readme

.devcontainer/devcontainer.json

+{
+    "name": "Nixtla Development Environment",
+    "image": "mcr.microsoft.com/vscode/devcontainers/python:3.11-bookworm",
+    "hostRequirements": {
+        "cpus": 4,
+        "memory": "16gb",
+        "storage": "32gb"
+    },
+    "customizations": {
+        "vscode": {
+            "settings": {
+                "terminal.integrated.shell.linux": "/bin/bash",
+                "python.terminal.activateEnvInCurrentTerminal": true,
+                "python.defaultInterpreterPath": ".venv/bin/python",
+                "python.pythonPath": ".venv/bin/python",
+                "[python]": {
+                    "editor.defaultFormatter": "charliermarsh.ruff",
+                    "editor.formatOnSave": true,
+                    "editor.codeActionsOnSave": {
+                        "source.fixAll": "explicit",
+                        "source.organizeImports": "explicit"
+                    }
+                },
+                "notebook.python.defaultInterpreterPath": ".venv/bin/python",
+                "notebook.codeActionsOnSave": {
+                    "source.fixAll": "explicit",
+                    "source.organizeImports": "explicit"
+                },
+                "ruff.nativeServer": "on",
+                "python.languageServer": "Default",
+                "debug.internalConsoleOptions": "neverOpen",
+                "extensions.ignoreRecommendations": true,
+                "files.insertFinalNewline": true
+            },
+            "extensions": [
+                "ms-python.python",
+                "ms-python.mypy",
+                "ms-python.vscode-pylance",
+                "ms-toolsai.jupyter@2025.2.0",
+                "charliermarsh.ruff@2025.22.0",
+                "GitHub.copilot",
+                "tamasfe.even-better-toml",
+                "anthropic.claude-code@1.0.127"
+            ]
+        }
+    },
+    "forwardPorts": [
+        8888
+    ],
+    "containerEnv": {
+        "UV_NO_SYNC": "1"
+    },
+    "onCreateCommand": "make devenv",
+    "postCreateCommand": "make init_codespace",
+    "waitFor": "postCreateCommand",
+    "features": {
+        "ghcr.io/devcontainers/features/docker-in-docker:2.12.3": {},
+        "ghcr.io/va-h/devcontainers-features/uv:1.1.4": {},
+        "ghcr.io/devcontainers/features/node:1.6.3": {}
+    }
+}

.github/ISSUE_TEMPLATE/bug-report.yml

+name: Bug report
+title: "[<Library component: Model|Core|etc...>] "
+description: Problems and issues with code of the library
+labels: [bug]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for reporting the problem..
+        Please make sure what you are reporting is a bug with reproducible steps. To ask questions
+        or share ideas, please post on our [Slack community](https://join.slack.com/t/nixtlacommunity/shared_invite/zt-1h77esh5y-iL1m8N0F7qV1HmH~0KYeAQ) instead.
+
+  - type: textarea
+    attributes:
+      label: What happened + What you expected to happen
+      description: Describe 1. the bug 2. expected behavior 3. useful information (e.g., logs)
+      placeholder: >
+        Please provide the context in which the problem occurred and explain what happened. Further,
+        please also explain why you think the behaviour is erroneous. It is extremely helpful if you can
+        copy and paste the fragment of logs showing the exact error messages or wrong behaviour here.
+
+        **NOTE**: please copy and paste texts instead of taking screenshots of them for easy future search.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Versions / Dependencies
+      description: Please specify the versions of the library, Python, OS, and other libraries that are used.
+      value: |
+        <details><summary>Click to expand</summary>
+        Dependencies:
+
+        </details>
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Reproducible example
+      description: >
+        Please provide a reproducible script. Providing a simple way to reproduce the issue
+        (minimal / no external dependencies) will help us triage and address issues in the timely manner!
+      value: |
+        ```python
+        # paste your code here
+        ```
+    validations:
+      required: true
+
+  - type: dropdown
+    attributes:
+      label: Issue Severity
+      description: |
+        How does this issue affect your experience as user?
+      multiple: false
+      options:
+        - "Low: It annoys or frustrates me."
+        - "Medium: It is a significant difficulty but I can work around it."
+        - "High: It blocks me from completing my task."
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

