tooluniverse 0.2.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

tooluniverse/data/efo_tools.json

@@ -0,0 +1,17 @@
+[
+    {
+        "type": "EFOTool",
+        "name": "OSL_get_efo_id_by_disease_name",
+        "description": "Tool to lookup Experimental Factor Ontology (EFO) IDs for diseases via the EMBL-EBI OLS API.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "disease": {
+                    "type": "string",
+                    "description": "Search query for diseases. Provide the disease name to lookup the corresponding EFO ID."
+                }
+            },
+            "required": ["disease"]
+        }
+    }
+]

tooluniverse/data/embedding_tools.json

@@ -0,0 +1,319 @@
+[
+    {
+        "type": "EmbeddingDatabase",
+        "name": "embedding_database_create",
+        "description": "Create a new embedding database from a collection of documents. Generates embeddings using OpenAI or Azure OpenAI models and stores them in a searchable database with FAISS vector index and SQLite metadata storage.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "create_from_docs",
+                    "description": "Action to create database from documents"
+                },
+                "database_name": {
+                    "type": "string",
+                    "description": "Name for the new database (must be unique)"
+                },
+                "documents": {
+                    "type": "array",
+                    "description": "List of document texts to embed and store",
+                    "items": {"type": "string"},
+                    "minItems": 1,
+                    "maxItems": 10000
+                },
+                "metadata": {
+                    "type": "array",
+                    "description": "Optional metadata for each document (same length as documents)",
+                    "items": {"type": "object"},
+                    "default": []
+                },
+                "model": {
+                    "type": "string",
+                    "description": "OpenAI/Azure OpenAI embedding model to use",
+                    "enum": ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"],
+                    "default": "text-embedding-3-small"
+                },
+                "description": {
+                    "type": "string",
+                    "description": "Optional description for the database",
+                    "default": ""
+                }
+            },
+            "required": ["database_name", "documents"]
+        },
+        "required_api_keys": [],
+        "optional_api_keys": ["OPENAI_API_KEY", "AZURE_OPENAI_API_KEY"],
+        "configs": {
+            "openai_config": {
+                "api_key": "${OPENAI_API_KEY}",
+                "base_url": "${OPENAI_BASE_URL:https://api.openai.com/v1}",
+                "timeout": 60,
+                "max_retries": 3
+            },
+            "azure_openai_config": {
+                "api_key": "${AZURE_OPENAI_API_KEY}",
+                "azure_endpoint": "${AZURE_OPENAI_ENDPOINT}",
+                "api_version": "${AZURE_OPENAI_API_VERSION:2024-02-01}",
+                "timeout": 120,
+                "max_retries": 5
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "faiss_index_type": "IndexFlatIP"
+            }
+        }
+    },
+    {
+        "type": "EmbeddingDatabase",
+        "name": "embedding_database_add",
+        "description": "Add new documents to an existing embedding database. Generates embeddings for new documents using the same model as the original database and appends them to the existing FAISS index.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "add_docs",
+                    "description": "Action to add documents to existing database"
+                },
+                "database_name": {
+                    "type": "string",
+                    "description": "Name of the existing database to add documents to"
+                },
+                "documents": {
+                    "type": "array",
+                    "description": "List of new document texts to embed and add",
+                    "items": {"type": "string"},
+                    "minItems": 1,
+                    "maxItems": 10000
+                },
+                "metadata": {
+                    "type": "array",
+                    "description": "Optional metadata for each new document (same length as documents)",
+                    "items": {"type": "object"},
+                    "default": []
+                }
+            },
+            "required": ["database_name", "documents"]
+        },
+        "required_api_keys": [],
+        "optional_api_keys": ["OPENAI_API_KEY", "AZURE_OPENAI_API_KEY"],
+        "configs": {
+            "openai_config": {
+                "api_key": "${OPENAI_API_KEY}",
+                "base_url": "${OPENAI_BASE_URL:https://api.openai.com/v1}",
+                "timeout": 60,
+                "max_retries": 3
+            },
+            "azure_openai_config": {
+                "api_key": "${AZURE_OPENAI_API_KEY}",
+                "azure_endpoint": "${AZURE_OPENAI_ENDPOINT}",
+                "api_version": "${AZURE_OPENAI_API_VERSION:2024-02-01}",
+                "timeout": 120,
+                "max_retries": 5
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "faiss_index_type": "IndexFlatIP"
+            }
+        }
+    },
+    {
+        "type": "EmbeddingDatabase",
+        "name": "embedding_database_search",
+        "description": "Search for semantically similar documents in an embedding database. Uses OpenAI embeddings to convert query text to vectors and performs similarity search using FAISS with optional metadata filtering.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "search",
+                    "description": "Action to search the database"
+                },
+                "database_name": {
+                    "type": "string",
+                    "description": "Name of the database to search in"
+                },
+                "query": {
+                    "type": "string",
+                    "description": "Query text to find similar documents for"
+                },
+                "top_k": {
+                    "type": "integer",
+                    "description": "Number of most similar documents to return",
+                    "minimum": 1,
+                    "maximum": 1000,
