D3v (#1398)

.github/actions/run-script-zerox-tests/action.yml

@@ -0,0 +1,14 @@
+name: 'Run SDK Auth Tests'
+description: 'Runs SDK authentication tests for R2R'
+runs:
+  using: "composite"
+  steps:
+    - name: Ingest zerox document
+      working-directory: ./py
+      shell: bash
+      run: poetry run python core/examples/scripts/run_ingest_with_zerox.py
+
+    - name: Test ingested zerox document
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_scripts.py test_ingested_zerox_document

.github/actions/setup-python-full/action.yml

@@ -10,7 +10,7 @@ runs:
     - name: Set up Python
       uses: actions/setup-python@v4
       with:
-        python-version: '3.10'
+        python-version: '3.11'
 
     - name: Install R2R CLI & Python SDK
       shell: bash

.github/actions/setup-python-light/action.yml

@@ -10,7 +10,7 @@ runs:
     - name: Set up Python environment
       uses: actions/setup-python@v4
       with:
-        python-version: '3.10'
+        python-version: '3.11'
 
     - name: Install Poetry and dependencies on Ubuntu and macOS
       if: inputs.os == 'ubuntu-latest' || inputs.os == 'macos-latest'

.github/workflows/build-r2r-docker.yml

@@ -30,7 +30,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Install toml package
         run: pip install toml

.github/workflows/build-unst-docker.yml

@@ -16,7 +16,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Install toml package
         run: pip install toml

.github/workflows/publish-to-pypi.yml

@@ -17,7 +17,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Install poetry
         working-directory: ./py

.github/workflows/r2r-full-integration-deep-dive-tests.yml

@@ -0,0 +1,44 @@
+name: R2R Deep-Dive Integration Tests
+
+on:
+  push:
+    branches:
+      - dev
+      - dev-minor
+  pull_request:
+    branches:
+      - dev
+      - dev-minor
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: "ubuntu-latest"
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      TELEMETRY_ENABLED: 'false'
+      R2R_PROJECT_NAME: r2r_default
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python and install dependencies
+        uses: ./.github/actions/setup-python-full
+        with:
+          os: "ubuntu-latest"
+
+      - name: Setup and start Docker
+        uses: ./.github/actions/setup-docker
+
+      - name: Login Docker
+        uses: ./.github/actions/login-docker
+        with:
+          docker_username: ${{ secrets.RAGTORICHES_DOCKER_UNAME }}
+          docker_password: ${{ secrets.RAGTORICHES_DOCKER_TOKEN }}
+
+      - name: Start R2R Full server
+        uses: ./.github/actions/start-r2r-full
+
+      - name: Run Test Zerox
+        uses: ./.github/actions/run-script-zerox-tests

docs/documentation/cli/graph.mdx

@@ -0,0 +1,127 @@
+---
+title: 'Knowledge Graph'
+description: 'Managing the knowledge graph with the R2R CLI.'
+---
+
+<Note>
+Occasionally this CLI documentation falls out of date, cross-check with the automatically generated <a href="/api-reference/introduction"> API Reference documentation </a> for the latest parameters.
+</Note>
+
+## Knowledge Graph Management
+
+### Create Graph
+
+Create a knowledge graph for a collection using the `create-graph` command:
+
+````bash
+r2r create-graph --collection-id my-collection --run --kg-creation-settings '{"key": "value"}' --force-kg-creation
+````
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="--collection-id" type="str">
+      Collection ID to create graph for. Default is "".
+    </ParamField>
+
+    <ParamField path="--run" type="flag">
+      Run the graph creation process.
+    </ParamField>
+
+    <ParamField path="--kg-creation-settings" type="str">
+      Settings for the graph creation process as a JSON string.
+    </ParamField>
+
+    <ParamField path="--force-kg-creation" type="flag">
+      Force the graph creation process.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Enrich Graph
+
+Enrich an existing knowledge graph using the `enrich-graph` command:
+
+````bash
+r2r enrich-graph --collection-id my-collection --run --force-kg-enrichment --kg-enrichment-settings '{"key": "value"}'
+````
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="--collection-id" type="str">
+      Collection ID to enrich graph for. Default is "".
+    </ParamField>
+
+    <ParamField path="--run" type="flag">
+      Run the graph enrichment process.
+    </ParamField>
+
+    <ParamField path="--force-kg-enrichment" type="flag">
+      Force the graph enrichment process.
+    </ParamField>
+
+    <ParamField path="--kg-enrichment-settings" type="str">
+      Settings for the graph enrichment process as a JSON string.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Get Entities
+
+Retrieve entities from the knowledge graph using the `get-entities` command:
+
+````bash
+r2r get-entities --collection-id my-collection --offset 0 --limit 10 --entity-ids entity1 entity2
+````
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="--collection-id" type="str" required>
+      Collection ID to retrieve entities from.
+    </ParamField>
+
+    <ParamField path="--offset" type="int">
+      Offset for pagination. Default is 0.
+    </ParamField>
+
+    <ParamField path="--limit" type="int">
+      Limit for pagination. Default is 100.
+    </ParamField>
+
+    <ParamField path="--entity-ids" type="list[str]">
+      Entity IDs to filter by.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Get Triples
+
+Retrieve triples from the knowledge graph using the `get-triples` command:
+
+````bash
+r2r get-triples --collection-id my-collection --offset 0 --limit 10 --triple-ids triple1 triple2 --entity-names entity1 entity2
+````
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="--collection-id" type="str" required>
+      Collection ID to retrieve triples from.
+    </ParamField>
+
+    <ParamField path="--offset" type="int">
+      Offset for pagination. Default is 0.
+    </ParamField>
+
+    <ParamField path="--limit" type="int">
+      Limit for pagination. Default is 100.
+    </ParamField>
+
+    <ParamField path="--triple-ids" type="list[str]">
+      Triple IDs to filter by.
+    </ParamField>
+
+    <ParamField path="--entity-names" type="list[str]">
+      Entity names to filter by.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+````