+blank_issues_enabled: true
+contact_links:
+  - name: Ask a question or get support
+    url: https://join.slack.com/t/nixtlacommunity/shared_invite/zt-1h77esh5y-iL1m8N0F7qV1HmH~0KYeAQ
+    about: Ask a question or request support for using a library of the nixtlaverse

.github/ISSUE_TEMPLATE/documentation-issue.yml

+name: Documentation
+title: "[<Library component: Models|Core|etc...>] "
+description: Report an issue with the library documentation
+labels: [documentation]
+body:
+  - type: markdown
+    attributes:
+      value: Thank you for helping us improve the library documentation!
+
+  - type: textarea
+    attributes:
+      label: Description
+      description: |
+        Tell us about the change you'd like to see. For example, "I'd like to
+        see more examples of how to use `cross_validation`."
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Link
+      description: |
+        If the problem is related to an existing section, please add a link to
+        the section. 
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature-request.yml

+name: Library feature request
+description: Suggest an idea for a project
+title: "[<Library component: Models|Core|etc...>] "
+labels: [enhancement, feature]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for finding the time to propose a new feature!
+        We really appreciate the community efforts to improve the nixtlaverse.
+
+  - type: textarea
+    attributes:
+      label: Description
+      description: A short description of your feature
+
+  - type: textarea
+    attributes:
+      label: Use case
+      description: >
+        Describe the use case of your feature request. It will help us understand and
+        prioritize the feature request.
+      placeholder: >
+        Rather than telling us how you might implement this feature, try to take a
+        step back and describe what you are trying to achieve.

.github/dependabot.yml

+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    groups:
+      ci-dependencies:
+        patterns: ["*"]

.github/release-drafter.yml

+name-template: 'v$NEXT_PATCH_VERSION'
+tag-template: 'v$NEXT_PATCH_VERSION'
+categories:
+  - title: 'New Features'
+    label: 'feature'
+  - title: 'Breaking Change'
+    label: 'breaking change'
+  - title: 'Bug Fixes'
+    label: 'fix'
+  - title: 'Documentation'
+    label: 'documentation'
+  - title: 'Dependencies'
+    label: 'dependencies'
+  - title: 'Enhancement'
+    label: 'enhancement'
+change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
+template: |
+  $CHANGES

.github/workflows/build-docs.yaml

+name: build-docs
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      environment:
+        description: 'The environment to deploy to'
+        required: true
+        type: choice
+        default: 'staging'
+        options:
+          - staging
+          - production
+
+jobs:
+  build-docs:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          submodules: "true"
+
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install -e '.[dev]' lazydocs pyyaml
+
+      # setup quarto for rendering example/tutorial nbs
+      - uses: quarto-dev/quarto-actions/setup@v2
+        with:
+          version: 1.4.515
+
+      - name: Build Docs
+        run: make all_docs
+
+      - name: Deploy (Push to main or Pull Request)
+        if: (github.event_name == 'push' && github.ref == 'refs/heads/main') || github.event_name == 'pull_request' || (github.event_name == 'workflow_dispatch' && github.event.inputs.environment == 'staging')
+        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_branch: docs-preview
+          publish_dir: docs/mintlify
+          user_name: github-actions[bot]
+          user_email: 41898282+github-actions[bot]@users.noreply.github.com
+
+      - name: Deploy (Release)
+        if: github.event_name == 'release' || (github.event_name == 'workflow_dispatch' && github.event.inputs.environment == 'production')
+        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_branch: docs
+          publish_dir: docs/mintlify
+          user_name: github-actions[bot]
+          user_email: 41898282+github-actions[bot]@users.noreply.github.com
+
+
+      - name: Trigger mintlify workflow (Push to main or Pull Request)
+        if: (github.event_name == 'push' && github.ref == 'refs/heads/main') || github.event_name == 'pull_request' || (github.event_name == 'workflow_dispatch' && github.event.inputs.environment == 'staging')
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          github-token: ${{ secrets.DOCS_WORKFLOW_TOKEN }}
+          script: |
+            await github.rest.actions.createWorkflowDispatch({
+              owner: 'nixtla',
+              repo: 'docs',
+              workflow_id: 'mintlify-action-preview.yml',
+              ref: 'main',
+            });
+
+      - name: Trigger mintlify workflow (Release)
+        if: github.event_name == 'release' || (github.event_name == 'workflow_dispatch' && github.event.inputs.environment == 'production')
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          github-token: ${{ secrets.DOCS_WORKFLOW_TOKEN }}
+          script: |
+            await github.rest.actions.createWorkflowDispatch({
+              owner: 'nixtla',
+              repo: 'docs',
+              workflow_id: 'mintlify-action.yml',
+              ref: 'main',
+            });

