bfa-irc-a-sdk 0.1.0__tar.gz

bfa_irc_a_sdk-0.1.0/PKG-INFO

@@ -0,0 +1,145 @@
+Metadata-Version: 2.4
+Name: bfa-irc-a-sdk
+Version: 0.1.0
+Summary: A generic Backend for Agents (BFA) SDK with FAISS semantic routing.
+Author: Sandro Garcia
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: httpx
+Requires-Dist: python-dotenv
+Requires-Dist: a2a-sdk
+Requires-Dist: numpy
+Requires-Dist: faiss-cpu
+Requires-Dist: pydantic
+Requires-Dist: fastmcp
+Requires-Dist: pyyaml
+Requires-Dist: mangum
+Requires-Dist: openai
+Requires-Dist: pyjwt
+Requires-Dist: cryptography
+Provides-Extra: local
+Requires-Dist: sentence-transformers; extra == "local"
+
+# Backend for Agents SDK (BFA) & IRC-A Protocol
+
+A generic and opinionated framework and SDK to implement the **BFA (Backend for Agents)** pattern and the **IRC-A (Internet Relay Chat for Agents)** protocol, featuring native support for **FAISS-based Semantic Routing (vector search)**, asymmetric zero-trust security boundaries, and standard abstractions for A2A Agents and MCP Servers.
+
+Read the official protocol specification:
+👉 **[IRC-A Protocol Whitepaper (v1.0.0)](IRC-A_Whitepaper.md)** - *Decentralized Agent Networks, Semantic Capability Routing, and Secure-by-Design Software Architecture.*
+
+---
+
+## Multilingual Documentation
+* [Português (Portuguese)](README.pt.md)
+* [Español (Spanish)](README.es.md)
+
+---
+
+## BFA / IRC-A Protocol Architecture
+
+The BFA Gateway acts as a semantic middleware and registry broker layer between consumers (e.g., messaging UIs, chat systems) and specialized agents/tools.
+
+```mermaid
+graph TD
+    Consumer["Consumer UI / Whatsapp / WebApp"] -->|1. Resolve Query| BFA[BFA Gateway]
+    
+    subgraph BFA_Gateway ["BFA Gateway (Backend for Agents)"]
+        Router[Semantic Router] -->|2. Search Embeddings| FAISS[FAISS Vector Store]
+        Registry[Registry] -->|Load metadata| Router
+    end
+    
+    BFA -->|3. Route & Invoke| Agent1["Cuentas Agent (A2A)"]
+    BFA -->|3. Route & Invoke| Agent2["Tarjetas Agent (A2A)"]
+    BFA -->|4. Execute Tool| MCP1["MDBank MCP (FastMCP)"]
+```
+
+---
+
+## Key Features
+
+1. **FAISS-Based Semantic Routing:** Instead of matching exact keywords (like BM25), the BFA Gateway indexes the descriptions, tags, and examples of agents and tools in a local FAISS vector index. This resolves queries to matching functions even when synonyms are used (e.g., matching *"plastic"* to *"credit card"*).
+2. **`BFAAgent` Abstraction:** Simplifies building A2A agents using the `a2a-sdk` and Starlette. Forces standard metadata declarations (`tags`, `examples`, `description`) required for semantic indexing.
+3. **`BFAMCP` Abstraction:** Wraps and extends `FastMCP` servers. Automatically exposes a standardized `/tools` endpoint returning input schemas, descriptions, and custom tags/examples for discovery.
+4. **Secure-by-Design IRC-A Security (Roadmap):** Employs asymmetric challenge-response registration handshakes, logical channel masking (via container-level `IRCA_CHANNELS` env variables) to segregate vector search spaces, and Ephemeral DET (Delegated Execution Tokens) to enable direct decentralized P2P invocation without gateway bottlenecks.
+5. **Serverless (AWS Lambda) Ready:** Includes a built-in **Mangum** adapter in the Gateway. Combined with the cloud-based `OpenAIEmbedder`, the BFA Gateway runs serverless on demand with zero cold-starts.
+
+---
+
+## Configuring Embedding Providers & Chunking
