Metadata-Version: 2.4
Name: cxidk
Version: 1.0.0
Summary: A high-level API for Google's CX Insights.
Author-email: Thiago Alberto <alrrtas@gmail.com>
License: 
                                         Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Operating System :: OS Independent
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: google-auth
Requires-Dist: google-api-python-client
Requires-Dist: google-cloud-contact-center-insights
Requires-Dist: google-cloud-speech
Requires-Dist: google-cloud-dlp
Requires-Dist: google-cloud-storage
Requires-Dist: vertexai
Requires-Dist: jsonschema
Requires-Dist: strenum
Requires-Dist: google-cloud-texttospeech
Requires-Dist: pydub
Requires-Dist: requests
Requires-Dist: google-cloud-dialogflow
Requires-Dist: google-cloud-dialogflow-cx
Requires-Dist: pandas
Requires-Dist: gspread
Requires-Dist: google-cloud-iam
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pylint; extra == "dev"
Requires-Dist: coverage; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Requires-Dist: pandas-stubs; extra == "dev"
Requires-Dist: pytest-mock; extra == "dev"
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Dynamic: license-file

<details open="open">
  <summary>Table of Contents</summary>
  <ol>
    <li>
      <a href="#about-the-conversational-insights-devkit">About the Conversational Insights DevKit</a>
      <ul>
        <li><a href="#key-features">Key Features</a></li>
        <li><a href="#built-with">Built With</a></li>
      </ul>
    </li>
    <li>
      <a href="#getting-started">Getting Started</a>
      <ul>
        <li><a href="#environment-setup">Environment Setup</a></li>
        <li><a href="#authentication">Authentication</a></li>
      </ul>
    </li>
    <li>
      <a href="#library-architecture">Library Architecture</a>
      <ul>
        <li><a href="#core">Core</a></li>
        <li><a href="#wrapper">Wrapper</a></li>
        <li><a href="#workflows">Workflows</a></li>
      </ul>
    </li>
    <li><a href="#usage-examples">Usage Examples</a></li>
    <li><a href="#contributing">Contributing</a></li>
    <li><a href="#license">License</a></li>
  </ol>
</details>

# Conversational Insights DevKit

The Conversational Insights DevKit is a high-level Python library designed to simplify and enhance your interaction with Google's [Conversational Insights API](https://cloud.google.com/python/docs/reference/contactcenterinsights/latest/google.cloud.contact_center_insights_v1.types.AnnotatorSelector). It extends the official Python Client, offering a more user-friendly and Pythonic interface for developers and maintainers looking to leverage conversational AI at scale.

## Key Features
The DevKit empowers you to perform a wide range of actions efficiently, including:
*   Ingest single or bulk conversations with associated metadata.
*   Transcribe mono audio files using Speech-to-Text V1 with diarization.
*   Perform speaker role recognition in transcripts using Gemini.
*   Create and manage Speech-to-Text V2 recognizers.
*   Configure BigQuery exports for conversational insights data.
*   Modify global Conversational Insights settings.
*   Transform transcript data formats from various vendors (e.g., Genesys Cloud, AWS) to Insights-compatible formats.
*   ...and much more, streamlining your conversational AI workflows!

## Built With
*   Python 3.8+

# Getting Started

This section guides you through setting up your development environment and authenticating with Google Cloud Platform.

## Environment Setup
Before you begin, ensure your Google Cloud Platform credentials are configured and install the necessary dependencies.

1.  **GCP CLI Setup (if not already done):**
    ```sh
    gcloud auth login
    gcloud auth application-default login # Authenticates the gcloud CLI to access Google Cloud APIs
    gcloud config set project <YOUR_GCP_PROJECT_ID>
    ```
    Replace `<YOUR_GCP_PROJECT_ID>` with your actual Google Cloud Project ID.

2.  **Install Dependencies:**
    ```sh
    python3 -m venv venv
    source ./venv/bin/activate
    python3 -m pip install -r requirements.txt
    ```

## Authentication
The DevKit supports various authentication methods, adapting to your execution environment.

### Google Colab
For Google Colab notebooks, use the following interactive authentication method:
```python
project_id = '<YOUR_GCP_PROJECT_ID>' # Replace with your GCP Project ID

# This will launch an interactive prompt to authenticate with GCP in your browser.
!gcloud auth application-default login --no-launch-browser

# This sets your active project for subsequent API calls, ensuring proper billing and quota usage.
!gcloud auth application-default set-quota-project $project_id
```

### Cloud Functions / Cloud Run
When deploying on serverless platforms like [Cloud Functions](https://cloud.google.com/functions) or [Cloud Run](https://cloud.google.com/run), the DevKit automatically picks up default environment credentials from the associated service account.

1.  Add this library to your `requirements.txt` file in your Cloud Function or Cloud Run service.
2.  Ensure the service account associated with your Cloud Function/Run service has the appropriate Dialogflow and Conversational Insights IAM roles (e.g., `Contact Center AI Insights Editor`).

### Local Python Environment
For local development, the DevKit can leverage your `gcloud CLI` credentials.

1.  Install the [gcloud CLI](https://cloud.google.com/sdk/docs/install).
2.  Initialize gcloud: `gcloud init`.
3.  Log in to your GCP account: `gcloud auth login`.
4.  Verify your active principal account: `gcloud auth list`.

This process authenticates your GCP principal account with the `gcloud CLI`, allowing the DevKit to automatically pick up these credentials for API calls.