.github/workflows/ci.yaml

+name: CI
+
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+      - 'timegpt-docs/**'
+  pull_request:
+    branches: [main]
+    paths-ignore:
+      - 'timegpt-docs/**'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  NIXTLA_API_KEY: ${{ secrets.NIXTLA_DEV_API_KEY }}
+  NIXTLA_BASE_URL: ${{ secrets.NIXTLA_DEV_BASE_URL }}
+  NIXTLA_API_KEY_CUSTOM: ${{ secrets.NIXTLA_API_KEY_CUSTOM }}
+  NIXTLA_BASE_URL_CUSTOM: ${{ secrets.NIXTLA_BASE_URL_CUSTOM }}
+  API_KEY_FRED: ${{ secrets.API_KEY_FRED }}
+
+jobs:
+  check-import:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+    steps:
+      - name: Clone repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install nixtla
+        run: pip install uv && uv pip install --system .
+
+      - name: Check import
+        run: python -c "from nixtla import NixtlaClient"
+
+  run-notebooks-test:
+    runs-on: nixtla-linux-large-public
+    timeout-minutes: 60
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11"]
+    steps:
+      - name: Clone repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install pip requirements
+        run: pip install uv && uv pip install --system ".[dev,distributed]"
+
+      - name: Run nbconvert
+        run: |
+          find nbs/docs/ -name "*.ipynb" -print0 | while IFS= read -r -d '' nb; do
+            if [[ "$(basename "$nb")" == "19_computing_at_scale_ray_distributed.ipynb" ]]; then
+              echo "Skipping $nb..."
+              continue
+            fi
+            echo "Running $nb..."
+            jupyter nbconvert --to notebook --execute --inplace "$nb"
+          done

.github/workflows/lint.yaml

+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: pip install black pre-commit
+
+      - name: Run pre-commit
+        run: pre-commit run --show-diff-on-failure --files nixtla/*

