Adding analyze to the example chatbot application (#29)

* Initial commit

Adding the Aimon Rely README, images, the postman collection, a simple client and examples.

A few small changes for error handling in the client and the example application.

Getting the Aimon API key from the streamlit app

updating README

Updating langchain example gif

Updating API endpoint

Adding V2 API with support for conciseness, completeness and toxicity checks (#1)

* Adding V2 API with support for conciseness, completeness and toxicity checks.

* Removing prints and updating config for the example application.

* Updating README

---------

Co-authored-by: Preetam Joshi <info@aimon.ai>

Updating postman collection

Fixed the simple aimon client's handling of batch requests.

Updated postman collection. Added support for a user_query parameter in the input data dictionary.

Updating readme

Fixed bug in the example app

Uploading client code

Adding more convenience APIs

Fixing bug in create_dataset

Added Github actions config to publish to PyPI. Cleaned up dependencies and updated documentation.

Fixing langchain example

Fixing doc links

Formatting changes

Changes for aimon-rely

* Adding instruction adherence and hallucination v0.2 to the client

Updating git ignore

Adding more to gitignore

Removing .idea files

* Fixing doc string

* Updating documentation

* Updating Client to use V3 API

* Fixing test

* Updating tests

* Updating documentation in the client

* Adding .streamlit dir to .gitignore

* initial version of decorators for syntactic sugar

* A few more changes

* updating analyze and detect decorators

* Adding new notebooks

* Fixing bug in analyze decorator

* Updating Detect decorator to make it simpler. Adding Metaflow example. Adding documentation for the chatbot.

* fixing chatbot example

* Fixed issue in detect decorator. Improved code organization.

* fixed typo

* Updated the decorators with a more cleaner interface. Added a metaflow analyze example.

* Updated version

* Updated Notebook

* Fixing context parsing issue with analyze_eval decorator

* Updating application to production in the analyze_prod decorator

* Updating SDK to handle instructions in evaluation and continuous monitoring.

* Deleting old notebook

* Fixing usability issues in the chatbot. Organizing examples a bit better.

* Adding analyze to the chatbot

---------

Co-authored-by: Preetam Joshi <info@aimon.ai>

Author: pjoshi30

examples/streamlit_apps/chatbot/aimon_chatbot_demo.py

@@ -5,7 +5,7 @@
 from llama_index.core.memory import ChatMemoryBuffer
 from llama_index.core import StorageContext, load_index_from_storage
 from llama_index.readers.web import SimpleWebPageReader
-from aimon import Detect
+from aimon import Detect, AnalyzeProd, Application, Model
 from aimon import AuthenticationError
 import logging
 import os
@@ -21,8 +21,9 @@
     'completeness': {'detector_name': 'default'},
     'toxicity': {'detector_name': 'default'},
 }
-detect = Detect(values_returned=['context', 'user_query', 'instructions', 'generated_text'], api_key=os.getenv("AIMON_API_KEY"), config=aimon_config)
-
+values_returned = ['context', 'user_query', 'instructions', 'generated_text']
+detect = Detect(values_returned=values_returned, api_key=os.getenv("AIMON_API_KEY"), config=aimon_config)
+analyze_prod = AnalyzeProd(Application("paul_graham_chatbot_aug_2024"), Model("gpt_4o_model", "GPT-4o"), values_returned=values_returned, config=aimon_config)
 
 @st.cache_resource(show_spinner=False)
 def load_data():
@@ -88,10 +89,11 @@ def split_into_paragraphs(text):
     return paragraphs
 
 
+@analyze_prod
 @detect
 def am_chat(usr_prompt, instructions):
     response = st.session_state.chat_engine.chat(usr_prompt)
-    context = get_source_docs(response)
+    context, relevance_scores = get_source_docs(response)
     return context, usr_prompt, instructions, response.response
 
 
@@ -145,7 +147,7 @@ def execute():
     if st.session_state.messages[-1]["role"] != "assistant":
         with st.chat_message("assistant"):
             if cprompt:
-                context, usr_prompt, instructions, response, am_res = am_chat(cprompt, instructions)
+                context, usr_prompt, instructions, response, am_res, am_analyze_res = am_chat(cprompt, instructions)
                 message = {"role": "assistant", "content": response}
                 am_res_json = am_res.to_json()
                 st.write(response)