Use intent model from archfc to pick prompt gateway (#328)

docs/source/build_with_arch/multi_turn.rst

@@ -0,0 +1,90 @@
+.. _arch_multi_turn_guide:
+
+Multi-Turn
+==========
+Developers often `struggle <https://www.reddit.com/r/LocalLLaMA/comments/18mqwg6/best_practice_for_rag_with_followup_chat/>`_ to efficiently handle
+``follow-up`` or ``clarification`` questions. Specifically, when users ask for changes or additions to previous responses, it requires developers to
+re-write prompts using LLMs with precise prompt engineering techniques. This process is slow, manual, error prone and adds latency and token cost for
+common scenarios that can be managed more efficiently.
+
+Arch is highly capable of accurately detecting and processing prompts in multi-turn scenarios so that you can buil fast and accurate agents in minutes.
+Below are some cnversational examples that you can build via Arch. Each example is enriched with annotations (via ** [Arch] ** ) that illustrates how Arch
+processess conversational messages on your behalf.
+
+.. Note::
+    The following section assumes that you have some knowledge about the core concepts of Arch, such as :ref:`prompt_targets <arch_overview_prompt_handling>`.
+    If you haven't familizaried yourself with Arch's concepts, we recommend you first read the :ref:`tech overview <tech_overview>` section firtst.
+    Additionally, the conversation examples below assume the usage of the following :ref:`arch_config.yaml <multi_turn_subsection_prompt_target>` file.
+
+Example 1: Adjusting Retrieval
+------------------------------
+.. code-block:: text
+
+    User: What are the benefits of renewable energy?
+    **[Arch]**: Check if there is an available <prompt_target> that can handle this user query.
+    **[Arch]**: Found "get_info_for_energy_source" prompt_target in arch_config.yaml. Forward prompt to the endpoint configured in "get_info_for_energy_source"
+    ...
+    Assistant: Renewable energy reduces greenhouse gas emissions, lowers air pollution, and provides sustainable power sources like solar and wind.
+
+    User: Include cost considerations in the response.
+    **[Arch]**: Follow-up detected. Forward prompt history to the "get_info_for_energy_source" prompt_target and post the following parameters consideration="cost"
+    ...
+    Assistant: Renewable energy reduces greenhouse gas emissions, lowers air pollution, and provides sustainable power sources like solar and wind. While the initial setup costs can be high, long-term savings from reduced fuel expenses and government incentives make it cost-effective.
+
+
+Example 2: Switching Intent
+---------------------------
+.. code-block:: text
+
+    User: What are the symptoms of diabetes?
+    **[Arch]**: Check if there is an available <prompt_target> that can handle this user query.
+    **[Arch]**: Found "diseases_symptoms" prompt_target in arch_config.yaml. Forward disease=diabeteres to "diseases_symptoms" prompt target
+    ...
+    Assistant: Common symptoms include frequent urination, excessive thirst, fatigue, and blurry vision.
+
+    User: How is it diagnosed?
+    **[Arch]**: New intent detected.
+    **[Arch]**: Found "disease_diagnoses" prompt_target in arch_config.yaml. Forward disease=diabeteres to "disease_diagnoses" prompt target
+    ...
+    Assistant: Diabetes is diagnosed through blood tests like fasting blood sugar, A1C, or an oral glucose tolerance test.
+
+
+Build Multi-Turn RAG Apps
+--------------------------
+The following section describes how you can easilly add support for multi-turn scenarios via Arch. You process and manage multi-turn prompts
+just like you manage single-turn ones. Arch handles the conpleixity of detecting the correct intent based on the last user prompt and
+the covnersational history, extracts relevant parameters needed by downstream APIs, and dipatches calls to any upstream LLMs to summarize the
+response from your APIs.
+
+
+.. _multi_turn_subsection_prompt_target:
+
+Step 1: Define Arch Config
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. literalinclude:: includes/multi_turn/prompt_targets_multi_turn.yaml
+    :language: yaml
+    :caption: Arch Config
+    :linenos:
+
+Step 2: Process Request in Flask
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Once the prompt targets are configured as above, handle parameters across multi-turn as if its a single-turn request
+
+.. literalinclude:: includes/multi_turn/multi_turn_rag.py
+    :language: python
+    :caption: Parameter handling with Flask
+    :linenos:
+
+Demo App
+~~~~~~~~
+
+For your convenience, we've built a `demo app <https://github.com/katanemo/archgw/main/demos/multi_turn_rag_agent>`_
+that you can test and modify locally for multi-turn RAG scenarios.
+
+.. figure:: includes/multi_turn/mutli-turn-example.png
+   :width: 100%
+   :align: center
+
+   Example multi-turn user conversation showing adjusting retrieval