updated

Dockerfile

@@ -7,12 +7,15 @@ COPY ./requirements.txt /app/requirements.txt
 RUN pip3 install --no-cache-dir --upgrade pip
 RUN pip3 install --no-cache-dir wheel setuptools build
 RUN pip3 install --no-cache-dir --use-pep517 -r /app/requirements.txt
-
+ 
 # User
 RUN useradd -m -u 1000 user
 USER user
 ENV HOME /home/user
 ENV PATH $HOME/.local/bin:$PATH
+ENV TIKTOKEN_CACHE_DIR $HOME/.cache/tiktoken
+
+RUN mkdir -p $HOME/.cache/tiktoken
 
 WORKDIR $HOME
 RUN mkdir app

agent.py

@@ -1,39 +1,47 @@
 import os
 from omegaconf import OmegaConf
 from vectara_agentic.agent import Agent
+from vectara_agentic.agent_config import AgentConfig
+from vectara_agentic.types import ModelProvider, AgentType
 
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
 initial_prompt = "How can I help you today?"
 
-
 def initialize_agent(_cfg, agent_progress_callback=None):
+
+    agent_config = AgentConfig(
+        agent_type = os.getenv("VECTARA_AGENTIC_AGENT_TYPE", AgentType.OPENAI.value),
+        main_llm_provider = os.getenv("VECTARA_AGENTIC_MAIN_LLM_PROVIDER", ModelProvider.OPENAI.value),
+        main_llm_model_name = os.getenv("VECTARA_AGENTIC_MAIN_MODEL_NAME", ""),
+        tool_llm_provider = os.getenv("VECTARA_AGENTIC_TOOL_LLM_PROVIDER", ModelProvider.OPENAI.value),
+        tool_llm_model_name = os.getenv("VECTARA_AGENTIC_TOOL_MODEL_NAME", ""),
+        observer = os.getenv("VECTARA_AGENTIC_OBSERVER_TYPE", "NO_OBSERVER")
+    )
+    fallback_agent_config = AgentConfig(
+        agent_type = os.getenv("VECTARA_AGENTIC_FALLBACK_AGENT_TYPE", AgentType.OPENAI.value),
+        main_llm_provider = os.getenv("VECTARA_AGENTIC_FALLBACK_MAIN_LLM_PROVIDER", ModelProvider.OPENAI.value),
+        main_llm_model_name = os.getenv("VECTARA_AGENTIC_FALLBACK_MAIN_MODEL_NAME", ""),
+        tool_llm_provider = os.getenv("VECTARA_AGENTIC_FALLBACK_TOOL_LLM_PROVIDER", ModelProvider.OPENAI.value),
+        tool_llm_model_name = os.getenv("VECTARA_AGENTIC_FALLBACK_TOOL_MODEL_NAME", ""),
+        observer = os.getenv("VECTARA_AGENTIC_OBSERVER_TYPE", "NO_OBSERVER")
+    )
+
     agent = Agent.from_corpus(
         vectara_corpus_key=_cfg.corpus_key,
         vectara_api_key=_cfg.api_key,
         tool_name="ask_ucsf_ortho",
         data_description="UCSF Orthopedic Website",
-        assistant_specialty="UCSF Orthopedic department",
-        vectara_summarizer="vectara-summary-ext-24-05-med-omni",
-        # vectara_reranker = "chain", vectara_rerank_k = 100, 
-        # vectara_rerank_chain = [
-        #     {
-        #         "type": "multilingual_reranker_v1",
-        #         "cutoff": 0.5,
-        #         "limit": 100
-        #     },
-        #     {
-        #         "type": "mmr",
-        #         "diversity_bias": 0.1
-        #     }
-        # ],
-        vectara_reranker="multilingual_reranker_v1",
-        vectara_rerank_k=100,
+        assistant_specialty="UCSF Orthopedic department, helping users with questions about the department.",
+        vectara_reranker="multilingual_reranker_v1", vectara_rerank_k=100,
         vectara_lambda_val=0.005,
-        vectara_summary_num_results=25,
-        verbose=False,
+        vectara_summarizer="vectara-summary-table-md-query-ext-jan-2025-gpt-4o",
+        vectara_summary_num_results=20,
+        verbose=True,
         agent_progress_callback=agent_progress_callback,
+        agent_config=agent_config,
+        fallback_agent_config=fallback_agent_config,
     )
     agent.report()
     return agent

requirements.txt

@@ -1,9 +1,9 @@
 omegaconf==2.3.0
 python-dotenv==1.0.1
-streamlit==1.43.2
+streamlit==1.45.0
 streamlit_feedback==0.1.3
 uuid==1.30
 langdetect==1.0.9
 langcodes==3.4.0
-vectara-agentic==0.2.9
-torch==2.6.0
+vectara-agentic==0.2.15
+torch==2.6.0

st_app.py

@@ -131,7 +131,7 @@ async def launch_bot():
     if st.session_state.prompt:
         with st.chat_message("assistant", avatar='🤖'):
             st.session_state.status = st.status('Processing...', expanded=False)
-            response = st.session_state.agent.chat(st.session_state.prompt)
+            response = await st.session_state.agent.achat(st.session_state.prompt)
             res = escape_dollars_outside_latex(response.response)
             message = {"role": "assistant", "content": res, "avatar": '🤖'}
             st.session_state.messages.append(message)