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
+      interval: 30s
+      start_period: 90s
+      timeout: 20s
+      retries: 3
+    depends_on:
+      - "etcd"
+      - "minio"
+
+networks:
+  milvus:
+    name: milvus

aiagents4pharma/talk2knowledgegraphs/entrypoint.sh

@@ -0,0 +1,190 @@
+#!/bin/bash
+# entrypoint.sh - Container entrypoint with automatic data loading
+
+set -e
+
+# Function to log with timestamp
+log() {
+	echo "[$(date '+%Y-%m-%d %H:%M:%S')] [ENTRYPOINT] $1"
+}
+
+log "=== talk2knowledgegraphs Container Starting ==="
+log "Container hostname: $(hostname)"
+
+# Show GPU info if available
+if command -v nvidia-smi >/dev/null 2>&1; then
+	log "Available GPUs:"
+	nvidia-smi -L 2>/dev/null || log "nvidia-smi failed"
+else
+	log "nvidia-smi not available"
+fi
+
+# Set default values for data loader environment variables
+export MILVUS_HOST=${MILVUS_HOST:-milvus-standalone}
+export MILVUS_PORT=${MILVUS_PORT:-19530}
+export MILVUS_USER=${MILVUS_USER:-root}
+export MILVUS_PASSWORD=${MILVUS_PASSWORD:-Milvus}
+export MILVUS_DATABASE=${MILVUS_DATABASE:-t2kg_primekg}
+export BATCH_SIZE=${BATCH_SIZE:-500}
+export CHUNK_SIZE=${CHUNK_SIZE:-5}
+export AUTO_INSTALL_PACKAGES=${AUTO_INSTALL_PACKAGES:-true}
+export FORCE_CPU=${FORCE_CPU:-false}
+export RUN_DATA_LOADER=${RUN_DATA_LOADER:-true}
+
+# Determine data directory with priority:
+# 1. External mount (/mnt/external_data)
+# 2. Environment variable DATA_DIR
+# 3. Default internal path
+if [ -d "/mnt/external_data" ] && [ "$(ls -A /mnt/external_data 2>/dev/null)" ]; then
+	export DATA_DIR="/mnt/external_data"
+	log "Using external data directory: $DATA_DIR"
+elif [ -n "$DATA_DIR" ] && [ -d "$DATA_DIR" ]; then
+	log "Using specified data directory: $DATA_DIR"
+elif [ -d "/app/aiagents4pharma/talk2knowledgegraphs/tests/files/biobridge_multimodal/" ]; then
+	export DATA_DIR="/app/aiagents4pharma/talk2knowledgegraphs/tests/files/biobridge_multimodal/"
+	log "Using default internal data directory: $DATA_DIR"
+else
+	log "WARNING: No valid data directory found!"
+	log "Checked:"
+	log "  - External mount: /mnt/external_data"
+	log "  - Environment DATA_DIR: ${DATA_DIR:-not set}"
+	log "  - Default internal: /app/aiagents4pharma/talk2knowledgegraphs/tests/files/biobridge_multimodal/"
+	log "Continuing without data loading..."
+	export RUN_DATA_LOADER="false"
+fi
+
+# Display configuration
+log "=== Configuration ==="
+log "MILVUS_HOST: $MILVUS_HOST"
+log "MILVUS_PORT: $MILVUS_PORT"
+log "MILVUS_DATABASE: $MILVUS_DATABASE"
+log "DATA_DIR: $DATA_DIR"
+log "BATCH_SIZE: $BATCH_SIZE"
+log "FORCE_CPU: $FORCE_CPU"
+log "RUN_DATA_LOADER: $RUN_DATA_LOADER"
+
+# Function to check if Milvus is ready
+check_milvus() {
+	python3 -c "
+import sys
+try:
+    from pymilvus import connections
+    connections.connect(host='$MILVUS_HOST', port='$MILVUS_PORT', user='$MILVUS_USER', password='$MILVUS_PASSWORD')
+    connections.disconnect('default')
+    sys.exit(0)
+except Exception:
+    sys.exit(1)
+" >/dev/null 2>&1
+}
+
+# Function to check if data already exists
+check_existing_data() {
+	python3 -c "
+import sys
+try:
+    from pymilvus import connections, utility, db
+    connections.connect(host='$MILVUS_HOST', port='$MILVUS_PORT', user='$MILVUS_USER', password='$MILVUS_PASSWORD')
+
+    # Check if database exists
+    if '$MILVUS_DATABASE' in db.list_database():
+        db.using_database('$MILVUS_DATABASE')
+        collections = utility.list_collections()
+        if collections:
+            connections.disconnect('default')
+            sys.exit(0)  # Data exists
+
+    connections.disconnect('default')
+    sys.exit(1)  # No data found
+except Exception:
+    sys.exit(1)
+" >/dev/null 2>&1
+}
+
+# Wait for Milvus to be ready (only if data loader is enabled)
+if [ "$RUN_DATA_LOADER" = "true" ]; then
+	log "Waiting for Milvus to be ready..."