+                    "default": 5
+                },
+                "filters": {
+                    "type": "object",
+                    "description": "Optional metadata filters to apply to search results",
+                    "additionalProperties": true,
+                    "default": {}
+                }
+            },
+            "required": ["database_name", "query"]
+        },
+        "required_api_keys": [],
+        "optional_api_keys": ["OPENAI_API_KEY", "AZURE_OPENAI_API_KEY"],
+        "configs": {
+            "openai_config": {
+                "api_key": "${OPENAI_API_KEY}",
+                "base_url": "${OPENAI_BASE_URL:https://api.openai.com/v1}",
+                "timeout": 60,
+                "max_retries": 3
+            },
+            "azure_openai_config": {
+                "api_key": "${AZURE_OPENAI_API_KEY}",
+                "azure_endpoint": "${AZURE_OPENAI_ENDPOINT}",
+                "api_version": "${AZURE_OPENAI_API_VERSION:2024-02-01}",
+                "timeout": 120,
+                "max_retries": 5
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "faiss_index_type": "IndexFlatIP"
+            }
+        }
+    },
+    {
+        "type": "EmbeddingDatabase",
+        "name": "embedding_database_load",
+        "description": "Load an existing embedding database from a local path or external source. Allows importing databases created elsewhere or backed up databases into the current ToolUniverse instance.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "load_database",
+                    "description": "Action to load database from external source"
+                },
+                "database_path": {
+                    "type": "string",
+                    "description": "Path to the existing database directory or file"
+                },
+                "database_name": {
+                    "type": "string",
+                    "description": "Local name to assign to the loaded database"
+                },
+                "overwrite": {
+                    "type": "boolean",
+                    "description": "Whether to overwrite existing database with same name",
+                    "default": false
+                }
+            },
+            "required": ["database_path", "database_name"]
+        },
+        "required_api_keys": [],
+        "optional_api_keys": ["OPENAI_API_KEY", "AZURE_OPENAI_API_KEY"],
+        "configs": {
+            "openai_config": {
+                "api_key": "${OPENAI_API_KEY}",
+                "base_url": "${OPENAI_BASE_URL:https://api.openai.com/v1}",
+                "timeout": 60,
+                "max_retries": 3
+            },
+            "azure_openai_config": {
+                "api_key": "${AZURE_OPENAI_API_KEY}",
+                "azure_endpoint": "${AZURE_OPENAI_ENDPOINT}",
+                "api_version": "${AZURE_OPENAI_API_VERSION:2024-02-01}",
+                "timeout": 120,
+                "max_retries": 5
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "faiss_index_type": "IndexFlatIP"
+            }
+        }
+    },
+    {
+        "type": "EmbeddingSync",
+        "name": "embedding_sync_upload",
+        "description": "Upload a local embedding database to HuggingFace Hub for sharing and collaboration. Creates a dataset repository with the database files and metadata.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "upload",
+                    "description": "Action to upload database to HuggingFace"
+                },
+                "database_name": {
+                    "type": "string",
+                    "description": "Name of the local database to upload"
+                },
+                "repository": {
+                    "type": "string",
+                    "description": "HuggingFace repository name (format: username/repo-name)"
+                },
+                "description": {
+                    "type": "string",
+                    "description": "Description for the HuggingFace dataset",
+                    "default": ""
+                },
+                "private": {
+                    "type": "boolean",
+                    "description": "Whether to create a private repository",
+                    "default": false
+                },
+                "commit_message": {
+                    "type": "string",
+                    "description": "Commit message for the upload",
+                    "default": "Upload embedding database"
+                }
+            },
+            "required": ["database_name", "repository"]
+        },
+        "required_api_keys": ["HF_TOKEN"],
+        "configs": {
+            "huggingface_config": {
+                "token": "${HF_TOKEN}",
+                "endpoint": "https://huggingface.co"
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "export_dir": "./exports"
+            }
+        }
+    },
+    {
+        "type": "EmbeddingSync",
+        "name": "embedding_sync_download",
+        "description": "Download an embedding database from HuggingFace Hub to local storage. Allows accessing databases shared by others or your own backups.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "action": {
+                    "type": "string",
+                    "const": "download",
+                    "description": "Action to download database from HuggingFace"
+                },
+                "repository": {
+                    "type": "string",
+                    "description": "HuggingFace repository to download from (format: username/repo-name)"
+                },
+                "local_name": {
+                    "type": "string",
+                    "description": "Local name for the downloaded database (optional, defaults to repo name)"
+                },
+                "overwrite": {
+                    "type": "boolean",
+                    "description": "Whether to overwrite existing local database with same name",
+                    "default": false
+                }
+            },
+            "required": ["repository"]
+        },
+        "required_api_keys": ["HF_TOKEN"],
+        "configs": {
+            "huggingface_config": {
+                "token": "${HF_TOKEN}",
+                "endpoint": "https://huggingface.co"
+            },
+            "storage_config": {
+                "data_dir": "./data/embeddings",
+                "export_dir": "./exports"
+            }
+        }
+    }
+]