+
+The BFA Gateway uses semantic embeddings to index agent/tool metadata in FAISS. You can choose between local models, cloud APIs, or offline mock routing via environment variables:
+
+| Mode / Provider | Environment Variables | Dependencies | Description |
+|---|---|---|---|
+| **Local Real (Default)** | None | `bfa-sdk[local]` | Uses `sentence-transformers` locally. Recommended for Python <= 3.12 environments. |
+| **OpenAI (Cloud)** | `BFA_USE_OPENAI_EMBEDDINGS=true`, `OPENAI_API_KEY="..."` | `openai` | Queries OpenAI's `text-embedding-3-small` endpoint. Perfect for serverless/Lambda environments. |
+| **Offline Mock (Feature Hashing)** | `BFA_USE_MOCK_EMBEDDINGS=true` | None | Uses a stable MD5 feature hashing trick to route queries based on keywords. Zero dependencies, fast, and local. |
+
+> [!NOTE]
+> **Why is there no Chunking in the Gateway?**
+> The BFA Gateway is a semantic router of services, not a document retrieval engine (RAG). It indexes short microservice metadata cards (names, descriptions, tags, examples) which fit completely within embedding token limits.
+> If you need to perform **Document Chunking** (RAG over PDFs/manuals), it should be implemented **inside the respective A2A Agent's internal database/logic**, keeping the Gateway lightweight and decoupled from document storage.
+
+---
+
+## Installation
+
+You can install the BFA SDK directly from GitHub using `pip`:
+
+```bash
+# Install the development version from the main branch
+pip install git+https://github.com/SandroG1977/bfa-sdk.git
+
+# Or install a specific version with the secure IRC-A protocol support
+pip install git+https://github.com/SandroG1977/bfa-sdk.git@feature/docstrings-init
+```
+
+---
+
+## Running the Demo
+
+### 2. Run the MDBank Demo
+The demo launches three mock servers in the background:
+1. A mock MDBank MCP server (`examples/mock_mdbank_mcp.py`) on port `8001`.
+2. A mock Cuentas A2A Agent (`examples/mock_cuentas_agent.py`) on port `8002`.
+3. A mock Tarjetas A2A Agent (`examples/mock_tarjetas_agent.py`) on port `8003`.
+4. The BFA Gateway on port `8000`, running dynamic discovery and performing test queries.
+
+To run:
+```bash
+python examples/run_demo.py
+```
+
+### 3. Run the UI Dashboard (IRC-A Central Hub)
+We have included a React-based UI Dashboard under `examples/frontend` to visually monitor the active agents/tools registry, register new microservices dynamically (plug-and-play), and chat with the routed banking agents:
+
+```bash
+# Navigate to the frontend folder
+cd examples/frontend
+
+# Install dependencies
+npm install
+
+# Start the development server
+npm start
+```
+Open `http://localhost:3000` to interact with your local agent hub in real-time.
+
+
+---
+
+## Credits & Acknowledgements
+
+This SDK is a community-driven implementation and expansion of the **BFA (Backend for Agents)** architectural pattern originally designed and documented by **Michael Douglas Barbosa Araujo** (Staff AI Architect). 
+
+You can read his original article introducing the pattern here:
+👉 [O padrão Back-end para Agentes (BFA) - Medium](https://medium.com/@mdbaraujo/o-padr%C3%A3o-back-end-para-agentes-bfa-a53c1c6d87fb)
+
+The goal of this project is to provide a standardized, packaged SDK extending his original concept with semantic vector routing (FAISS) and unified base adapters. All credit for the underlying protocol and architectural vision belongs to him.
+
+

