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

@@ -11,6 +11,7 @@ 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 ToolsCatalog
+from vectara_agentic.types import ModelProvider, AgentType
 
 teaching_styles = ['Inquiry-based', 'Socratic', 'traditional']
 languages = {'English': 'en', 'Spanish': 'es', 'French': 'fr', 'German': 'de', 'Arabic': 'ar', 'Chinese': 'zh-cn', 
@@ -22,8 +23,10 @@ class AgentTools:
         self.tools_factory = ToolsFactory()
         self.agent_config = agent_config
         self.cfg = _cfg
-        self.vec_factory = VectaraToolFactory(vectara_api_key=_cfg.api_key,
-                                              vectara_corpus_key=_cfg.corpus_key)
+        self.vec_factory = VectaraToolFactory(
+            vectara_api_key=_cfg.api_key,
+            vectara_corpus_key=_cfg.corpus_key
+        )
 
     def adjust_response_to_student(
             self,
@@ -54,23 +57,22 @@ class AgentTools:
 
 
     def get_tools(self):
-        class JusticeHarvardArgs(BaseModel):
-            query: str = Field(..., description="The user query.")
-
         vec_factory = VectaraToolFactory(vectara_api_key=self.cfg.api_key,vectara_corpus_key=self.cfg.corpus_key)
-        summarizer = 'vectara-summary-ext-24-05-med-omni'
+        summarizer = 'vectara-summary-table-md-query-ext-jan-2025-gpt-4o'
         query_tool = vec_factory.create_rag_tool(
             tool_name = "ask_about_justice_harvard",
             tool_description = """
             Answer questions about the justice, morality, politics and related topics,
             based on transcripts of recordings from the Justice Harvard class that includes a lot of content on these topics.
             """,
-            tool_args_schema = JusticeHarvardArgs,
-            reranker = "multilingual_reranker_v1", rerank_k = 100,
+            reranker = "multilingual_reranker_v1", rerank_k = 100, rerank_cutoff = 0.3,
             n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-            summary_num_results = 10,
+            summary_num_results = 15,
+            max_tokens = 4096, max_response_chars = 8192,
             vectara_summarizer = summarizer,
             include_citations = True,
+            verbose = False,
+            save_history = True,
         )
 
         tools_factory = ToolsFactory()
@@ -80,7 +82,7 @@ class AgentTools:
                         self.adjust_response_to_student,
                     ]
                 ] +
-                tools_factory.standard_tools() + 
+                tools_factory.standard_tools() +
                 tools_factory.guardrail_tools() +
                 [query_tool]
         )
@@ -89,7 +91,8 @@ def initialize_agent(_cfg, agent_progress_callback=None):
     bot_instructions = f"""
     - You are a helpful teacher assistant, with expertise in education in various teaching styles.
     - Obtain information using tools to answer the user's query.
-    - If the tool cannot provide information relevant to the user's query, tell the user that you are unable to provide an answer.
+    - If the tool cannot provide information relevant to the user's query, try calling the tool again with a rephrased query.
+      If it fails 3 times, then tell the user that you are unable to provide an answer.
     - If the tool can provide relevant information, use the adjust_response_to_student tool 
       to rephrase the text (including citations if any) to ensure it fits the student's age of {_cfg.student_age}, 
       the {_cfg.style} teaching style and the {_cfg.language} language.
@@ -99,9 +102,26 @@ 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_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(
         agent_config=agent_config,
+        fallback_agent_config=fallback_agent_config,
         tools=AgentTools(_cfg, agent_config).get_tools(),
         topic="justice, morality, politics, and philosophy",
         custom_instructions=bot_instructions,

requirements.txt

@@ -1,10 +1,10 @@
 omegaconf==2.3.0
 python-dotenv==1.0.1
-streamlit==1.41.1
+streamlit==1.45.0
 streamlit_pills==0.3.0
 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

@@ -153,7 +153,7 @@ 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)