tooluniverse/data/enrichr_tools.json

@@ -0,0 +1,31 @@
+[
+    {
+        "type": "EnrichrTool",
+        "name": "enrichr_gene_enrichment_analysis",
+        "description": "Perform gene enrichment analysis using Enrichr to find biological pathways, processes, and molecular functions associated with a list of genes. Returns connectivity paths between genes and enrichment terms.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "gene_list": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "description": "List of gene names or symbols to analyze. At least 2 genes are required for path ranking analysis.",
+                    "minItems": 2
+                },
+                "libs": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "description": "List of enrichment libraries to use for analysis.",
+                    "default": [
+                        "WikiPathways_2024_Human",
+                        "Reactome_Pathways_2024",
+                        "MSigDB_Hallmark_2020",
+                        "GO_Molecular_Function_2023",
+                        "GO_Biological_Process_2023"
+                    ]
+                }
+            },
+            "required": ["gene_list"]
+        }
+    }
+]

tooluniverse/data/europe_pmc_tools.json

@@ -0,0 +1,22 @@
+[
+    {
+        "type": "EuropePMCTool",
+        "name": "EuropePMC_search_articles",
+        "description": "Search for articles on Europe PMC including abstracts. The tool queries the Europe PMC web service using provided keywords and returns articles with details such as title, abstract, journal, publication year, and a URL to the full article.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Search query for Europe PMC. Use keywords separated by spaces to refine your search."
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Number of articles to return. This sets the maximum number of articles retrieved from Europe PMC.",
+                    "default": 5
+                }
+            },
+            "required": ["query"]
+        }
+    }
+]

tooluniverse/data/expert_feedback_tools.json

@@ -0,0 +1,10 @@
+[
+    {
+        "name": "mcp_auto_loader_expert_feedback",
+        "description": "Automatically discover and load all tools from Human Expert Feedback MCP Server. Provides tools for consulting human experts on complex medical decisions.",
+        "type": "MCPAutoLoaderTool",
+        "tool_prefix": "expert_",
+        "server_url": "http://${EXPERT_FEEDBACK_MCP_SERVER_URL}/mcp",
+        "required_api_keys": ["EXPERT_FEEDBACK_MCP_SERVER_URL"]
+    }
+]