docs/documentation/cli/ingestion.mdx

@@ -0,0 +1,105 @@
+---
+title: 'Ingestion'
+description: 'Ingesting files with the R2R CLI.'
+---
+
+<Note>
+Occasionally this CLI documentation falls out of date, cross-check with the automatcially generated <a href="/api-reference/introduction"> API Reference documentation </a> for the latest parameters.
+</Note>
+
+## Document Ingestion and Management
+
+### Ingest Files
+
+Ingest files or directories into your R2R system using the `ingest-files` command:
+
+```bash
+r2r ingest-files path/to/file1.txt path/to/file2.txt \
+  --document-ids 9fbe403b-c11c-5aae-8ade-ef22980c3ad1 \
+  --metadatas '{"key1": "value1"}'
+```
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="file_paths" type="list[str]" required>
+      The paths to the files to ingest.
+    </ParamField>
+
+    <ParamField path="--document-ids" type="list[str]">
+      Optional document IDs to assign to the ingested files. If not provided, new document IDs will be generated.
+    </ParamField>
+
+    <ParamField path="--metadatas" type="str">
+      Optional metadata to attach to the ingested files, provided as a JSON string. If ingesting multiple files, the metadata will be applied to all files.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Retry Failed Ingestions
+
+Retry ingestion for documents that previously failed using the `retry-ingest-files` command:
+
+```bash
+r2r retry-ingest-files 9fbe403b-c11c-5aae-8ade-ef22980c3ad1
+```
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="document_ids" type="list[str]" required>
+      The IDs of the documents to retry ingestion for.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Update Files
+
+Update existing documents using the `update-files` command:
+
+```bash
+r2r update-files path/to/file1_v2.txt \
+  --document-ids 9fbe403b-c11c-5aae-8ade-ef22980c3ad1 \
+  --metadatas '{"key1": "value2"}'
+```
+
+<AccordionGroup>
+  <Accordion title="Arguments">
+    <ParamField path="file_paths" type="list[str]" required>
+      The paths to the updated files.
+    </ParamField>
+
+    <ParamField path="--document-ids" type="str" required>
+      The IDs of the documents to update, provided as a comma-separated string.
+    </ParamField>
+
+    <ParamField path="--metadatas" type="str">
+      Optional updated metadata to attach to the documents, provided as a JSON string. If updating multiple files, the metadata will be applied to all files.
+    </ParamField>
+  </Accordion>
+</AccordionGroup>
+
+### Ingest Sample Files
+
+Ingest one or more sample files from the R2R GitHub repository using the `ingest-sample-file` or `ingest-sample-files` commands:
+
+```bash
+# Ingest a single sample file
+r2r ingest-sample-file
+
+# Ingest a smaller version of the sample file
+r2r ingest-sample-file --v2
+
+# Ingest multiple sample files
+r2r ingest-sample-files
+```
+
+These commands have no additional arguments. The `--v2` flag for `ingest-sample-file` ingests a smaller version of the sample Aristotle text file.
+
+### Ingest Local Sample Files
+
+Ingest the local sample files in the `core/examples/data_unstructured` directory using the `ingest-sample-files-from-unstructured` command:
+
+```bash
+r2r ingest-sample-files-from-unstructured
+```
+
+This command has no additional arguments. It will ingest all files found in the `data_unstructured` directory.