aiagents4pharma 0.0.0__py3-none-any.whl

aiagents4pharma/talk2scholars/configs/tools/question_and_answer/default.yaml

@@ -0,0 +1,62 @@
+# Configuration for the PDF question_and_answer Tool - Traditional RAG Pipeline with GPU Support
+
+# Milvus vector database settings
+milvus:
+  # Connection settings
+  host: ${oc.env:MILVUS_HOST,localhost} # Changed default from 127.0.0.1 to localhost
+  port: ${oc.env:MILVUS_PORT,19530}
+
+  # Database and collection settings
+  db_name: ${oc.env:MILVUS_DB_NAME,pdf_rag_db}
+  collection_name: ${oc.env:MILVUS_COLLECTION_NAME,pdf_rag_documents}
+
+  # Ensure collection persists across restarts
+  consistency_level: "Strong"
+  embedding_dim: 768
+
+# Document processing settings
+chunk_size: 1200 # Number of characters per text chunk
+chunk_overlap: 200 # Overlap between adjacent chunks
+
+# Parallel processing settings
+embedding_batch_size: 1500 # Number of chunks to embed in a single API call
+max_parallel_pdfs: 10 # Maximum number of PDFs to process in parallel
+
+# Traditional RAG Pipeline Settings
+# Step 1: Initial retrieval (cast wide net)
+initial_retrieval_k: 100 # Number of chunks to retrieve before reranking
+mmr_diversity: 0.8 # MMR diversity parameter (0=max diversity, 1=max relevance)
+
+# Step 2: Reranking settings
+top_k_chunks: 25 # Final number of chunks after reranking
+reranker:
+  model: "nvidia/nv-rerankqa-mistral-4b-v3"
+  api_key: ${oc.env:NVIDIA_API_KEY}
+
+# Answer generation settings
+prompt_template: |
+  You are a scientific research assistant specialized in reading and extracting information from research papers.
+  Your role is to answer questions by retrieving relevant information from the provided context.
+
+  - Provide detailed, structured, and well-argued explanations—not just brief summaries.
+  - Cite specific sources using only the title of the paper.
+  - If the context is insufficient, clearly state that more information is needed.
+
+  Context:
+  {context}
+
+  Question: {question}
+
+  Your answer should be comprehensive, accurate, and clearly structured for a scientific audience.
+
+# GPU Detection and Performance Settings
+gpu_detection:
+  # Timeout for GPU detection command (seconds)
+  detection_timeout: 10
+
+  # Log GPU detection results
+  log_detection: true
+
+  # Force CPU mode even if GPU is detected (for testing CPU Milvus)
+  # Uncomment the line below to force CPU mode:
+  # force_cpu_mode: true

aiagents4pharma/talk2scholars/configs/tools/retrieve_semantic_scholar_paper_id/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/tools/retrieve_semantic_scholar_paper_id/default.yaml

@@ -0,0 +1,12 @@
+api_endpoint: "https://api.semanticscholar.org/graph/v1/paper/search"
+request_timeout: 10
+api_fields:
+  - "paperId"
+  - "title"
+  - "abstract"
+  - "year"
+  - "authors"
+  - "citationCount"
+  - "url"
+# Commented fields that could be added later if needed
+# - "externalIds"

aiagents4pharma/talk2scholars/configs/tools/search/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/tools/search/default.yaml

@@ -0,0 +1,26 @@
+api_endpoint: "https://api.semanticscholar.org/graph/v1/paper/search"
+default_limit: 2
+request_timeout: 10
+api_fields:
+  - "paperId"
+  - "title"
+  - "abstract"
+  - "year"
+  - "authors.name"
+  - "authors.authorId"
+  - "citationCount"
+  - "url"
+  - "externalIds"
+  - "venue"
+  - "publicationVenue" # Full object, instead of specific subfields
+  - "journal" # Full object, instead of specific subfields
+  - "publicationDate"
+
+# Commented fields that could be added later if needed
+#  - "publicationTypes"
+#  - "openAccessPdf"
+
+# Default search parameters
+search_params:
+  limit: ${.default_limit} # Reference to the default_limit above
+  fields: ${.api_fields} # Reference to the api_fields above

aiagents4pharma/talk2scholars/configs/tools/single_paper_recommendation/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/tools/single_paper_recommendation/default.yaml