+	max_attempts=30
+	attempt=1
+
+	while [ $attempt -le $max_attempts ]; do
+		if check_milvus; then
+			log "Milvus is ready!"
+			break
+		else
+			log "Milvus not ready yet (attempt $attempt/$max_attempts), waiting 10 seconds..."
+			sleep 10
+			attempt=$((attempt + 1))
+		fi
+	done
+
+	if [ $attempt -gt $max_attempts ]; then
+		log "ERROR: Milvus failed to become ready after $max_attempts attempts"
+		log "Continuing without data loading..."
+		export RUN_DATA_LOADER="false"
+	fi
+fi
+
+# Run data loader if enabled and Milvus is ready
+if [ "$RUN_DATA_LOADER" = "true" ]; then
+	if check_existing_data; then
+		log "Data already exists in Milvus, skipping data loading"
+		echo "SKIPPED" >/tmp/data_loading_status
+	else
+		log "No existing data found, starting data loading process..."
+		echo "IN_PROGRESS" >/tmp/data_loading_status
+
+		# Verify data directory contents
+		if [ ! -d "$DATA_DIR" ]; then
+			log "ERROR: Data directory does not exist: $DATA_DIR"
+			echo "FAILED" >/tmp/data_loading_status
+		else
+			log "Data directory contents preview:"
+			find "$DATA_DIR" -name "*.parquet*" | head -5 | while read file; do
+				log "  Found: $file"
+			done
+
+			# Check if data loader script exists
+			if [ -f "/app/aiagents4pharma/talk2knowledgegraphs/milvus_data_dump.py" ]; then
+				log "Starting Milvus data loader..."
+				cd /app/aiagents4pharma/talk2knowledgegraphs
+
+				if python3 milvus_data_dump.py; then
+					log "Data loading completed successfully!"
+					echo "SUCCESS" >/tmp/data_loading_status
+				else
+					log "ERROR: Data loading failed! Continuing with application startup..."
+					echo "FAILED" >/tmp/data_loading_status
+				fi
+			else
+				log "ERROR: Data loader script not found at /app/aiagents4pharma/talk2knowledgegraphs/milvus_data_dump.py"
+				log "Continuing with application startup..."
+				echo "FAILED" >/tmp/data_loading_status
+			fi
+		fi
+	fi
+else
+	log "Data loader disabled"
+	echo "DISABLED" >/tmp/data_loading_status
+fi
+
+# Start the main application
+log "Data loading phase completed. Starting main application..."
+
+# Ensure Python path includes the app directory
+export PYTHONPATH="/app:${PYTHONPATH}"
+
+# Create cache directory and set path for container
+cache_dir="/app/aiagents4pharma/talk2knowledgegraphs/tests/files"
+if [ ! -d "$cache_dir" ]; then
+	log "Creating cache directory: $cache_dir"
+	mkdir -p "$cache_dir"
+fi
+
+# Set container-specific cache path
+export CACHE_EDGE_INDEX_PATH="/app/aiagents4pharma/talk2knowledgegraphs/tests/files/t2kg_primekg_edge_index.pkl"
+
+log "Starting main application..."
+log "Python path: $PYTHONPATH"
+log "Cache edge index path: $CACHE_EDGE_INDEX_PATH"
+log "Executing command: $@"
+exec "$@"

aiagents4pharma/talk2knowledgegraphs/install.md

@@ -0,0 +1,140 @@
+**Talk2KnowledgeGraphs** is an AI agent designed to interact with biomedical knowledge graphs. Biomedical knowledge graphs contains crucial information in the form of entities (nodes) and their relationships (edges). These graphs are used to represent complex biological systems, such as metabolic pathways, protein-protein interactions, and gene regulatory networks. In order to easily interact with this information, Talk2KnowledgeGraphs uses natural language processing (NLP) to enable users to ask questions and make requests. By simply asking questions or making requests, users can:
+
+- Dataset loading: load knowledge graph from datasets.
+- Embedding: embed entities and relationships in the knowledge graph.
+- Knowledge graph construction: construct a knowledge graph from dataframes.
+- Subgraph extraction: extract subgraphs from the initial knowledge graph.
+- Retrieval: retrieve information from the (sub-) knowledge graph.
+- Reasoning: reason over the (sub-) knowledge graph.
+- Visualization: visualize the (sub-) knowledge graph.
