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

@@ -5,12 +5,17 @@ from omegaconf import OmegaConf
 
 from vectara_agentic.agent import Agent
 from vectara_agentic.tools import VectaraToolFactory
+from vectara_agentic.types import ModelProvider, AgentType
+from vectara_agentic.agent_config import AgentConfig
 
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
 initial_prompt = "How can I help you today?"
 
+    # Never refer to the search results in your response.
+    # Ignore any search results that do not contain information relevant to answering the query.
+
 prompt = """
 [
   {"role": "system", "content": 
@@ -18,10 +23,10 @@ prompt = """
   },
   {"role": "user", "content": " 
     [INSTRUCTIONS]
+    Your goal is to help the user with customer support and diagnostics questions about hardware and servers (SuperMicro products).
     If the search results are irrelevant to the question respond with *** I do not have enough information to answer this question.***
     Search results may include tables in a markdown format. When answering a question using a table be careful about which rows and columns contain the answer and include all relevant information from the relevant rows and columns that the query is asking about.
     Do not base your response on information or knowledge that is not in the search results.
-    Make sure your response is answering the query asked. If the query is related to an entity (such as a person or place), make sure you use search results related to that entity.
     Your output should always be in a single language - the $vectaraLangName language. Check spelling and grammar for the $vectaraLangName language.
     Search results for the query *** $vectaraQuery***, are listed below, some are text, some MAY be tables in markdown format.
     #foreach ($qResult in $vectaraQueryResultsDeduped)
@@ -35,7 +40,6 @@ prompt = """
     #end
     Think carefully step by step, analyze the search results provided, and craft a clear and accurate response to *** $vectaraQuery *** using information and facts in the search results provided. 
     Give a slight preference to search results that appear earlier in the list.
-    Your goal is to help with customer support and diagnostics questions about hardware (SuperMicro products).
     Only cite relevant search results in your answer following these specific instructions: $vectaraCitationInstructions
     If the search results are irrelevant to the query, respond with ***I do not have enough information to answer this question.***. 
     Respond always in the $vectaraLangName language, and only in that language."}
@@ -45,11 +49,12 @@ prompt = """
 def create_assistant_tools(cfg):
 
     class QueryTIProducts(BaseModel):
-        query: str = Field(description="The user query.")
         name: Optional[str] = Field(
-            default="",
-            description="The server name.",
-            examples=['SuperServer SYS-821GE-TNHR', 'A+ Server AS -4125GS-TNRT']
+            description="The server name",
+            examples=[
+                "SuperServer SYS-821GE-TNHR",
+                "A+ Server AS-4125GS-TNRT"
+            ]
         )
     vec_factory = VectaraToolFactory(
         vectara_api_key=cfg.api_key,
@@ -64,25 +69,27 @@ def create_assistant_tools(cfg):
         returns a response to a user question about Supermicro servers.
         """,
         tool_args_schema = QueryTIProducts,
-        reranker = "slingshot", rerank_k = 100, rerank_cutoff = 0.1,
-        # reranker = "chain", rerank_k = 100,
-        #     rerank_chain = [
-        #         {
-        #             "type": "slingshot",
-        #             "cutoff": 0.2
-        #         },
-        #         {
-        #             "type": "mmr",
-        #             "diversity_bias": 0.1
-        #         },
-        #     ],
-        n_sentences_before = 2, n_sentences_after = 6, lambda_val = 0.02,
+        n_sentences_before = 2, n_sentences_after = 8, lambda_val = 0.01,
+        #reranker = "slingshot", rerank_k = 100, rerank_cutoff = 0.3,
+        reranker = "chain", rerank_k = 100,
+        rerank_chain = [
+            {
+                "type": "slingshot",
+                "cutoff": 0.3
+            },
+            {
+                "type": "mmr",
+                "diversity_bias": 0.1
+            },
+        ],
+        max_tokens = 4096, max_response_chars = 8192,
         vectara_summarizer = summarizer,
         vectara_prompt_text = prompt,
         summary_num_results = 15,
         include_citations = True,
-        verbose = True,
-        save_history = True
+        verbose = False,
+        save_history = True,
+        fcs_threshold = 0.2,
     )
 
     # search_supermicro = vec_factory.create_search_tool(
@@ -93,6 +100,9 @@ def create_assistant_tools(cfg):
     #     """,
     #     tool_args_schema = QueryTIProducts,
     #     reranker = "slingshot", rerank_k = 100, rerank_cutoff = 0.5,
+    #     n_sentences_before = 0, n_sentences_after = 0,
+    #     save_history = True,
+    #     summarize_docs = True
     # )
 
     return [ask_supermicro] #, search_supermicro]
@@ -101,18 +111,40 @@ def initialize_agent(_cfg, agent_progress_callback=None):
     bot_instructions = """
     - You are a helpful assistant, with expertise in diagnosing customer issues related to SuperMicro products.
       You can help diagnose, troubleshoot and understand hardware issues.
-    - Always use the 'ask_supermicro' tool to get the information you need to respond to the user query, 
-      and never use your internal knoweldge.
-    - WHen using the 'ask_supermicro' tool, always rephrase the query to the tool as a diagnostics question.
-      If the tool does not return relevant information, try to rephrase the query in a different way, and call the tool again.
+    - Use the 'ask_supermicro' tool to get the information about server, components, or diagnostics steps 
+      so that you can use this information in aggregate to formulate your response to the user.
+    - Never use your internal knoweldge.
+    - Form queries to 'ask_supermicro' tool always as question, and in a way that maximizes the chance of getting a relevant answer.
+    - If the 'ask_supermicro' tool responds with "I do not have enough information to answer this question" or "suspected hallucination",
+      try to rephrase the query to 'ask_supermicro' as a diagnostic question and call the 'ask_supermicro' tool again.
     """
 
+    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(
         tools=create_assistant_tools(_cfg),
         topic="troubleshooting Supermicro products",
         custom_instructions=bot_instructions,
         agent_progress_callback=agent_progress_callback,
         use_structured_planning=False,
+        agent_config=agent_config,
+        fallback_agent_config=fallback_agent_config,
+        verbose=True,
     )
     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==0.2.11
+vectara-agentic==0.2.15
 torch==2.6.0

st_app.py

@@ -8,6 +8,7 @@ from streamlit_feedback import streamlit_feedback
 from utils import thumbs_feedback, escape_dollars_outside_latex, send_amplitude_data
 
 from vectara_agentic.agent import AgentStatusType
+
 from agent import initialize_agent, get_agent_config
 
 initial_prompt = "How can I help you today?"
@@ -131,7 +132,7 @@ 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)