.github/workflows/models-performance.yaml

+name: Models Performance
+
+permissions: write-all
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths-ignore:
+      - 'timegpt-docs/**'
+defaults:
+  run:
+    shell: bash -l {0}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  run-models-performance:
+    runs-on: ubuntu-latest
+    env:
+      NIXTLA_API_KEY: ${{ secrets.NIXTLA_DEV_API_KEY }}
+      NIXTLA_BASE_URL: ${{ secrets.NIXTLA_DEV_BASE_URL }}
+      PLOTS_REPO_URL: https://github.com/Nixtla/nixtla/blob/docs-figs-model-performance
+    steps:
+      - name: Clone repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: "3.10"
+
+      - name: Install pip requirements
+        run: pip install uv && uv pip install --system '.[dev]'
+
+      - name: Run evaluation
+        run: python -m action_files.models_performance.main
+
+      - name: Upload results to the PR
+        if: github.event_name == 'pull_request'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: >
+          python action_files/comment_file.py
+          --search_term "Experiment Results"
+          --file "action_files/models_performance/summary.md"
+
+      - name: Upload images to new branch main
+        run: |
+          git config --global user.email azul@nixtla.io
+          git config --global user.name AzulGarza
+          git push https://$GITHUB_TOKEN@github.com/nixtla/nixtla.git --delete docs-figs-model-performance || true
+          git checkout -b docs-figs-model-performance
+          git add -f "*.png"
+          git commit -m "[cd] update png images" || echo "No changes to commit"
+          git push https://$GITHUB_TOKEN@github.com/nixtla/nixtla.git HEAD:docs-figs-model-performance

.github/workflows/no-response.yaml

+name: No Response Bot
+
+on:
+  issue_comment:
+    types: [created]
+  schedule:
+    - cron: '0 4 * * *'
+
+jobs:
+  noResponse:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: lee-dohm/no-response@9bb0a4b5e6a45046f00353d5de7d90fb8bd773bb # v0.5.0
+        with:
+          closeComment: >
+            This issue has been automatically closed because it has been awaiting a response for too long.
+            When you have time to to work with the maintainers to resolve this issue, please post a new comment and it will be re-opened.
+            If the issue has been locked for editing by the time you return to it, please open a new issue and reference this one.
+          daysUntilClose: 30
+          responseRequiredLabel: awaiting response
+          token: ${{ github.token }}

.github/workflows/pytest.yml

+name: pytest
+
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+      - 'timegpt-docs/**'
+  pull_request:
+    branches: [main]
+    paths-ignore:
+      - 'timegpt-docs/**'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  NIXTLA_API_KEY: ${{ secrets.NIXTLA_DEV_API_KEY }}
+  NIXTLA_BASE_URL: ${{ secrets.NIXTLA_DEV_BASE_URL }}
+  NIXTLA_API_KEY_CUSTOM: ${{ secrets.NIXTLA_API_KEY_CUSTOM }}
+  NIXTLA_BASE_URL_CUSTOM: ${{ secrets.NIXTLA_BASE_URL_CUSTOM }}
+  API_KEY_FRED: ${{ secrets.API_KEY_FRED }}
+
+
+jobs:
+  run-tests:
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 60
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-14, nixtla-linux-large-public, windows-latest]
+        python-version: ["3.9", "3.10", "3.11"]
+        # windows python 3.13 can't install pyreadr
+        # TODO: in 3.12, it doesn't support ray<=2.20
+    steps:
+      - name: Clone repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Setup uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+          cache-dependency-glob: "pyproject.toml"
+          python-version: ${{ matrix.python-version }}
+
+      - name: Setup devenv
+        run: >
+          make devenv
+
+      - name: Run tests (Linux Python 3.11)
+        if: runner.os == 'Linux' && matrix.python-version == '3.11'
+        run: uv run pytest --cov=nixtla --reruns 3 --reruns-delay 10 --only-rerun ConnectError --only-rerun "Too Many Requests" nixtla_tests
+
+      - name: Run tests (not Linux Python 3.11)
+        if: runner.os != 'Linux' || matrix.python-version != '3.11'
+        run: uv run pytest --cov=nixtla -m "not distributed_run" --reruns 3 --reruns-delay 10 --only-rerun ConnectError --only-rerun "Too Many Requests" nixtla_tests

.github/workflows/python-publish.yml

+name: Upload Python Packages
+
+on:
+  push:
+    tags: ['v*']
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up Python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: python -m pip install --upgrade pip && pip install build
+
+      - name: Build nixtla package
+        run: python -m build
+
+      - name: Publish nixtla package
+        uses: pypa/gh-action-pypi-publish@76f52bc884231f62b9a034ebfe128415bbaabdfc # v1.12.4
+