+
+📝 By default, `talk2knowledgegraphs` includes a small subset of the PrimeKG knowledge graph, allowing users to start interacting with it out of the box.
+To switch to a different knowledge graph or use your own, refer to the [deployment guide](https://virtualpatientengine.github.io/AIAgents4Pharma/talk2knowledgegraphs/deployment/).
+
+## Installation
+
+If your machine has NVIDIA GPU(s), please install the following this:
+
+- [nvidia-cuda-toolkit](https://developer.nvidia.com/cuda-toolkit)
+- [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/1.17.8/install-guide.html) (required for GPU support with Docker; enables containers to access NVIDIA GPUs for accelerated computing). After installing `nvidia-container-toolkit`, please restart Docker to ensure GPU support is enabled.
+
+### Docker (stable-release)
+
+_This agent is available on Docker Hub._
+
+**Prerequisites**
+
+- If your machine has NVIDIA GPU(s), please install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/1.17.8/install-guide.html) (required for GPU support with Docker; enables containers to access NVIDIA GPUs for accelerated computing). After installing `nvidia-container-toolkit`, please restart Docker to ensure GPU support is enabled.
+
+- [Milvus](https://milvus.io) (for a vector database)
+
+---
+
+#### 1. Download files
+
+Choose the appropriate version of the `docker-compose.yml` file based on your system:
+
+**For GPU:**
+
+```sh
+wget https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2knowledgegraphs/docker-compose/gpu/docker-compose.yml \
+     https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2knowledgegraphs/docker-compose/gpu/.env.example
+```
+
+**For CPU:**
+
+```sh
+wget https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2knowledgegraphs/docker-compose/cpu/docker-compose.yml \
+     https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2knowledgegraphs/docker-compose/cpu/.env.example
+```
+
+#### 2. Setup environment variables
+
+```sh
+cp .env.example .env
+```
+
+Edit `.env` with your API keys:
+
+```env
+# .env.example (DO NOT put actual API keys here, read the README.md)
+
+# OPENAI API KEY
+OPENAI_API_KEY=your_openai_api_key_here
+
+# LangSmith API KEY
+LANGCHAIN_TRACING_V2=true
+LANGCHAIN_API_KEY=your_langchain_api_key_here
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# Set environment variables for data loader
+MILVUS_HOST=localhost
+MILVUS_PORT=19530
+MILVUS_USER=root
+MILVUS_PASSWORD=Milvus
+MILVUS_DATABASE=your_database_name_here
+
+# Specify the data directory for multimodal data to your own data directory
+# DATA_DIR=/your_absolute_path_to_your_data_dir/
+
+BATCH_SIZE=500
+```
+
+---
+
+#### 3. Start the agent
+
+```sh
+docker compose up -d
+```
+
+---
+
+### Access the Web UI
+
+Once started, open:
+
+```
+http://localhost:8501
+```
+
+> In the background, the BioBridge multimodal embeddings will be inserted into the Milvus database, and the `talk2knowledgegraphs` service will start. Once the data is fully inserted, the application will be in a healthy state and accessible at the above address.
+>
+> You can monitor the process using:
+>
+> ```sh
+> docker logs -f talk2knowledgegraphs
+> ```
+
+---
+
+## Get Key
+
+- `NVIDIA_API_KEY` – required (obtain a free key at [https://build.nvidia.com/explore/discover](https://build.nvidia.com/explore/discover))
+
+**LangSmith** support is optional. To enable it, create an API key [here](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key).
+
+_Please note that this will create a new tracing project in your Langsmith
+account with the name `T2X-xxxx`, where `X` can be `KG` (KnowledgeGraphs).
+If you skip the previous step, it will default to the name `default`.
+`xxxx` will be the 4-digit ID created for the session._
+
+---
+
+## Notes for Windows Users
+
+If you are using Windows, it is recommended to install [**Git Bash**](https://git-scm.com/downloads) for a smoother experience when running the bash commands in this guide.
+
+- For applications that use **Docker Compose**, Git Bash is **required**.
+- For applications that use **docker run** manually, Git Bash is **optional**, but recommended for consistency.
+
+You can download Git Bash here: [Git for Windows](https://git-scm.com/downloads).
+
+When using Docker on Windows, make sure you **run Docker with administrative privileges** if you face permission issues.
+
+To resolve permission issues, you can:
+
+- Review the official Docker documentation on [Windows permission requirements](https://docs.docker.com/desktop/setup/install/windows-permission-requirements/).
+- Alternatively, follow the community discussion and solutions on [Docker Community Forums](https://forums.docker.com/t/error-when-trying-to-run-windows-containers-docker-client-must-be-run-with-elevated-privileges/136619).