bfa_irc_a_sdk-0.1.0/README.md

@@ -0,0 +1,118 @@
+# Backend for Agents SDK (BFA) & IRC-A Protocol
+
+A generic and opinionated framework and SDK to implement the **BFA (Backend for Agents)** pattern and the **IRC-A (Internet Relay Chat for Agents)** protocol, featuring native support for **FAISS-based Semantic Routing (vector search)**, asymmetric zero-trust security boundaries, and standard abstractions for A2A Agents and MCP Servers.
+
+Read the official protocol specification:
+👉 **[IRC-A Protocol Whitepaper (v1.0.0)](IRC-A_Whitepaper.md)** - *Decentralized Agent Networks, Semantic Capability Routing, and Secure-by-Design Software Architecture.*
+
+---
+
+## Multilingual Documentation
+* [Português (Portuguese)](README.pt.md)
+* [Español (Spanish)](README.es.md)
+
+---
+
+## BFA / IRC-A Protocol Architecture
+
+The BFA Gateway acts as a semantic middleware and registry broker layer between consumers (e.g., messaging UIs, chat systems) and specialized agents/tools.
+
+```mermaid
+graph TD
+    Consumer["Consumer UI / Whatsapp / WebApp"] -->|1. Resolve Query| BFA[BFA Gateway]
+    
+    subgraph BFA_Gateway ["BFA Gateway (Backend for Agents)"]
+        Router[Semantic Router] -->|2. Search Embeddings| FAISS[FAISS Vector Store]
+        Registry[Registry] -->|Load metadata| Router
+    end
+    
+    BFA -->|3. Route & Invoke| Agent1["Cuentas Agent (A2A)"]
+    BFA -->|3. Route & Invoke| Agent2["Tarjetas Agent (A2A)"]
+    BFA -->|4. Execute Tool| MCP1["MDBank MCP (FastMCP)"]
+```
+
+---
+
+## Key Features
+
+1. **FAISS-Based Semantic Routing:** Instead of matching exact keywords (like BM25), the BFA Gateway indexes the descriptions, tags, and examples of agents and tools in a local FAISS vector index. This resolves queries to matching functions even when synonyms are used (e.g., matching *"plastic"* to *"credit card"*).
+2. **`BFAAgent` Abstraction:** Simplifies building A2A agents using the `a2a-sdk` and Starlette. Forces standard metadata declarations (`tags`, `examples`, `description`) required for semantic indexing.
+3. **`BFAMCP` Abstraction:** Wraps and extends `FastMCP` servers. Automatically exposes a standardized `/tools` endpoint returning input schemas, descriptions, and custom tags/examples for discovery.
+4. **Secure-by-Design IRC-A Security (Roadmap):** Employs asymmetric challenge-response registration handshakes, logical channel masking (via container-level `IRCA_CHANNELS` env variables) to segregate vector search spaces, and Ephemeral DET (Delegated Execution Tokens) to enable direct decentralized P2P invocation without gateway bottlenecks.
+5. **Serverless (AWS Lambda) Ready:** Includes a built-in **Mangum** adapter in the Gateway. Combined with the cloud-based `OpenAIEmbedder`, the BFA Gateway runs serverless on demand with zero cold-starts.
+
+---
+
+## Configuring Embedding Providers & Chunking
+
+The BFA Gateway uses semantic embeddings to index agent/tool metadata in FAISS. You can choose between local models, cloud APIs, or offline mock routing via environment variables:
+
+| Mode / Provider | Environment Variables | Dependencies | Description |
+|---|---|---|---|
+| **Local Real (Default)** | None | `bfa-sdk[local]` | Uses `sentence-transformers` locally. Recommended for Python <= 3.12 environments. |
+| **OpenAI (Cloud)** | `BFA_USE_OPENAI_EMBEDDINGS=true`, `OPENAI_API_KEY="..."` | `openai` | Queries OpenAI's `text-embedding-3-small` endpoint. Perfect for serverless/Lambda environments. |
+| **Offline Mock (Feature Hashing)** | `BFA_USE_MOCK_EMBEDDINGS=true` | None | Uses a stable MD5 feature hashing trick to route queries based on keywords. Zero dependencies, fast, and local. |
+
+> [!NOTE]
+> **Why is there no Chunking in the Gateway?**
+> The BFA Gateway is a semantic router of services, not a document retrieval engine (RAG). It indexes short microservice metadata cards (names, descriptions, tags, examples) which fit completely within embedding token limits.
+> If you need to perform **Document Chunking** (RAG over PDFs/manuals), it should be implemented **inside the respective A2A Agent's internal database/logic**, keeping the Gateway lightweight and decoupled from document storage.
+
+---
+
+## Installation
+
+You can install the BFA SDK directly from GitHub using `pip`:
+
+```bash
+# Install the development version from the main branch
+pip install git+https://github.com/SandroG1977/bfa-sdk.git
+
+# Or install a specific version with the secure IRC-A protocol support
+pip install git+https://github.com/SandroG1977/bfa-sdk.git@feature/docstrings-init
+```
+
+---
+
+## Running the Demo
+
+### 2. Run the MDBank Demo
+The demo launches three mock servers in the background:
+1. A mock MDBank MCP server (`examples/mock_mdbank_mcp.py`) on port `8001`.
+2. A mock Cuentas A2A Agent (`examples/mock_cuentas_agent.py`) on port `8002`.
+3. A mock Tarjetas A2A Agent (`examples/mock_tarjetas_agent.py`) on port `8003`.
+4. The BFA Gateway on port `8000`, running dynamic discovery and performing test queries.
+
+To run:
+```bash
+python examples/run_demo.py
+```
+
+### 3. Run the UI Dashboard (IRC-A Central Hub)
+We have included a React-based UI Dashboard under `examples/frontend` to visually monitor the active agents/tools registry, register new microservices dynamically (plug-and-play), and chat with the routed banking agents:
+
+```bash
+# Navigate to the frontend folder
+cd examples/frontend
+
+# Install dependencies
+npm install
+
+# Start the development server
+npm start
+```
+Open `http://localhost:3000` to interact with your local agent hub in real-time.
+
+
+---
+
+## Credits & Acknowledgements
+
+This SDK is a community-driven implementation and expansion of the **BFA (Backend for Agents)** architectural pattern originally designed and documented by **Michael Douglas Barbosa Araujo** (Staff AI Architect). 
+
+You can read his original article introducing the pattern here:
+👉 [O padrão Back-end para Agentes (BFA) - Medium](https://medium.com/@mdbaraujo/o-padr%C3%A3o-back-end-para-agentes-bfa-a53c1c6d87fb)
+
+The goal of this project is to provide a standardized, packaged SDK extending his original concept with semantic vector routing (FAISS) and unified base adapters. All credit for the underlying protocol and architectural vision belongs to him.
+
+

