solana-agent 20.0.0__tar.gz → 22.0.5__tar.gz

{solana_agent-20.0.0 → solana_agent-22.0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 20.0.0
+Version: 22.0.5
 Summary: Agentic IQ
 License: MIT
 Keywords: ai,openai,ai agents,agi
@@ -14,11 +14,10 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Dist: openai (>=1.68.2,<2.0.0)
-Requires-Dist: pydantic (>=2.11.1,<3.0.0)
+Requires-Dist: openai (>=1.70.0,<2.0.0)
+Requires-Dist: pydantic (>=2.11.2,<3.0.0)
 Requires-Dist: pymongo (>=4.11.3,<5.0.0)
-Requires-Dist: zep-cloud (>=2.8.0,<3.0.0)
-Requires-Dist: zep-python (>=2.0.2,<3.0.0)
+Requires-Dist: zep-cloud (>=2.9.0,<3.0.0)
 Project-URL: Documentation, https://docs.solana-agent.com
 Project-URL: Repository, https://github.com/truemagic-coder/solana-agent
 Description-Content-Type: text/markdown
@@ -40,9 +39,11 @@ Description-Content-Type: text/markdown
 Build your AI business in three lines of code!
 
 ## Why?
-* Three lines of code required
+* Three lines of code setup
+* Multi-Agent Swarm
 * Multi-Modal Streaming
 * Conversational Memory & History
+* Built-in Internet Search
 * Intelligent Routing
 * Business Alignment
 * Extensible Tooling
@@ -53,12 +54,15 @@ Build your AI business in three lines of code!
 
 ## Features
 
+* Easy three lines of code setup
+* Designed for a multi-agent swarm 
 * Seamless text and audio streaming with real-time multi-modal processing
 * Persistent memory that preserves context across all agent interactions
+* Quick built-in Internet Search to answer your queries
 * Streamlined message history for all agent interactions
-* Intelligent query routing to agents with optimal domain expertise
+* Intelligent query routing to agents with optimal domain expertise or your own custom routing
 * Unified value system ensuring brand-aligned agent responses
-* Powerful tool integration using standard Python packages and/or inline classes
+* Powerful tool integration using standard Python packages and/or inline tools
 * Assigned tools are utilized by agents automatically and effectively
 * Simple business definition using JSON
 
@@ -67,7 +71,7 @@ Build your AI business in three lines of code!
 * [Python](https://python.org) - Programming Language
 * [OpenAI](https://openai.com) - LLMs
 * [MongoDB](https://mongodb.com) - Conversational History (optional)
-* [Zep](https://getzep.com) - Conversational Memory (optional)
+* [Zep Cloud](https://getzep.com) - Conversational Memory (optional)
 
 ## Installation
 
@@ -75,31 +79,14 @@ You can install Solana Agent using pip:
 
 `pip install solana-agent`
 
-## Basic Usage
+## Usage
+
+### Text/Text Streaming
 
 ```python
 from solana_agent import SolanaAgent
 
 config = {
-    "business": { # optional
-        "mission": "To provide users with a one-stop shop for their queries.",
-        "values": {
-            "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
-            "Ethical": "Agents must use a strong ethical framework in their interactions with users.",
-        },
-        "goals": [
-            "Empower users with great answers to their queries.",
-        ],
-        "voice": "The voice of the brand is that of a research business."
-    },
-    "mongo": { # optional
-        "connection_string": "mongodb://localhost:27017",
-        "database": "solana_agent"
-    },
-    "zep": { # optional
-        "api_key": "your-zep-api-key",
-        "base_url": "your-zep-base-url", # not applicable if using Zep Cloud
-    },
     "openai": {
         "api_key": "your-openai-api-key",
     },
@@ -123,17 +110,104 @@ async for response in solana_agent.process("user123", "What are the latest AI de
     print(response, end="")
 ```
 
-## Plugin Usage
+### Audio/Audio Streaming
 
-Plugins like Solana Agent Kit (sakit) integrate automatically with Solana Agent.
+```python
+from solana_agent import SolanaAgent
 
