reconify 3.0.0

A package for sending data to the Reconify platform

Reconify PIP module

The Reconify module is used for sending data to the Reconify platform at www.reconify.com.

Currently the module supports processing and analyzing Chats, Completions, and Images from:

• OpenAI
• Amazon Bedrock (Amazon Titan, AI21 Jurassic, Anthropic Claude, Cohere Command, Meta LLama 2, Mistral, and Stability Stable Diffusion)
• Anthropic
• Cohere
• Mistral
• Perplexity

Support for additional actions and providers will be added.

Get started

The first step is to create an account at app.reconify.com.

Generate API and APP Keys

In the Reconify console, add an Application to your account. This will generate both an API_KEY and an APP_KEY which will be used in the code below to send data to Reconify.

Install the module

pip install reconify

Integrate the module with OpenAI

The following instructions are for OpenAI's Python SDK v1 or later (released in Nov 2023). For earlier versions of OpenAI's SDK, follow the legacy instructions

Import the module

from reconify import reconifyOpenAIHandler

Initialize the module

Prior to initializing the Reconify module, make sure to import the OpenaAI module.

from openai import OpenAI
openai_client = OpenAI(api_key = 'YOUR_OPENAI_KEY')

Configure the instance of Reconify passing the OpenAi instance along with the Reconify API_KEY and APP_KEY created above.

reconifyOpenAIHandler.config(openai_client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

This is all that is needed for a basic integration. The module takes care of sending the correct data to Reconify when you call openai_client.completions.create, openai_client.chat.completions.create, openai_client.images.generate.

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyOpenAIHandler.config(openai_client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyOpenAIHandler.setUser ({
   "userId": "ABC123",
   "isAuthenticated": 1,
   "firstName": "Francis",
   "lastName": "Smith",
   "email": "",
   "phone": "",
   "gender": "female"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyOpenAIHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyOpenAIHandler.setSessionTimeout(15)

See Examples with OpenAI

Integrate the module with Amazon Bedrock Runtime

Import the module

from reconify import reconifyBedrockRuntimeHandler

Initialize the module

Prior to initializing the Reconify module, make sure to import the Amazon boto3 module.

import boto3
bedrock = boto3.client('bedrock-runtime')

Configure the instance of Reconify passing the Bedrock Runtime instance along with the Reconify API_KEY and APP_KEY created above.

reconifyBedrockRuntimeHandler.config(bedrock, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

This is all that is needed for a basic integration. The module takes care of sending the correct data to Reconify when you call bedrock.invoke_model().

Response handling

When using the Reconify module, the response body from invoke_model will be converted from botocore.response.StreamingBody to JSON and saved in the response as parsedBody. See the examples below for more info.

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyBedrockRuntimeHandler.config(bedrock, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyBedrockRuntimeHandler.setUser ({
   "userId": "ABC123",
   "firstName": "Francis",
   "lastName": "Smith"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyBedrockRuntimeHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyBedrockRuntimeHandler.setSessionTimeout(15)

See Examples with Amazon Bedrock Runtime

Integrate the module with Anthropic

The following instructions are for Anthropic's Python SDK.

Import the module

from reconify import reconifyAnthropicHandler

Initialize the module

Prior to initializing the Reconify module, make sure to import the Anthropic module.

from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
anthropic = Anthropic(api_key = 'YOUR_ANTHROPIC_KEY')

Configure the instance of Reconify passing the Anthropic instance along with the Reconify API_KEY and APP_KEY created above.

reconifyAnthropicHandler.config(anthropic, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

This is all that is needed for a basic integration. The module takes care of sending the correct data to Reconify.

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyAnthropicHandler.config(anthropic, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyAnthropicHandler.setUser ({
   "userId": "ABC123",
   "firstName": "Francis",
   "lastName": "Smith"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyAnthropicHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyAnthropicHandler.setSessionTimeout(15)

See Examples with Anthropic

Integrate the module with Cohere

The following instructions are for Cohere's Python SDK.

Import the module

from reconify import reconifyCohereHandler

Initialize the module

Prior to initializing the Reconify module, make sure to import the Cohere module.

from cohere import Client
cohere_client = Client('YOUR_COHERE_KEY')

Configure the instance of Reconify passing the Cohere instance along with the Reconify API_KEY and APP_KEY created above.

reconifyCohereHandler.config(cohere_client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

This is all that is needed for a basic integration. The module takes care of sending the correct data to Reconify.

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyCohereHandler.config(cohere_client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyCohereHandler.setUser ({
   "userId": "ABC123",
   "firstName": "Francis",
   "lastName": "Smith"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyCohereHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyCohereHandler.setSessionTimeout(15)

See Examples with Cohere

Integrate the module with Mistral

The following instructions are for Mistral's Python SDK.