bfa_irc_a_sdk-0.1.0/bfa_irc_a_sdk.egg-info/PKG-INFO

@@ -0,0 +1,145 @@
+Metadata-Version: 2.4
+Name: bfa-irc-a-sdk
+Version: 0.1.0
+Summary: A generic Backend for Agents (BFA) SDK with FAISS semantic routing.
+Author: Sandro Garcia
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: httpx
+Requires-Dist: python-dotenv
+Requires-Dist: a2a-sdk
+Requires-Dist: numpy
+Requires-Dist: faiss-cpu
+Requires-Dist: pydantic
+Requires-Dist: fastmcp
+Requires-Dist: pyyaml
+Requires-Dist: mangum
+Requires-Dist: openai
+Requires-Dist: pyjwt
+Requires-Dist: cryptography
+Provides-Extra: local
+Requires-Dist: sentence-transformers; extra == "local"
+
+# Backend for Agents SDK (BFA) & IRC-A Protocol
+
+A generic and opinionated framework and SDK to implement the **BFA (Backend for Agents)** pattern and the **IRC-A (Internet Relay Chat for Agents)** protocol, featuring native support for **FAISS-based Semantic Routing (vector search)**, asymmetric zero-trust security boundaries, and standard abstractions for A2A Agents and MCP Servers.
+
+Read the official protocol specification:
+👉 **[IRC-A Protocol Whitepaper (v1.0.0)](IRC-A_Whitepaper.md)** - *Decentralized Agent Networks, Semantic Capability Routing, and Secure-by-Design Software Architecture.*
+
+---
+
+## Multilingual Documentation
+* [Português (Portuguese)](README.pt.md)
+* [Español (Spanish)](README.es.md)
+
+---
+
+## BFA / IRC-A Protocol Architecture
+
+The BFA Gateway acts as a semantic middleware and registry broker layer between consumers (e.g., messaging UIs, chat systems) and specialized agents/tools.
+
+```mermaid
+graph TD
+    Consumer["Consumer UI / Whatsapp / WebApp"] -->|1. Resolve Query| BFA[BFA Gateway]
+    
+    subgraph BFA_Gateway ["BFA Gateway (Backend for Agents)"]
+        Router[Semantic Router] -->|2. Search Embeddings| FAISS[FAISS Vector Store]
+        Registry[Registry] -->|Load metadata| Router
+    end
+    
+    BFA -->|3. Route & Invoke| Agent1["Cuentas Agent (A2A)"]
+    BFA -->|3. Route & Invoke| Agent2["Tarjetas Agent (A2A)"]
+    BFA -->|4. Execute Tool| MCP1["MDBank MCP (FastMCP)"]
+```
+
+---
+
+## Key Features
+
+1. **FAISS-Based Semantic Routing:** Instead of matching exact keywords (like BM25), the BFA Gateway indexes the descriptions, tags, and examples of agents and tools in a local FAISS vector index. This resolves queries to matching functions even when synonyms are used (e.g., matching *"plastic"* to *"credit card"*).
+2. **`BFAAgent` Abstraction:** Simplifies building A2A agents using the `a2a-sdk` and Starlette. Forces standard metadata declarations (`tags`, `examples`, `description`) required for semantic indexing.
+3. **`BFAMCP` Abstraction:** Wraps and extends `FastMCP` servers. Automatically exposes a standardized `/tools` endpoint returning input schemas, descriptions, and custom tags/examples for discovery.
+4. **Secure-by-Design IRC-A Security (Roadmap):** Employs asymmetric challenge-response registration handshakes, logical channel masking (via container-level `IRCA_CHANNELS` env variables) to segregate vector search spaces, and Ephemeral DET (Delegated Execution Tokens) to enable direct decentralized P2P invocation without gateway bottlenecks.
+5. **Serverless (AWS Lambda) Ready:** Includes a built-in **Mangum** adapter in the Gateway. Combined with the cloud-based `OpenAIEmbedder`, the BFA Gateway runs serverless on demand with zero cold-starts.
+
+---
+
+## Configuring Embedding Providers & Chunking