-`pip install sakit`
+config = {
+    "openai": {
+        "api_key": "your-openai-api-key",
+    },
+    "agents": [
+        {
+            "name": "research_specialist",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "specialization": "Research and knowledge synthesis",
+        },
+        {
+            "name": "customer_support",
+            "instructions": "You provide friendly, helpful customer support responses.",
+            "specialization": "Customer inquiries",
+        }
+    ],
+}
+
+solana_agent = SolanaAgent(config=config)
+
+audio_content = audio_file.read()
+
+async for response in solana_agent.process("user123", audio_content, output_format="audio", audio_voice="nova", audio_input_format="webm", audio_output_format="aac"):
+    print(response, end="")
+```
+
+### Text/Audio Streaming
 
 ```python
 from solana_agent import SolanaAgent
 
 config = {
-    "business": { # optional
+    "openai": {
+        "api_key": "your-openai-api-key",
+    },
+    "agents": [
+        {
+            "name": "research_specialist",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "specialization": "Research and knowledge synthesis",
+        },
+        {
+            "name": "customer_support",
+            "instructions": "You provide friendly, helpful customer support responses.",
+            "specialization": "Customer inquiries",
+        }
+    ],
+}
+
+solana_agent = SolanaAgent(config=config)
+
+async for response in solana_agent.process("user123", "What is the latest news on Elon Musk?", output_format="audio", audio_voice="nova", audio_output_format="aac"):
+    print(response, end="")
+```
+
+### Audio/Text Streaming
+
+```python
+from solana_agent import SolanaAgent
+
+config = {
+    "openai": {
+        "api_key": "your-openai-api-key",
+    },
+    "agents": [
+        {
+            "name": "research_specialist",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "specialization": "Research and knowledge synthesis",
+        },
+        {
+            "name": "customer_support",
+            "instructions": "You provide friendly, helpful customer support responses.",
+            "specialization": "Customer inquiries",
+        }
+    ],
+}
+
+solana_agent = SolanaAgent(config=config)
+
+audio_content = audio_file.read()
+
+async for response in solana_agent.process("user123", audio_content, audio_input_format="aac"):
+    print(response, end="")
+```
+
+## Optional Feature Configs
+
+### Business Alignment
+
+```python
+config = {
+    "business": {
         "mission": "To provide users with a one-stop shop for their queries.",
         "values": {
             "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
@@ -144,31 +218,70 @@ config = {
         ],
         "voice": "The voice of the brand is that of a research business."
     },
-    "openai": { # optional
-        "api_key": "your-openai-api-key",
-    },
-    "ollama": { # optional
-        "url": "your-ollama-url",
-    },
-    "mongo": { # optional
+}
+```
+
+### Conversational History
+
+```python
+config = {
+    "mongo": {
         "connection_string": "mongodb://localhost:27017",
         "database": "solana_agent"
     },
-    "zep": { # optional
-        "api_key": "your-zep-api-key",
-        "base_url": "your-zep-base-url", # not applicable if using Zep Cloud
+}
+```
+
+### Conversational Memory
+
+```python
+config = {
+    "zep": {
+        "api_key": "your-zep-cloud-api-key",
+    },
+}
+```
+
+### Disable Internet Searching
+
+```python
+async for response in solana_agent.process("user123", "Write me a poem.", internet_search=False):
+    print(response, end="")
+```
+
+### Customize Audio Voice
+
+This is an audio to audio example using the `audio_instructions` parameter.
+
+```python
+async for response in solana_agent.process("user123", audio_content, output_format="audio", audio_voice="nova", audio_input_format="webm", audio_output_format="aac", audio_instructions="You speak with an American southern accent"):
+    print(response, end="")
+```
+
+## Tools
+
+Tools can be used from plugins like Solana Agent Kit (sakit) or via custom inline tools. Tools available via plugins integrate automatically with Solana Agent.
+
+### Plugin Usage Example
+
+`pip install sakit`
+
+```python
+from solana_agent import SolanaAgent
+
+config = {
+    "openai": {
+        "api_key": "your-openai-api-key",
     },
     "tools": {
         "search_internet": {
-            "api_key": "your-perplexity-key", # Required
-            "citations": True, # Optional, defaults to True
-            "model": "sonar"  # Optional, defaults to "sonar"
+            "api_key": "your-perplexity-api-key",
         },
     },
     "agents": [
         {
             "name": "research_specialist",
-            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly. You use your search_internet tool to get the latest information.",
             "specialization": "Research and knowledge synthesis",
             "tools": ["search_internet"],
         },
@@ -182,13 +295,11 @@ config = {
 
 solana_agent = SolanaAgent(config=config)
 
-async for response in solana_agent.process("user123", "What are the latest AI developments?"):
+async for response in solana_agent.process("user123", "What are the latest AI developments?", internet_search=False):
     print(response, end="")
 ```
 
