apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-26 09:16:24 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update doc (#178)

Browse source 
* Update doc

* Update links
This commit is contained in:
Shuguang Chen 2024-10-10 22:30:54 -07:00 • committed by GitHub
parent 7b51cce2f7
commit 11fba23f1f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 82 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

12
docs/source/build_with_arch/rag.rst
View file

@ -9,7 +9,7 @@ Retrieval-Augmented Generation (RAG) applications.
Parameter Extraction for RAG
----------------------------
To build RAG (Retrieval-Augmented Generation) applications, you can configure prompt targets with parameters,
To build RAG (Retrieval Augmented Generation) applications, you can configure prompt targets with parameters,
enabling Arch to retrieve critical information in a structured way for processing. This approach improves the
retrieval quality and speed of your application. By extracting parameters from the conversation, you can pull
the appropriate chunks from a vector database or SQL-like data store to enhance accuracy. With Arch, you can
@ -37,12 +37,12 @@ Once the prompt targets are configured as above, handling those parameters is
-----------------------------------------------------------------------------------------------------------------------------------------
Developers struggle to efficiently handle ``follow-up`` or ``clarification`` questions. Specifically, when users ask for
changes or additions to previous responses their AI applications often generate entirely new responses instead of adjusting
previous ones.Arch offers **intent** tracking as a feature so that developers can know when the user has shifted away from a
previous ones. Arch offers ``intent tracking`` as a feature so that developers can know when the user has shifted away from a
previous intent so that they can dramatically improve retrieval accuracy, lower overall token cost and improve the speed of
their responses back to users.
Arch uses its built-in lightweight NLI and embedding models to know if the user has steered away from an active intent.
Arch's intent-drift detection mechanism is based on its' :ref:`prompt_targets <prompt_target>` primtive. Arch tries to match an incoming
Arch's intent-drift detection mechanism is based on its :ref:`prompt target <prompt_target>` primtive. Arch tries to match an incoming
prompt to one of the prompt_targets configured in the gateway. Once it detects that the user has moved away from an active
active intent, Arch adds the ``x-arch-intent-marker`` headers to the request before sending it your application servers.
@ -50,15 +50,15 @@ active intent, Arch adds the ``x-arch-intent-marker`` headers to the request bef
:language: python
:linenos:
:lines: 101-157
:emphasize-lines: 14-24
:emphasize-lines: 14-25
:caption: Intent Detection Example
.. Note::
Arch is (mostly) stateless so that it can scale in an embarrassingly parrallel fashion. So, while Arch offers
intent-drift detetction, you still have to maintain converational state with intent drift as meta-data. The
following code snippets show how easily you can build and enrich conversational history with Langchain (in python),
intent-drift detetction, you still have to maintain converational state with intent drift as metadata. The
following code snippets show how easily you can build and enrich conversational history with Langchain (in Python),
so that you can use the most relevant prompts for your retrieval and for prompting upstream LLMs.