+
+The BFA Gateway uses semantic embeddings to index agent/tool metadata in FAISS. You can choose between local models, cloud APIs, or offline mock routing via environment variables:
+
+| Mode / Provider | Environment Variables | Dependencies | Description |
+|---|---|---|---|
+| **Local Real (Default)** | None | `bfa-sdk[local]` | Uses `sentence-transformers` locally. Recommended for Python <= 3.12 environments. |
+| **OpenAI (Cloud)** | `BFA_USE_OPENAI_EMBEDDINGS=true`, `OPENAI_API_KEY="..."` | `openai` | Queries OpenAI's `text-embedding-3-small` endpoint. Perfect for serverless/Lambda environments. |
+| **Offline Mock (Feature Hashing)** | `BFA_USE_MOCK_EMBEDDINGS=true` | None | Uses a stable MD5 feature hashing trick to route queries based on keywords. Zero dependencies, fast, and local. |
+
+> [!NOTE]
+> **Why is there no Chunking in the Gateway?**
+> The BFA Gateway is a semantic router of services, not a document retrieval engine (RAG). It indexes short microservice metadata cards (names, descriptions, tags, examples) which fit completely within embedding token limits.
+> If you need to perform **Document Chunking** (RAG over PDFs/manuals), it should be implemented **inside the respective A2A Agent's internal database/logic**, keeping the Gateway lightweight and decoupled from document storage.
+
+---
+
+## Installation
+
+You can install the BFA SDK directly from GitHub using `pip`:
+
+```bash
+# Install the development version from the main branch
+pip install git+https://github.com/SandroG1977/bfa-sdk.git
+
+# Or install a specific version with the secure IRC-A protocol support
+pip install git+https://github.com/SandroG1977/bfa-sdk.git@feature/docstrings-init
+```
+
+---
+
+## Running the Demo
+
+### 2. Run the MDBank Demo
+The demo launches three mock servers in the background:
+1. A mock MDBank MCP server (`examples/mock_mdbank_mcp.py`) on port `8001`.
+2. A mock Cuentas A2A Agent (`examples/mock_cuentas_agent.py`) on port `8002`.
+3. A mock Tarjetas A2A Agent (`examples/mock_tarjetas_agent.py`) on port `8003`.
+4. The BFA Gateway on port `8000`, running dynamic discovery and performing test queries.
+
+To run:
+```bash
+python examples/run_demo.py
+```
+
+### 3. Run the UI Dashboard (IRC-A Central Hub)
+We have included a React-based UI Dashboard under `examples/frontend` to visually monitor the active agents/tools registry, register new microservices dynamically (plug-and-play), and chat with the routed banking agents:
+
+```bash
+# Navigate to the frontend folder
+cd examples/frontend
+
+# Install dependencies
+npm install
+
+# Start the development server
+npm start
+```
+Open `http://localhost:3000` to interact with your local agent hub in real-time.
+
+
+---
+
+## Credits & Acknowledgements
+
+This SDK is a community-driven implementation and expansion of the **BFA (Backend for Agents)** architectural pattern originally designed and documented by **Michael Douglas Barbosa Araujo** (Staff AI Architect). 
+
+You can read his original article introducing the pattern here:
+👉 [O padrão Back-end para Agentes (BFA) - Medium](https://medium.com/@mdbaraujo/o-padr%C3%A3o-back-end-para-agentes-bfa-a53c1c6d87fb)
+
+The goal of this project is to provide a standardized, packaged SDK extending his original concept with semantic vector routing (FAISS) and unified base adapters. All credit for the underlying protocol and architectural vision belongs to him.
+
+