# Library Architecture
The Conversational Insights DevKit is structured into three main components, designed for flexibility and ease of use:

## Core
Located in `src/cxidk/core`, this folder contains the fundamental building blocks of the DevKit, directly mapping to core resource types of the Conversational Insights API.
*   Offers high-level classes and methods for direct API interaction.
*   Serves as the foundation for constructing more complex tools and workflows.
*   Manages foundational functionalities such as authentication and global configurations.

## Wrapper
The `src/cxidk/wrapper` folder provides an additional layer of simplicity on top of the underlying SDK implementations.
*   Streamlines manipulation of global Conversational Insights configurations.
*   Facilitates single and bulk conversation ingestion, including metadata.
*   Manages Google Cloud Storage (GCS) blobs (creation, listing, etc.).
*   Generates transcriptions from audio files using Speech-to-Text V1 and V2.

## Workflows
The `src/cxidk/workflow` folder introduces new classes and methods designed to address common needs not directly supported by existing API offerings.
*   Transforms transcripts from vendors like Genesys Cloud to an Insights-compatible format.
*   Transforms transcripts from vendors like AWS to an Insights-compatible format.
*   Performs speaker role recognition within transcripts using Gemini.
*   QAI Scorecard Optimization: Meta-prompting workflow to evaluate and refine QA scorecard logic using Gemini 3.0 reasoning.
*   Granular Topic Refinement: End-to-end pipeline for refining CCAI Issue Models into deeper L2 categories via BigQuery and Gemini.

# Usage Examples
Now that you understand the library's structure, here are some practical examples demonstrating its core functionalities.

## Ingest Audio with Role Recognition
This example demonstrates a complete workflow: transcribing a mono audio file, performing role recognition using Gemini, combining the results, uploading the transcript to GCS, and then ingesting it into Conversational Insights.

```python
import uuid
from cxidk.workflow import role_recognizer as rr
from cxidk.wrapper import speech, format, storage
from cxidk.core import insights

# Placeholder values for demonstration. Update these with your actual details.
_PROBER_PROJECT_ID = "your-gcp-project-id"
_MONO_SHORT_AUDIO_LOCATION = "path/to/your/audio.wav" # e.g., 'data/sample_mono_audio.wav'
_TMP_PROBER_BUCKET = "your-gcs-bucket-name" # e.g., 'my-insights-temp-bucket'
_PARENT = f"projects/{_PROBER_PROJECT_ID}/locations/global" # Or specific location like 'us-central1'

# Initialize components
sp = speech.V2(project_id=_PROBER_PROJECT_ID)
ft = format.Speech()
role_recognizer = rr.RoleRecognizer()
gcs = storage.Gcs(
  project_name=_PROBER_PROJECT_ID,
  bucket_name=_TMP_PROBER_BUCKET
)

# 1. Create transcription using STT V2
transcript = sp.create_transcription(
  audio_file_path=_MONO_SHORT_AUDIO_LOCATION,
  recognizer_path='projects/<project-number>/locations/global/recognizers/<recognizer-id>' # IMPORTANT: Update with your recognizer path
)

# 2. Convert transcription to a dictionary format
transcript = ft.v2_recognizer_to_dict(transcript)

# 3. Predict roles in the transcript using Gemini
roles = role_recognizer.predict_roles(conversation=transcript)

# 4. Combine transcript with recognized roles
transcript = role_recognizer.combine(transcript, roles)

# 5. Upload the processed transcript to GCS
file_name = f'{uuid.uuid4()}.json'
gcs.upload_blob(
  file_name=file_name,
  data=transcript
)
gcs_path = f"gs://{_TMP_PROBER_BUCKET}/{file_name}"

# 6. Ingest the conversation into Conversational Insights
ingestion = insights.Ingestion(
  parent=_PARENT,
  transcript_path=gcs_path
)
operation = ingestion.single() # Initiates the ingestion and returns an operation object
print(f"Ingestion operation initiated: {operation.name}")
```

## Ingesting a Single Conversation
This example demonstrates how to ingest a pre-processed conversation from a GCS path directly into Conversational Insights.

```python
# Assuming 'gcs_path' is already defined from a previous step or directly provided
# Example: gcs_path = "gs://your-bucket/your-transcript.json"
# _PARENT should be defined as "projects/your-gcp-project-id/locations/global" or specific location

ingestion = insights.Ingestion(
  parent=_PARENT, # e.g., "projects/your-gcp-project-id/locations/global"
  transcript_path=gcs_path
)
operation = ingestion.single()
print(f"Ingestion operation initiated: {operation.name}")
```

## Vendor Transcript Conversion
Convert a transcript from a third-party vendor format (e.g., AWS) into a format compatible with Conversational Insights.

```python
import json
from cxidk.wrapper import format

# Load your AWS transcript data
# For a full example, refer to `tests/integration/data/aws_transcript.json`
with open('tests/integration/data/aws_transcript.json', 'r') as f:
  aws_data = json.load(f)

# Initialize the Insights format utility
ft = format.Insights()

# Convert the AWS transcript
aws_transcript = ft.from_aws(transcript=aws_data)

print("AWS transcript converted successfully.")
# The 'aws_transcript' variable now holds the Insights-compatible data
```

For more end-to-end examples, refer to the integration tests located under `/tests/integration/test_ingestion.py`.

# Contributing
We welcome contributions, bug reports, and feature requests! Please follow these steps to contribute:

1.  **Fork** the Project repository.
2.  **Create** your Feature Branch (`git checkout -b feature/AmazingFeature`).
3.  **Commit** your Changes (`git commit -m 'Add some AmazingFeature'`).
4.  **Push** to the Branch (`git push origin feature/AmazingFeature`).
5.  **Open** a Pull Request.

# License
Distributed under the Apache 2.0 License. See [LICENSE](LICENSE.txt) for more information.
```