Import the module

from reconify import reconifyMistralHandler

Initialize the module

Prior to initializing the Reconify module, make sure to import the Mistral module.

from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage
client = MistralClient(api_key = 'YOUR_MISTRAL_KEY')

Configure the instance of Reconify passing the Mistral instance along with the Reconify API_KEY and APP_KEY created above.

reconifyMistralHandler.config(client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

This is all that is needed for a basic integration. The module takes care of sending the correct data to Reconify.

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyMistralHandler.config(client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyMistralHandler.setUser ({
   "userId": "ABC123",
   "firstName": "Francis",
   "lastName": "Smith"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyMistralHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyMistralHandler.setSessionTimeout(15)

See Examples with Mistral

Integrate the module with Perplexity

The following instructions are for Perplexity.

Import the module

from reconify import reconifyUniversalHandler

Initialize the module

Configure the instance of Reconify passing the Reconify API_KEY and APP_KEY created above.

reconifyUniversalHandler.config( 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key'
)

After making a call to the Perplexity, send the input parameters and response data to Reconify, along with the start and end time stamps.

input = {
    "model":"pplx-7b-chat",
    "messages":[
        {"role": "system", "content": "You are a comic"},
        {"role": "user", "content": "Tell a cat joke"},
    ]
}

start = reconifyUniversalHandler.getTimestamp()
response = requests.post("https://api.perplexity.ai/chat/completions", json=input, headers = {
    "accept":"application/json",
    "content-type":"application/json",
    "authorization": "Bearer YOUR_PERPLEXITY_KEY"
})
end = reconifyUniversalHandler.getTimestamp()

reconifyUniversalHandler.logChat(input, response.text, start, end)

Optional Config Parameters

There are additional optional parameters that can be passed in to the handler.

• debug: (default False) Enable/Disable console logging
• trackImages: (default True) Turn on/off tracking of createImage

For example:

reconifyUniversalHandler.config(client, 
   appKey = 'Your_App_Key', 
   apiKey = 'Your_Api_Key',
   debug = True
)

Optional methods

You can optionally pass in a user object or session ID to be used in the analytics reporting. The session ID will be used to group interactions together in the same session transcript.

Set a user

The user JSON should include a unique userId, all the other fields are optional. Without a unique userId, each user will be treated as a new user.

reconifyUniversalHandler.setUser ({
   "userId": "ABC123",
   "firstName": "Francis",
   "lastName": "Smith"
})

Set a Session ID

The Session ID is an alphanumeric string.

reconifyUniversalHandler.setSession('MySessionId')

Set Session Timeout

Set the session timeout in minutes to override the default

reconifyUniversalHandler.setSessionTimeout(15)

See Examples with Perplexity

Examples with OpenAI

Chat Example

from openai import OpenAI
from reconify import reconifyOpenAIHandler

openai_client = OpenAI(api_key = 'YOUR_OPENAI_KEY')

reconifyOpenAIHandler.config(openai_client, 'Your_App_Key', 'Your_Api_Key')

reconifyOpenAIHandler.setUser({
   "userId": "12345",
   "isAuthenticated": 1,
   "firstName": "Jim",
   "lastName": "Stand",
   "gender": "male"
})

response = openai_client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are an expert on commedians."},
        {"role": "user", "content": "Tell a joke about cats"},
    ],
    temperature=0,
)

Completion Example

from openai import OpenAI
from reconify import reconifyOpenAIHandler

openai_client = OpenAI(api_key = 'YOUR_OPENAI_KEY')

reconifyOpenAIHandler.config(openai_client, 'Your_App_Key', 'Your_Api_Key')

reconifyOpenAIHandler.setUser({
   "userId": "12345",
   "isAuthenticated": 1,
   "firstName": "Jim",
   "lastName": "Stand",
   "gender": "male"
})

response = openai_client.completions.create(
   model = "text-davinci-003",
   prompt = "write a haiku about cats",
   max_tokens = 100,
   temperature = 0,
)

Image Example

from openai import OpenAI
from reconify import reconifyOpenAIHandler

openai_client = OpenAI(api_key = 'YOUR_OPENAI_KEY')

reconifyOpenAIHandler.config(openai_client, 'Your_App_Key', 'Your_Api_Key')

reconifyOpenAIHandler.setUser({
   "userId": "12345",
   "isAuthenticated": 1,
   "firstName": "Jim",
   "lastName": "Stand",
   "gender": "male"
})

response = openai_client.images.generate(
   model = "dall-e-3",
   prompt = "a cat on the moon",
   n = 1,
   size = "1024x1024",
   quality="standard",
   response_format = "url"
)