@@ -0,0 +1,26 @@
+api_endpoint: "https://api.semanticscholar.org/recommendations/v1/papers/forpaper"
+default_limit: 2
+request_timeout: 10
+api_fields:
+  - "paperId"
+  - "title"
+  - "abstract"
+  - "year"
+  - "authors.name"
+  - "authors.authorId"
+  - "citationCount"
+  - "url"
+  - "externalIds"
+  - "venue"
+  - "publicationVenue" # Full object, instead of specific subfields
+  - "journal" # Full object, instead of specific subfields
+  - "publicationDate"
+# Commented fields that could be added later if needed
+#  - "publicationTypes"
+#  - "openAccessPdf"
+
+# Default recommendation parameters
+recommendation_params:
+  limit: ${.default_limit} # Reference to the default_limit above
+  fields: ${.api_fields} # Reference to the api_fields above
+  from_pool: "all-cs" # Using all-cs pool as specified in docs

aiagents4pharma/talk2scholars/configs/tools/zotero_read/__init__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/tools/zotero_read/default.yaml

@@ -0,0 +1,57 @@
+# Default configuration for Zotero search tool
+library_type: "user" # Type of library ('user' or 'group')
+default_limit: 2
+request_timeout: 10
+chunk_size: 16384  # Size (in bytes) for streaming PDF download chunks
+user_id: ${oc.env:ZOTERO_USER_ID} # Load from environment variable
+api_key: ${oc.env:ZOTERO_API_KEY} # Load from environment variable
+
+# Default search parameters
+search_params:
+  limit: ${.default_limit}
+
+# Item Types and Limit
+zotero:
+  max_limit: 100
+  filter_item_types:
+    [
+      "Artwork",
+      "Audio Recording",
+      "Bill",
+      "Blog Post",
+      "Book",
+      "Book Section",
+      "Case",
+      "Conference Paper",
+      "Dataset",
+      "Dictionary Entry",
+      "Document",
+      "E-mail",
+      "Encyclopedia Article",
+      "Film",
+      "Forum Post",
+      "Hearing",
+      "Instant Message",
+      "Interview",
+      "Journal Article",
+      "Letter",
+      "Magazine Article",
+      "Manuscript",
+      "Map",
+      "Newspaper Article",
+      "Patent",
+      "Podcast",
+      "Preprint",
+      "Presentation",
+      "Radio Broadcast",
+      "Report",
+      "Software",
+      "Standard",
+      "Statute",
+      "Thesis",
+      "TV Broadcast",
+      "Video Recording",
+      "Web Page",
+    ]
+
+  # filter_excluded_types: ["attachment", "note", "annotation"]

aiagents4pharma/talk2scholars/configs/tools/zotero_write/__inti__.py

@@ -0,0 +1,3 @@
+"""
+Import all the modules in the package
+"""

aiagents4pharma/talk2scholars/configs/tools/zotero_write/default.yaml

@@ -0,0 +1,55 @@
+# Default configuration for Zotero search tool
+library_type: "user" # Type of library ('user' or 'group')
+default_limit: 2
+request_timeout: 10
+user_id: ${oc.env:ZOTERO_USER_ID} # Load from environment variable
+api_key: ${oc.env:ZOTERO_API_KEY} # Load from environment variable
+
+# Default search parameters
+search_params:
+  limit: ${.default_limit}
+
+# Item Types and Limit
+zotero:
+  max_limit: 100
+  filter_item_types:
+    [
+      "Artwork",
+      "Audio Recording",
+      "Bill",
+      "Blog Post",
+      "Book",
+      "Book Section",
+      "Case",
+      "Conference Paper",
+      "Dataset",
+      "Dictionary Entry",
+      "Document",
+      "E-mail",
+      "Encyclopedia Article",
+      "Film",
+      "Forum Post",
+      "Hearing",
+      "Instant Message",
+      "Interview",
+      "Journal Article",
+      "Letter",
+      "Magazine Article",
+      "Manuscript",
+      "Map",
+      "Newspaper Article",
+      "Patent",
+      "Podcast",
+      "Preprint",
+      "Presentation",
+      "Radio Broadcast",
+      "Report",
+      "Software",
+      "Standard",
+      "Statute",
+      "Thesis",
+      "TV Broadcast",
+      "Video Recording",
+      "Web Page",
+    ]
+  # filter_excluded_types: ["attachment", "note", "annotation"]