-To create a plugin like Solana Agent Kit - read the [code](https://github.com/truemagic-coder/solana-agent-kit)
-
-## Custom Inline Tool Usage
+### Custom Inline Tool Example
 
 ```python
 from solana_agent import SolanaAgent
@@ -241,31 +352,9 @@ class TestTool(Tool):
             }
 
 config = {
-    "business": { # optional
-        "mission": "To provide users with a one-stop shop for their queries.",
-        "values": {
-            "Friendliness": "Users must be treated fairly, openly, and with friendliness.",
-            "Ethical": "Agents must use a strong ethical framework in their interactions with users.",
-        },
-        "goals": [
-            "Empower users with great answers to their queries.",
-        ],
-        "voice": "The voice of the brand is that of a research business."
-    },
-    "openai": { # optional
+    "openai": {
         "api_key": "your-openai-api-key",
     },
-    "ollama": { # optional
-        "url": "your-ollama-url",
-    },
-    "mongo": { # optional
-        "connection_string": "mongodb://localhost:27017",
-        "database": "solana_agent"
-    },
-    "zep": { # optional
-        "api_key": "your-zep-api-key",
-        "base_url": "your-zep-base-url", # not applicable if using Zep Cloud
-    },
     "agents": [
         {
             "name": "research_specialist",
@@ -284,18 +373,93 @@ solana_agent = SolanaAgent(config=config)
 
 test_tool = TestTool()
 
-solana_agent.register_tool(test_tool)
+solana_agent.register_tool("customer_support", test_tool)
 
 async for response in solana_agent.process("user123", "What are the latest AI developments?"):
     print(response, end="")
 ```
 
+## Training your Agents
+
+Many use-cases for Solana Agent require training your agents on your company data.
+
+This can be accomplished via runtime prompt injection. Integrations that work well with this method are KBs like Pinecone and FAQs.
+
+```python
+from solana_agent import SolanaAgent
+
+config = {
+    "openai": {
+        "api_key": "your-openai-api-key",
+    },
+    "agents": [
+        {
+            "name": "research_specialist",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "specialization": "Research and knowledge synthesis",
+        },
+        {
+            "name": "customer_support",
+            "instructions": "You provide friendly, helpful customer support responses.",
+            "specialization": "Customer inquiries",
+        }
+    ],
+}
+
+solana_agent = SolanaAgent(config=config)
+
+async for response in solana_agent.process("user123", "What are the latest AI developments?", "This is my FAQ"):
+    print(response, end="")
+```
+
+## Custom Routing
+
+In advanced cases like implementing a ticketing system on-top of Solana Agent - you can use your own router.
+
+```python
+from solana_agent import SolanaAgent
+from solana_agent.interfaces.services.routing import RoutingService as RoutingServiceInterface
+
+config = {
+    "openai": {
+        "api_key": "your-openai-api-key",
+    },
+    "agents": [
+        {
+            "name": "research_specialist",
+            "instructions": "You are an expert researcher who synthesizes complex information clearly.",
+            "specialization": "Research and knowledge synthesis",
+        },
+        {
+            "name": "customer_support",
+            "instructions": "You provide friendly, helpful customer support responses.",
+            "specialization": "Customer inquiries",
+        }
+    ],
+}
+
+class Router(RoutingServiceInterface)
+    def __init__(self):
+        # your router initialization - delete the following pass
+        pass
+
+    async def route_query(self, query: str) -> str:
+        # a simple example to route always to customer_support agent
+        return "customer_support"
+
+router = Router()
+
+solana_agent = SolanaAgent(config=config)
+
+async for response in solana_agent.process("user123", "What are the latest AI developments?", router=router):
+    print(response, end="")
+```
+
 ## Notes
 * Solana Agent agents can only call one tool per response.
 * Solana Agent agents choose the best tool for the job.
 * Solana Agent tools do not use OpenAI function calling.
 * Solana Agent tools are async functions.
-* Solana Agent will use OpenAI for audio and Ollama and for text if both config vars are set
 
 ## Local Setup