version bump

agent.py

@@ -8,15 +8,16 @@ load_dotenv(override=True)
 
 from pydantic import Field, BaseModel
 from vectara_agentic.agent import Agent
+from vectara_agentic.agent_config import AgentConfig
 from vectara_agentic.tools import ToolsFactory, VectaraToolFactory
-from vectara_agentic.tools_catalog import rephrase_text
+from vectara_agentic.tools_catalog import ToolsCatalog
 
 teaching_styles = ['Inquiry-based', 'Socratic', 'traditional']
 languages = {'English': 'en', 'Spanish': 'es', 'French': 'fr', 'German': 'de', 'Arabic': 'ar', 'Chinese': 'zh-cn', 
              'Hebrew': 'he', 'Hindi': 'hi', 'Italian': 'it', 'Japanese': 'ja', 'Korean': 'ko', 'Portuguese': 'pt'}
 initial_prompt = "How can I help you today?"
 
-def create_assistant_tools(cfg):        
+def create_assistant_tools(cfg, agent_config):        
 
     def adjust_response_to_student(
             text: str = Field(description='the text to adjust. may include citations in markdown format.'), 
@@ -41,15 +42,14 @@ def create_assistant_tools(cfg):
             .replace("{language}", cfg.language) \
             .replace("{student_age}", str(cfg.student_age))
 
+        rephrase_text = ToolsCatalog(agent_config).rephrase_text
         return rephrase_text(text, instructions)
 
 
     class JusticeHarvardArgs(BaseModel):
         query: str = Field(..., description="The user query.")
 
-    vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_key, 
-                                     vectara_customer_id=cfg.customer_id, 
-                                     vectara_corpus_id=cfg.corpus_id)
+    vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_key,vectara_corpus_key=cfg.corpus_key)
     summarizer = 'vectara-summary-ext-24-05-med-omni'
     query_tool = vec_factory.create_rag_tool(
         tool_name = "ask_about_justice_harvard",
@@ -91,9 +91,10 @@ def initialize_agent(_cfg, agent_progress_callback=None):
     - Response in a concise and clear manner, and provide the most relevant information to the student.
     - Never discuss politics, and always respond politely.
     """
-
+    agent_config = AgentConfig()
     agent = Agent(
-        tools=create_assistant_tools(_cfg),
+        agent_config=agent_config,
+        tools=create_assistant_tools(_cfg, agent_config=agent_config),
         topic="justice, morality, politics, and philosophy",
         custom_instructions=bot_instructions,
         agent_progress_callback=agent_progress_callback
@@ -103,8 +104,7 @@ def initialize_agent(_cfg, agent_progress_callback=None):
 
 def get_agent_config() -> OmegaConf:
     cfg = OmegaConf.create({
-        'customer_id': str(os.environ['VECTARA_CUSTOMER_ID']),
-        'corpus_id': str(os.environ['VECTARA_CORPUS_ID']),
+        'corpus_key': str(os.environ['VECTARA_CORPUS_KEY']),
         'api_key': str(os.environ['VECTARA_API_KEY']),
         'examples': os.environ.get('QUERY_EXAMPLES', None),
         'demo_name': "Justice-Harvard",

requirements.txt

@@ -6,4 +6,4 @@ streamlit_feedback==0.1.3
 uuid==1.30
 langdetect==1.0.9
 langcodes==3.4.0
-vectara-agentic==0.1.22
+vectara-agentic==0.2.0

st_app.py

@@ -154,8 +154,8 @@ async def launch_bot():
     if st.session_state.prompt:
         with st.chat_message("assistant", avatar='🤖'):
             st.session_state.status = st.status('Processing...', expanded=False)
-            res = st.session_state.agent.chat(st.session_state.prompt)
-            res = escape_dollars_outside_latex(res)
+            response = st.session_state.agent.chat(st.session_state.prompt)
+            res = escape_dollars_outside_latex(response.response)
             message = {"role": "assistant", "content": res, "avatar": '🤖'}
             st.session_state.messages.append(message)
             st.markdown(res)