Examples with Amazon Bedrock Runtime

Anthropic Claude example

import boto3
from reconify import reconifyBedrockRuntimeHandler

bedrock = boto3.client('bedrock-runtime')

reconifyBedrockRuntimeHandler.config(bedrock, 'Your_App_Key', 'Your_Api_Key')

reconifyOpenAIHandler.setUser({
   "userId": "12345",
   "firstName": "Jane",
   "lastName": "Smith"
})

response = bedrock.invoke_model(
    modelId = "anthropic.claude-instant-v1",
    contentType = "application/json",
    accept = "application/json",
    body = "{\"prompt\":\"\\n\\nHuman: Tell a cat joke.\\n\\nAssistant:\",\"max_tokens_to_sample\":300,\"temperature\":1,\"top_k\":250,\"top_p\":0.999,\"stop_sequences\":[\"\\n\\nHuman:\"],\"anthropic_version\":\"bedrock-2023-05-31\"}"
)

#The botocore.response.StreamingBody object will be converted to JSON and saved in parsedBody
print(response.get("parsedBody"))

Stable Diffusion image example

import boto3
from reconify import reconifyBedrockRuntimeHandler

bedrock = boto3.client('bedrock-runtime')

reconifyBedrockRuntimeHandler.config(bedrock, 'Your_App_Key', 'Your_Api_Key')

reconifyOpenAIHandler.setUser({
   "userId": "12345",
   "firstName": "Jane",
   "lastName": "Smith"
})

response = bedrock.invoke_model(
    modelId = "stability.stable-diffusion-xl-v0",
    contentType = "application/json",
    accept = "application/json",
    body = "{\"text_prompts\":[{\"text\":\"a cat drinking boba tea\"}],\"cfg_scale\":10,\"seed\":0,\"steps\":50}"
)
#The botocore.response.StreamingBody object will be converted to JSON and saved in parsedBody
#The following will print out the image result in JSON base64
print(response.get("parsedBody"))

Examples with Anthropic

Chat Example

from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
from reconify import reconifyAnthropicHandler

anthropic = Anthropic(api_key = 'YOUR_ANTHROPIC_KEY')

reconifyAnthropicHandler.config(anthropic, 'Your_App_Key', 'Your_Api_Key')

reconifyAnthropicHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith",
})

response = anthropic.messages.create(
    model="claude-2.1",
    max_tokens=300,
    messages = [
      {"role": "user", "content" : "Tell me a cat joke"}
    ]
)

Completions Example

from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
from reconify import reconifyAnthropicHandler

anthropic = Anthropic(api_key = 'YOUR_ANTHROPIC_KEY')

reconifyAnthropicHandler.config(anthropic, 'Your_App_Key', 'Your_Api_Key')

reconifyAnthropicHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith",
})

response = anthropic.completions.create(
    model="claude-2",
    max_tokens_to_sample=300,
    prompt=f"{HUMAN_PROMPT} Tell me a good cat joke{AI_PROMPT}",
)

Examples with Cohere

Chat Example

from cohere import Client
from reconify import reconifyCohereHandler

cohere_client = Client('YOUR_COHERE_KEY')

reconifyCohereHandler.config(cohere_client, 'Your_App_Key', 'Your_Api_Key')

reconifyCohereHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith"
})

response = cohere_client.chat(
    model="command",
    message="tell me a good cat joke"
)

Generate Example

from cohere import Client
from reconify import reconifyCohereHandler

cohere_client = Client('YOUR_COHERE_KEY')

reconifyCohereHandler.config(cohere_client, 'Your_App_Key', 'Your_Api_Key')

reconifyCohereHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith"
})

response = cohere_client.generate(
    model="command",
    prompt="write a cat haiku",
    max_tokens=300
)

Examples with Mistral

Chat Example

from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage
from reconify import reconifyMistralHandler

client = MistralClient(api_key = 'YOUR_MISTRAL_KEY')

reconifyMistralHandler.config(client, 'Your_App_Key', 'Your_Api_Key')

reconifyMistralHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith"
})

response = client.chat(
    model="mistral-tiny",
    messages=[
      ChatMessage(role="user", content="Tell me a cat joke")
    ]
)

Examples with Perplexity

Chat Example

import requests
from reconify import reconifyUniversalHandler

reconifyUniversalHandler.config('Your_App_Key', 'Your_Api_Key')

reconifyUniversalHandler.setUser({
   "userId": "12345",
   "firstName": "Jim",
   "lastName": "Smith"
})

input = {
    "model":"pplx-7b-chat",
    "messages":[
        {"role": "system", "content": "You are a comic"},
        {"role": "user", "content": "Tell a cat joke"},
    ]
}

start = reconifyUniversalHandler.getTimestamp()

response = requests.post("https://api.perplexity.ai/chat/completions", json=input, headers = {
    "accept":"application/json",
    "content-type":"application/json",
    "authorization": "Bearer YOUR_PERPLEXITY_KEY"
})

end = reconifyUniversalHandler.getTimestamp()

reconifyUniversalHandler.logChat(input, response.text, start, end)