.github/workflows/release-drafter.yml

+name: Release Drafter
+
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  update_release_draft:
+    permissions:
+      contents: write
+      pull-requests: read
+    runs-on: ubuntu-latest
+    steps:
+      - uses: release-drafter/release-drafter@b1476f6e6eb133afa41ed8589daba6dc69b4d3f5 # v6.1.0
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-publish.yml

+name: Upload Python Packages to TestPyPI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up Python
+        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # 5.4.0
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: python -m pip install --upgrade pip && pip install build
+
+      - name: Build nixtla package
+        run: python -m build
+
+      - name: Publish nixtla package
+        uses: pypa/gh-action-pypi-publish@76f52bc884231f62b9a034ebfe128415bbaabdfc # v1.12.4
+        with:
+          repository-url: https://test.pypi.org/legacy/
+

.gitignore

+.ipynb_checkpoints
+__pycache__
+*.egg-info
+Gemfile*
+Gemfile.lock
+docs/_site
+build
+dist
+.vscode
+.idea
+*.gif
+*.csv
+*/data/*
+*.parquet
+*.tar.gz
+tmp
+_docs/
+_proc/
+.DS_Store
+.gitattributes
+.gitconfig
+nbs/.last_checked
+.venv
+.idea
+.env
+*/summary.md
+*/*.png
+longhorizon
+data
+*.rda
+nbs/_extensions
+!nbs/assets/*
+
+# VSCode
+*.code-workspace
+
+# ignore files created in the docs folder
+docs/*.md
+docs/**/*.mdx
+
+docs-scripts
+docs/mintlify/examples
+docs/mintlify/assets
+
+nbs/_extensions
+.quarto
+
+*.png
+
+.coverage*
\ No newline at end of file

.pre-commit-config.yaml

+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - id: ruff
+        files: 'nixtla'
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.1
+    hooks:
+      - id: mypy
+        args: [--ignore-missing-imports]
+        files: 'nixtla'

