Fixed issue in detect decorator. Improved code organization. (#21)

* 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 <preetam@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

---------

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

aimon/decorators/detect.py

@@ -38,6 +38,7 @@ def wrapper(*args, **kwargs):
                 aimon_payload['user_query'] = result_dict['user_query']
             if 'instructions' in result_dict:
                 aimon_payload['instructions'] = result_dict['instructions']
+            aimon_payload['config'] = self.config
 
             data_to_send = [aimon_payload]
 

examples/chatbot/README.md

@@ -7,6 +7,8 @@ related to the webpage, in which case it is likely to answer out of its own lear
 
 ## Setup
 
+Make sure you have the AIMon API key which can be obtained by signing up on the AIMon website.
+
 ### Installation
 
 Install the required packages from the `requirements.txt` file specified in this directory.

examples/chatbot/requirements.txt

@@ -2,5 +2,5 @@ llama-index
 llama-index-readers-web
 streamlit
 openai
-aimon
+aimon>=0.5.0
 

examples/metaflow/README.md

@@ -6,6 +6,8 @@ The summarizer is built using Langchain.
 
 ## Setup
 
+Make sure you have the AIMon API key which can be obtained by signing up on the AIMon website.
+
 ### Installation
 
 Install the required packages from the `requirements.txt` file specified in this directory.
@@ -19,8 +21,8 @@ pip install -r requirements.txt
 You will need to specify AIMon and OpenAI API keys as part of their respective environment variables. 
 
 ```bash
-export OPENAI_KEY=YOUR_OPENAI_API
-export AIMON_API_KEY=YOUR_AIMON_API
+export OPENAI_KEY=YOUR_OPENAI_API_KEY
+export AIMON_API_KEY=YOUR_AIMON_API_KEY
 ```
 
 ### Running the flow

examples/metaflow/requirements.txt

@@ -1,6 +1,6 @@
 langchain
 langchain-community
 metaflow
-aimon
+aimon>=0.5.0
 openai
 

examples/summarization/README.md

@@ -0,0 +1,33 @@
+# Summarization
+
+This is a simple streamlit based Langchain Summarization application with an inline AIMon detector.
+
+## Setup
+
+Make sure you have the AIMon API key which can be obtained by signing up on the AIMon website.
+
+### Installation
+
+Install the required packages from the `requirements.txt` file specified in this directory.
+
+```bash
+pip install -r requirements.txt
+```
+
+### API Keys
+
+You will need to specify AIMon and OpenAI API keys in a `secrets.toml` file inside the 
+`.streamlit` directory. 
+
+```toml
+openai_key=YOUR_OPENAI_API_KEY
+aimon_api_key=YOUR_AIMON_API_KEY
+```
+
+### Running the Summarization App
+
+The summarization app is a streamlit app. You can run it using this command:
+
+```bash
+streamlit run langchain_summarization_app.py
+```

examples/summarization/langchain_summarization_app.py

@@ -0,0 +1,70 @@
+import streamlit as st
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.docstore.document import Document
+from langchain.llms.openai import OpenAI
+from langchain.chains.summarize import load_summarize_chain
+
+from aimon import Detect
+
+# Streamlit app
+st.title('LangChain Text Summarizer')
+
+# Get OpenAI API key and source text input
+openai_api_key = st.secrets.openai_key
+aimon_api_key = st.secrets.aimon_api_key
+source_text = st.text_area("Source Text", height=200)
+
+config = {"hallucination": {"detector_name": "default"},
+          "conciseness": {"detector_name": "default"},
+          "completeness": {"detector_name": "default"},
+          "toxicity": {"detector_name": "default"}
+          }
+detect = Detect(['context', 'generated_text'], api_key=aimon_api_key, config=config)
+
+
+@detect
+def summarize():
+    # Split the source text
+    text_splitter = CharacterTextSplitter()
+    texts = text_splitter.split_text(source_text)
+    # Create Document objects for the texts
+    docs = [Document(page_content=t) for t in texts[:3]]
+    # Initialize the OpenAI module, load and run the summarize chain
+    llm = OpenAI(temperature=0, openai_api_key=openai_api_key)
+    chain = load_summarize_chain(llm, chain_type="map_reduce")
+    doc_summary = chain.run(docs)
+    return source_text, doc_summary
+
+
+# Check if the 'Summarize' button is clicked
+if st.button("Summarize"):
+    # Validate inputs
+    if not openai_api_key.strip() or not aimon_api_key.strip():
+        st.write("Please provide the OpenAI and AIMon API keys in the .streamlit/secrets.toml file.")
+    if not source_text.strip():
+        st.write(f"Please complete the missing fields.")
+    else:
+        try:
+            context, summary, aimon_res = summarize()
+            # Display summary
+            st.header('Summary')
+            st.write(summary)
+
+            # You could perform any action based on the AIMon response (aimon_res) here
+            # ....
+
+            # Display the Aimon Rely response
+            st.header('Aimon Rely - Hallucination Detector Response')
+            st.json(aimon_res.hallucination)
+
+            st.header('Aimon Rely - Conciseness Detector Response')
+            st.json(aimon_res.conciseness)
+
+            st.header('Aimon Rely - Completeness Detector Response')
+            st.json(aimon_res.completeness)
+
+            st.header('Aimon Rely - Toxicity Detector Response')
+            st.json(aimon_res.toxicity)
+
+        except Exception as e:
+            st.write(f"An error occurred: {e}")

examples/requirements.txt → examples/summarization/requirements.txt

@@ -1,9 +1,6 @@
 openai
 langchain
 langchain-community
-tiktoken
-requests
-pytest
 streamlit
-pandas
-boto3
+tiktoken
+aimon>=0.5.0