bfa_irc_a_sdk-0.1.0/bfa_irc_a_sdk.egg-info/SOURCES.txt

@@ -0,0 +1,21 @@
+README.md
+pyproject.toml
+bfa_irc_a_sdk.egg-info/PKG-INFO
+bfa_irc_a_sdk.egg-info/SOURCES.txt
+bfa_irc_a_sdk.egg-info/dependency_links.txt
+bfa_irc_a_sdk.egg-info/requires.txt
+bfa_irc_a_sdk.egg-info/top_level.txt
+bfa_sdk/__init__.py
+bfa_sdk/config.py
+bfa_sdk/core/__init__.py
+bfa_sdk/core/agent.py
+bfa_sdk/core/gateway.py
+bfa_sdk/core/mcp.py
+bfa_sdk/router/embedder.py
+bfa_sdk/router/search.py
+tests/test_config.py
+tests/test_core_wrappers.py
+tests/test_embedder.py
+tests/test_gateway.py
+tests/test_irca_security.py
+tests/test_router.py

bfa_irc_a_sdk-0.1.0/bfa_irc_a_sdk.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

bfa_irc_a_sdk-0.1.0/bfa_irc_a_sdk.egg-info/requires.txt

@@ -0,0 +1,17 @@
+fastapi
+uvicorn
+httpx
+python-dotenv
+a2a-sdk
+numpy
+faiss-cpu
+pydantic
+fastmcp
+pyyaml
+mangum
+openai
+pyjwt
+cryptography
+
+[local]
+sentence-transformers

bfa_irc_a_sdk-0.1.0/bfa_irc_a_sdk.egg-info/top_level.txt

@@ -0,0 +1 @@
+bfa_sdk

bfa_irc_a_sdk-0.1.0/bfa_sdk/__init__.py

@@ -0,0 +1,13 @@
+# Backend for Agents SDK (BFA)
+# Version 0.1.0
+"""
+BFA SDK: A lightweight framework for Backend for Agents (BFA) architecture with FAISS semantic routing.
+"""
+
+
+from bfa_sdk.core.agent import BFAAgent
+from bfa_sdk.core.mcp import BFAMCP
+from bfa_sdk.core.gateway import create_gateway_app
+from bfa_sdk.router.search import BFASemanticRouter
+
+__all__ = ["BFAAgent", "BFAMCP", "create_gateway_app", "BFASemanticRouter"]

bfa_irc_a_sdk-0.1.0/bfa_sdk/config.py

@@ -0,0 +1,45 @@
+import os
+import yaml
+from typing import List, Dict, Any
+
+class BFAConfig:
+    """
+    Configuration helper parsing endpoints and models from environment variables
+    or a YAML configuration file.
+    """
+    def __init__(self, config_path: str = None):
+        self.agent_endpoints: List[str] = []
+        self.mcp_endpoints: List[str] = []
+        self.embedding_model: str = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+        self.use_mock_embeddings: bool = False
+        self.use_openai_embeddings: bool = False
+        self.openai_api_key: str = ""
+
+        # Load from config file if provided
+        if config_path and os.path.exists(config_path):
+            self.load_from_file(config_path)
+        else:
+            self.load_from_env()
+
+    def load_from_file(self, path: str):
+        with open(path, "r") as f:
+            data = yaml.safe_load(f) or {}
+            self.agent_endpoints = data.get("agent_endpoints", [])
+            self.mcp_endpoints = data.get("mcp_endpoints", [])
+            self.embedding_model = data.get("embedding_model", self.embedding_model)
+            self.use_mock_embeddings = data.get("use_mock_embeddings", False)
+            self.use_openai_embeddings = data.get("use_openai_embeddings", False)
+            self.openai_api_key = data.get("openai_api_key", "")
+
+    def load_from_env(self):
+        # Parse comma-separated strings
+        agents_env = os.getenv("BFA_AGENT_ENDPOINTS", "")
+        self.agent_endpoints = [x.strip() for x in agents_env.split(",") if x.strip()]
+
+        mcps_env = os.getenv("BFA_MCP_ENDPOINTS", "")
+        self.mcp_endpoints = [x.strip() for x in mcps_env.split(",") if x.strip()]
+
+        self.embedding_model = os.getenv("BFA_EMBEDDING_MODEL", self.embedding_model)
+        self.use_mock_embeddings = os.getenv("BFA_USE_MOCK_EMBEDDINGS", "false").lower() == "true"
+        self.use_openai_embeddings = os.getenv("BFA_USE_OPENAI_EMBEDDINGS", "false").lower() == "true"
+        self.openai_api_key = os.getenv("OPENAI_API_KEY", "")

bfa_irc_a_sdk-0.1.0/bfa_sdk/core/__init__.py

@@ -0,0 +1 @@
+# Core modules for BFA SDK