CHANGELOG.md

+# Changelog
+
+## 0.6.6
+
+### 🚀 Feature Enhancements
+
+#### Online anomaly detection
+
+We introduce the `online_anomaly_detection` method, which allows you to define a `detection_size` on which to look for anomalies.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.6.6).*
+
+## 0.6.5
+
+### 🚀 Feature Enhancements
+
+#### Persisting fine-tuned models
+
+You can now run an isolated fine-tuning process, save the model and use it afterwards in all of our methods, i.e. `forecast`, `cross_validation` and `detect_anomalies`.
+
+#### zstd compression
+
+All requests above 1MB are now automatically compressed using [zstd](https://github.com/facebook/zstd), which will help when sending large amounts of data, as well as users with slow connections.
+
+#### refit argument in cross_validation
+
+It's now possible to fine-tune the model only on the first window when performing `cross_validation` by setting `refit=False`. This will dramatically decrease the time it takes to run cross validation with fine-tuning.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.6.5).*
+
+## 0.6.4
+
+### 🚀 Feature Enhancements
+
+#### Integer and custom pandas frequencies
+
+It's now possible to provide integer timestamps and an integer frequency as well as non-standard timestamps and custom pandas frequencies like [CustomBusinessHour](https://pandas.pydata.org/docs/reference/api/pandas.tseries.offsets.CustomBusinessHour.html)
+
+#### Usage method
+
+You can now programatically get the number of calls you've made to our API as well as your limits by calling the `usage` method.
+
+#### Historic exogenous in cross validation
+
+The `cross_validation` method now supports the `hist_exog_list` parameter, which allows you to define historical exogenous features.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.6.4).*
+
+## 0.6.2
+
+### 🚀 Feature Enhancements
+
+#### Finetune depth
+
+You can now specify the depth of the fine-tuning process by setting `finetune_depth` in the `forecast` and `cross_validation` methods.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.6.2).*
+
+## 0.6.0
+
+### 🚀 Feature Enhancements
+
+#### V2 API endpoints
+
+The client now makes requests to the the V2 API endpoints, which have a lower latency.
+
+#### orjson serialization
+
+We now use [orjson](https://github.com/ijl/orjson) to serialize the payloads, which provides a performance improvement, especially when using exogenous features.
+
+#### Historical exogenous features
+
+It's now possible to define historical exogenous features in the `forecast` method by providing the feature names through `hist_exog_list`.
+
+#### Feature contributions
+
+You can now get the contributions of your exogenous features to the forecast by setting `feature_contributions=True` in the `forecast` method.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.6.0).*
+
+## 0.5.0
+
+### 🚀 Feature Enhancements
+
+#### Cross Validation endpoint
+
+The `cross_validation` method used to make one API call per window, now the method makes a single API call.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.5.0).*
+
+## 0.4.0
+
+### 🔄 Changes & Deprecations
+
+- **Deprecation of `nixtlats`package:**
+  The `nixtlats` package has been deprecated in favor of the new `nixtla` package. Please make sure to install the `nixtla` package and update your imports like the following:
+
+  **Before:**
+  ```python
+  from nixtlats import NixtlaClient
+  ```
+
+  **After:**
+  ```python
+  from nixtla import NixtlaClient
+  ```
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.4.0).*
+
+## 0.3.0
+
+### 🔄 Changes & Deprecations
+
+- **Deprecation of `TimeGPT` Class:**
+  In an effort to streamline our API and align with industry best practices, we're deprecating the `TimeGPT` class in favor of the new `NixtlaClient` class. This change is designed to provide a more intuitive and powerful interface for interacting with our services.
+
+  **Before:**
+  ```python
+  from nixtlats import TimeGPT
+
+  # Initialize the TimeGPT model
+  timegpt = TimeGPT()
+  ```
+
+  **After:**
+  ```python
+  from nixtlats import NixtlaClient
+
+  # Initialize the NixtlaClient
+  nixtla = NixtlaClient()
+  ```
+
+- **Renaming of Configuration Parameters:**
+  To enhance clarity and consistency with other SDKs, we've renamed the `token` parameter to `api_key` and `environment` to `base_url`.
+
+  **Before:**
+  ```python
+  timegpt = TimeGPT(token='YOUR_TOKEN', environment='YOUR_ENVIRONMENT_URL')
+  ```
+
+  **After:**
+  ```python
+  nixtla = NixtlaClient(api_key='YOUR_API_KEY', base_url='YOUR_BASE_URL')
+  ```
+
+- **Introduction of `NixtlaClient.validate_api_key`:**
