ChatGPT Retrieval Plugin

.dockerignore

@@ -0,0 +1,10 @@
+# Ignore files that are already ignored by git
+.gitignore
+
+scripts/
+tests/
+examples/
+*.md
+*.pyc
+.dockerignore
+Dockerfile

.gitignore

@@ -0,0 +1,138 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# .vscode files
+.vscode/*
+
+# Pycharm
+.idea/
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+myvenv/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# macOS .DS_Store files
+.DS_Store

.well-known/ai-plugin.json

@@ -0,0 +1,19 @@
+{
+  "schema_version": "v1",
+  "name_for_model": "retrieval",
+  "name_for_human": "Retrieval Plugin",
+  "description_for_model": "Plugin for searching through the user's documents (such as files, emails, and more) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal information.",
+  "description_for_human": "Search through your documents",
+  "auth": {
+    "type": "user_http",
+    "authorization_type": "bearer"
+  },
+  "api": {
+    "type": "openapi",
+    "url": "https://your-app-url.com/.well-known/openapi.yaml",
+    "has_user_authentication": false
+  },
+  "logo_url": "https://your-app-url.com/.well-known/logo.png",
+  "contact_email": "hello@contact.com", 
+  "legal_info_url": "hello@legal.com"
+}

.well-known/openapi.yaml

@@ -0,0 +1,196 @@
+openapi: 3.0.2
+info:
+  title: Retrieval Plugin API
+  description: A retrieval API for querying and filtering documents based on natural language queries and metadata
+  version: 1.0.0
+  servers:
+    - url: https://your-app-url.com
+paths:
+  /query:
+    post:
+      summary: Query
+      description: This endpoint accepts an array of search query objects, each containing a natural language query string ("query") and an optional metadata filter ("filter"). Filters can help refine search results based on criteria such as document source or time period, but are not necessary in most cases. You can send multiple queries to compare information from different sources or break down complex questions into sub-questions. If you receive a ResponseTooLargeError, try splitting up the queries into multiple calls to this endpoint.
+      operationId: query_query_post
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/QueryRequest"
+        required: true
+      responses:
+        "200":
+          description: Successful Response
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/QueryResponse"
+        "422":
+          description: Validation Error
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/HTTPValidationError"
+      security:
+        - HTTPBearer: []
+components:
+  schemas:
+    DocumentChunkMetadata:
+      title: DocumentChunkMetadata
+      type: object
+      properties:
+        source:
+          $ref: "#/components/schemas/Source"
+        source_id:
+          title: Source Id
+          type: string
+        url:
+          title: Url
+          type: string
+        created_at:
+          title: Created At
+          type: string
+        author:
+          title: Author
+          type: string
+        document_id:
+          title: Document Id
+          type: string
+    DocumentChunkWithScore:
+      title: DocumentChunkWithScore
+      required:
+        - text
+        - metadata
+        - score
+      type: object
+      properties:
+        id:
+          title: Id
+          type: string
+        text:
+          title: Text
+          type: string
+        metadata:
+          $ref: "#/components/schemas/DocumentChunkMetadata"
+        embedding:
+          title: Embedding
+          type: array
+          items:
+            type: number
+        score:
+          title: Score
+          type: number
+    DocumentMetadataFilter:
+      title: DocumentMetadataFilter
+      type: object
+      properties:
+        document_id:
+          title: Document Id
+          type: string
+        source:
+          $ref: "#/components/schemas/Source"
+        source_id:
+          title: Source Id
+          type: string
+        author:
+          title: Author
+          type: string
+        start_date:
+          title: Start Date
+          type: string
+        end_date:
+          title: End Date
+          type: string
+    HTTPValidationError:
+      title: HTTPValidationError
+      type: object
+      properties:
+        detail:
+          title: Detail
+          type: array
+          items:
+            $ref: "#/components/schemas/ValidationError"
+    Query:
+      title: Query
+      required:
+        - query
+      type: object
+      properties:
+        query:
+          title: Query
+          type: string
+        filter:
+          $ref: "#/components/schemas/DocumentMetadataFilter"
+        top_k:
+          title: Top K
+          type: integer
+          default: 3
+    QueryRequest:
+      title: QueryRequest
+      required:
+        - queries
+      type: object
+      properties:
+        queries:
+          title: Queries
+          type: array
+          items:
+            $ref: "#/components/schemas/Query"
+    QueryResponse:
+      title: QueryResponse
+      required:
+        - results
+      type: object
+      properties:
+        results:
+          title: Results
+          type: array
+          items:
+            $ref: "#/components/schemas/QueryResult"
+    QueryResult:
+      title: QueryResult
+      required:
+        - query
+        - results
+      type: object
+      properties:
+        query:
+          title: Query
+          type: string
+        results:
+          title: Results
+          type: array
+          items:
+            $ref: "#/components/schemas/DocumentChunkWithScore"
+    Source:
+      title: Source
+      enum:
+        - email
+        - file
+        - chat
+      type: string
+      description: An enumeration.
+    ValidationError:
+      title: ValidationError
+      required:
+        - loc
+        - msg
+        - type
+      type: object
+      properties:
+        loc:
+          title: Location
+          type: array
+          items:
+            anyOf:
+              - type: string
+              - type: integer
+        msg:
+          title: Message
+          type: string
+        type:
+          title: Error Type
+          type: string
+  securitySchemes:
+    HTTPBearer:
+      type: http
+      scheme: bearer

Dockerfile

@@ -0,0 +1,24 @@
+
+FROM python:3.10 as requirements-stage
+
+WORKDIR /tmp
+
+RUN pip install poetry
+
+COPY ./pyproject.toml ./poetry.lock* /tmp/
+
+
+RUN poetry export -f requirements.txt --output requirements.txt --without-hashes
+
+FROM python:3.10
+
+WORKDIR /code
+
+COPY --from=requirements-stage /tmp/requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . /code/
+
+# Heroku uses PORT, Azure App Services uses WEBSITES_PORT, Fly.io uses 8080 by default
+CMD ["sh", "-c", "uvicorn server.main:app --host 0.0.0.0 --port ${PORT:-${WEBSITES_PORT:-8080}}"]