aiagents4pharma/talk2scholars/docker-compose/cpu/.env.example

@@ -0,0 +1,21 @@
+# .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_heres
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# ZOTERO API KEY
+ZOTERO_API_KEY=your_zotero_api_key_here
+ZOTERO_USER_ID=your_zotero_user_id_here
+
+# Set environment variables for data loader
+MILVUS_HOST=milvus-standalone
+MILVUS_PORT=19530
+MILVUS_DB_NAME=pdf_rag_db
+MILVUS_COLLECTION_NAME=pdf_rag_documents

aiagents4pharma/talk2scholars/docker-compose/cpu/docker-compose.yml

@@ -0,0 +1,90 @@
+version: "1.0.0"
+
+services:
+  # talk2scholars
+  talk2scholars:
+    container_name: talk2scholars
+    image: vpatientengine/talk2scholars:latest
+    platform: linux/amd64
+    ports:
+      - "8501:8501"
+    environment:
+      - MILVUS_HOST=milvus-standalone
+      - MILVUS_PORT=19530
+    env_file:
+      - .env
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8501/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    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/talk2scholars/docker-compose/gpu/.env.example

@@ -0,0 +1,21 @@
+# .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_heres
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# ZOTERO API KEY
+ZOTERO_API_KEY=your_zotero_api_key_here
+ZOTERO_USER_ID=your_zotero_user_id_here
+
+# Set environment variables for data loader
+MILVUS_HOST=milvus-standalone
+MILVUS_PORT=19530
+MILVUS_DB_NAME=pdf_rag_db
+MILVUS_COLLECTION_NAME=pdf_rag_documents

aiagents4pharma/talk2scholars/docker-compose/gpu/docker-compose.yml

@@ -0,0 +1,105 @@
+version: "1.0.0"
+
+services:
+  # talk2scholars
+  talk2scholars:
+    container_name: talk2scholars
+    image: vpatientengine/talk2scholars: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
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8501/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+    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/talk2scholars/install.md

@@ -0,0 +1,122 @@
+# Talk2Scholars
+
+## Installation
+
+- [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)
+
+**Prerequisites**
+
+- [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/talk2scholars/docker-compose/gpu/docker-compose.yml \
+     https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2scholars/docker-compose/gpu/.env.example
+```
+
+**For CPU:**
+
+```sh
+wget https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2scholars/docker-compose/cpu/docker-compose.yml \
+     https://raw.githubusercontent.com/VirtualPatientEngine/AIAgents4Pharma/main/aiagents4pharma/talk2scholars/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_heres
+
+# NVIDIA API KEY
+NVIDIA_API_KEY=your_nvidia_api_key_here
+
+# ZOTERO API KEY
+ZOTERO_API_KEY=your_zotero_api_key_here
+ZOTERO_USER_ID=your_zotero_user_id_here
+
+# Set environment variables for data loader
+MILVUS_HOST=milvus-standalone
+MILVUS_PORT=19530
+MILVUS_DB_NAME=pdf_rag_db
+MILVUS_COLLECTION_NAME=pdf_rag_documents
+```
+
+---
+
+#### 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 `talk2scholars` 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 talk2scholars
+> ```
+
+---
+
+## Get Key
+
+- `NVIDIA_API_KEY` – required (obtain a free key at [https://build.nvidia.com/explore/discover](https://build.nvidia.com/explore/discover))
+- `ZOTERO_API_KEY` – required (generate at [https://www.zotero.org/user/login#applications](https://www.zotero.org/user/login#applications))
+
+  **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).

aiagents4pharma/talk2scholars/state/__init__.py

@@ -0,0 +1,7 @@
+"""
+This file is used to import all the modules in the package.
+"""
+
+from . import state_talk2scholars
+
+__all__ = ["state_talk2scholars"]