+  Replacing the previous `NixtlaClient.validate_token` method, this update aligns with the new authentication parameter naming and offers a straightforward way to validate API keys.
+
+  **Before:**
+  ```python
+  timegpt.validate_token()
+  ```
+
+  **After:**
+  ```python
+  nixtla.validate_api_key()
+  ```
+
+- **Environment Variable Changes:**
+  In line with the renaming of parameters, we've updated the environment variables to set up the API key and base URL. The `TIMEGPT_TOKEN` is now replaced with `NIXTLA_API_KEY`, and we've introduced `NIXTLA_BASE_URL` for custom API URLs.
+
+#### **Backward Compatibility & Future Warnings:**
+
+These changes are designed to be backward compatible. However, users can expect to see future warnings when utilizing deprecated features, such as the `TimeGPT` class.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.3.0).*
+
+## 0.2.0 (Previously Released)
+
+### 🔄 Changes & Deprecations
+
+- **Renaming of Fine-Tuning Parameters:**
+  The `finetune_steps` and `finetune_loss` parameters were renamed to `fewshot_steps` and `fewshot_loss`. Additionally, the model parameter values changed from `short-horizon` and `long-horizon` to `timegpt-1` and `timegpt-1-long-horizon`, with an emphasis on preserving backward compatibility. In version 0.3.0, these changes are deprecated in favor of reverting to the original parameter names and values, ensuring a seamless transition for existing users.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.2.0).*
+
+## 0.1.21
+
+### 🚀 Feature Enhancements
+
+#### Introduction of Quantile Forecasts in `forecast` and `cross_validation` Methods 📈
+
+We're thrilled to announce the integration of the `quantiles` argument into TimeGP's `forecast` and `cross_validation` methods. This feature allows users to specify a list of quantiles, offering a comprehensive view of potential future values under uncertainty.
+
+- **Quantile Forecasting Capability:**
+  By providing a list of quantiles, users can now obtain forecasts at various percentiles of the forecast distribution. This is crucial for understanding the range of possible outcomes and assessing risks more effectively.
+
+``` python
+# Generate quantile forecasts
+quantiles = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
+timegpt_quantile_fcst_df = timegpt.forecast(df=df, h=12, quantiles=quantiles, ...)
+```
+
+- **Enhanced Cross-Validation with Quantiles:**
+  The `cross_validation` method has been updated to support quantile forecasting, enabling a more nuanced validation of model performance across different percentiles.
+
+``` python
+# Apply quantile forecasting in cross-validation
+timegpt_cv_quantile_fcst_df = timegpt.cross_validation(df=df, h=12, n_windows=5, quantiles=quantiles, ...)
+```
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.1.21).*
+
+## 0.1.20
+
+### 🚀 Feature Enhancements
+
+#### Enhanced Model Fine-tuning with `finetune_loss` and `finetune_steps` 🛠️
+
+The latest update brings a significant enhancement to the fine-tuning capabilities of our forecasting models. With the introduction of the `finetune_loss`, users now have the ability to not only specify the number of steps for fine-tunning (with `finetune_steps`) but also to define the target loss for fine-tunning, offering more granular control over model optimization.
+
+- **`finetune_loss` Options:**
+  - `default`: Adopts the model's preset loss function, optimized during initial training.
+  - `mae` (Mean Absolute Error): Focuses on the mean of the absolute differences between predicted and actual values.
+  - `mse` (Mean Squared Error): Emphasizes the mean of the squares of the differences between predicted and actual values.
+  - `rmse` (Root Mean Squared Error): Provides the square root of MSE, offering error terms in the same units as the predictions.
+  - `mape` (Mean Absolute Percentage Error): Measures the mean absolute percent difference between predicted and actual values.
+  - `smape` (Symmetric Mean Absolute Percentage Error): Offers a symmetric version of MAPE, ensuring equal treatment of over and underestimations.
+
+- **`finetune_steps`:** Determines the number of steps to execute during the fine-tuning process. It is crucial to set `finetune_steps` to a value greater than 0 to activate the fine-tuning mechanism with the chosen `finetune_loss` function. This allows for a more tailored optimization, aligning the model closely with specific forecasting requirements and improving its predictive performance.
+
+``` python
+# Configure model fine-tuning with custom loss function and steps
+fcst_df = timegpt.forecast(df, model='timegpt-1-long-horizon', finetune_loss='mape', finetune_steps=50)
+
