solana-agent 22.0.5__tar.gz → 22.0.6__tar.gz

{solana_agent-22.0.5 → solana_agent-22.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 22.0.5
+Version: 22.0.6
 Summary: Agentic IQ
 License: MIT
 Keywords: ai,openai,ai agents,agi
@@ -262,7 +262,12 @@ async for response in solana_agent.process("user123", audio_content, output_form
 
 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
+* Agents can only call one tool per response
+* Agents choose the best tool for the job
+* Tools do not use OpenAI function calling
+* Tools are async functions
+
+### Tool Usage Example
 
 `pip install sakit`
 
@@ -379,11 +384,13 @@ async for response in solana_agent.process("user123", "What are the latest AI de
     print(response, end="")
 ```
 
-## Training your Agents
+## Agent Training
 
 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.
+This can be accomplished via runtime prompt injection. Integrations that work well with this method are vector stores like Pinecone and FAQs.
+
+This knowledge applies to all your AI agents.
 
 ```python
 from solana_agent import SolanaAgent
@@ -393,11 +400,6 @@ config = {
         "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.",
@@ -408,7 +410,7 @@ config = {
 
 solana_agent = SolanaAgent(config=config)
 
-async for response in solana_agent.process("user123", "What are the latest AI developments?", "This is my FAQ"):
+async for response in solana_agent.process("user123", "How do replace the latch on my dishwasher?", "This is my corporate appliance fixing FAQ"):
     print(response, end="")
 ```
 
@@ -455,16 +457,6 @@ async for response in solana_agent.process("user123", "What are the latest AI de
     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.
-
-## Local Setup
-
-A Docker Compose and Zep Config file is available at the root of this project
-
 ## API Documentation
 
 The official up-to-date documentation site

{solana_agent-22.0.5 → solana_agent-22.0.6}/README.md

@@ -238,7 +238,12 @@ async for response in solana_agent.process("user123", audio_content, output_form
 
 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
+* Agents can only call one tool per response
+* Agents choose the best tool for the job
+* Tools do not use OpenAI function calling
+* Tools are async functions
+
+### Tool Usage Example
 
 `pip install sakit`
 
@@ -355,11 +360,13 @@ async for response in solana_agent.process("user123", "What are the latest AI de
     print(response, end="")
 ```
 
-## Training your Agents
+## Agent Training
 
 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.
+This can be accomplished via runtime prompt injection. Integrations that work well with this method are vector stores like Pinecone and FAQs.
+
+This knowledge applies to all your AI agents.
 
 ```python
 from solana_agent import SolanaAgent
@@ -369,11 +376,6 @@ config = {
         "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.",
@@ -384,7 +386,7 @@ config = {
 
 solana_agent = SolanaAgent(config=config)
 
-async for response in solana_agent.process("user123", "What are the latest AI developments?", "This is my FAQ"):
+async for response in solana_agent.process("user123", "How do replace the latch on my dishwasher?", "This is my corporate appliance fixing FAQ"):
     print(response, end="")
 ```
 
@@ -431,16 +433,6 @@ async for response in solana_agent.process("user123", "What are the latest AI de
     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.
-
-## Local Setup
-
-A Docker Compose and Zep Config file is available at the root of this project
-
 ## API Documentation
 
 The official up-to-date documentation site

{solana_agent-22.0.5 → solana_agent-22.0.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "solana-agent"
-version = "22.0.5"
+version = "22.0.6"
 description = "Agentic IQ"
 authors = ["Bevan Hunt <bevan@bevanhunt.com>"]
 license = "MIT"