+# Apply fine-tuning to cross-validation for enhanced model validation
+cv_df = timegpt.cross_validation(df, model='timegpt-1', finetune_loss='smape', finetune_steps=50)
+```
+
+This update opens up new possibilities for refining forecasting models, ensuring they are finely tuned to the specific characteristics and challenges of the forecasting task at hand.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.1.20).*
+
+## 0.1.19
+
+### 🚀 Feature Enhancements
+
+#### Advanced Data Partitioning with `num_partitions` 🔄
+
+We're excited to introduce the `num_partitions` argument for our `forecast`, `cross_validation`, and `detect_anomalies` methods, offering more control over data processing and parallelization:
+
+- **Optimized Resource Utilization in Distributed Environments:** For Spark, Ray, or Dask dataframes, `num_partitions` enables the system to either leverage all available parallel resources or to specify the number of parallel processes. This ensures efficient resource allocation and utilization across distributed computing environments.
+
+``` python
+# Utilize num_partitions in distributed environments
+fcst_df = timegpt.forecast(df, model='timegpt-1-long-horizon', num_partitions=10)
+```
+
+- **Efficient Handling of Large Pandas Dataframes:** When working with Pandas dataframes, `num_partitions` groups series into specified partitions, allowing for sequential API calls. This is particularly useful for large dataframes that are impractical to send over the internet in one go, enhancing performance and efficiency.
+
+``` python
+# Efficiently process large Pandas dataframes
+cv_df = timegpt.cross_validation(df, model='timegpt-1', num_partitions=5)
+```
+
+This new feature provides a flexible approach to handling data across different environments, ensuring optimal performance and resource management.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.1.19).*
+
+## 0.1.18
+
+### 🚀 Feature Enhancements
+
+#### Forecast Using Diverse Models 🌐
+
+Release of new forecasting methods. Among the updates, we've unveiled the **`timegpt-1-long-horizon`** model, crafted specifically for long-term forecasts that span multiple seasonalities. To use it, simply specify the model in your methods like so:
+
+``` python
+from nixtlats import TimeGPT
+
+# Initialize the TimeGPT model
+timegpt = TimeGPT()
+
+# Generate forecasts using the long-horizon model
+fcst_df = timegpt.forecast(..., model='timegpt-1-long-horizon')
+
+# Perform cross-validation with the long-horizon model
+cv_df = timegpt.cross_validation(..., model='timegpt-1-long-horizon')
+
+# Detect anomalies with the long-horizon model
+anomalies_df = timegpt.detect_anomalies(..., model='timegpt-1-long-horizon')
+```
+
+Choose between `timegpt-1` for the first version of `TimeGPT` or `timegpt-1-long-horizon` for long horizon tasks..
+
+#### Cross-Validation Methodology 📊
+
+You can dive deeper into your forecasting pipelines with the new `cross_validation` feature. This method enables you to validate forecasts across different windows efficiently:
+
+``` python
+# Set up cross-validation with a custom horizon, number of windows, and step size
+cv_df = timegpt.cross_validation(df, h=35, n_windows=5, step_size=5)
+```
+
+This will generate 5 distinct forecast sets, each with a horizon of 35, stepping through your data every 5 timestamps.
+
+### 🔁 Retry Behavior for Robust API Calls
+
+The new retry mechanism allows the making of more robust API calls (preventing them from crashing with large-scale tasks).
+
+- **`max_retries`**: Number of max retries for an API call.
+- **`retry_interval`**: Pause between retries.
+- **`max_wait_time`**:  Total duration of retries.
+
+``` python
+timegpt = TimeGPT(max_retries=10, retry_interval=5, max_wait_time=360)
+```
+
+### 🔑 Token Inference Made Simple
+
+The `TimeGPT` class now automatically infers your `TIMEGPT_TOKEN` using `os.environ.get('TIMEGPT_TOKEN')`, streamlining your setup:
+
+``` python
+# No more manual token handling - TimeGPT has got you covered
+timegpt = TimeGPT()
+```
+For more information visit our [FAQS](https://docs.nixtla.io/docs/faqs#setting-up-your-authentication-token-for-nixtla-sdk) section.
+
+### 📘 Introducing the FAQ Section
+
+Questions? We've got answers! Our new [FAQ section](https://docs.nixtla.io/docs/faqs) tackles the most common inquiries, from integrating exogenous variables to configuring authorization tokens and understanding long-horizon forecasts.
+
+*See full changelog [here](https://github.com/Nixtla/nixtla/releases/v0.1.18).*

CODE_OF_CONDUCT.md

+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+support@nixtla.io.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.