Add Alibaba cloud Bailian index intergration (run-llama#13378)

llama-index-integrations/indices/llama-index-indices-managed-dashscope/.gitignore

@@ -0,0 +1,156 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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/
+.ruff_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
+notebooks/
+
+# 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/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json
+
+# local test file
+tests/test_local.py

llama-index-integrations/indices/llama-index-indices-managed-dashscope/BUILD

@@ -0,0 +1,3 @@
+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/indices/llama-index-indices-managed-dashscope/Makefile

@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help:	## Show all Makefile targets.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format:	## Run code autoformatters (black).
+	pre-commit install
+	git ls-files | xargs pre-commit run black --files
+
+lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
+	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test:	## Run tests via pytest.
+	pytest tests
+
+watch-docs:	## Build and watch documentation.
+	sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/

llama-index-integrations/indices/llama-index-indices-managed-dashscope/README.md

@@ -0,0 +1,46 @@
+# LlamaIndex Indices Integration: Managed-Dashscope
+
+## Installation
+
+```shell
+pip install llama-index-indices-managed-dashscope
+```
+
+## Usage
+
+```python
+import os
+from llama_index.core.schema import QueryBundle
+from llama_index.readers.dashscope.base import DashScopeParse
+from llama_index.readers.dashscope.utils import ResultType
+
+os.environ["DASHSCOPE_API_KEY"] = "your_api_key_here"
+os.environ["DASHSCOPE_WORKSPACE_ID"] = "your_workspace_here"
+
+# init retriever from scratch
+from llama_index.indices.managed.dashscope.retriever import (
+    DashScopeCloudRetriever,
+)
+
+
+file_list = [
+    # your files (accept doc, docx, pdf)
+]
+
+parse = DashScopeParse(result_type=ResultType.DASHCOPE_DOCMIND)
+documents = parse.load_data(file_path=file_list)
+
+# create a new index
+index = DashScopeCloudIndex.from_documents(
+    documents,
+    "my_first_index",
+    verbose=True,
+)
+
+# # connect to an existing index
+# index = DashScopeCloudIndex("my_first_index")
+
+retriever = index.as_retriever()
+nodes = retriever.retrieve("test query")
+print(nodes)
+```

llama-index-integrations/indices/llama-index-indices-managed-dashscope/llama_index/indices/managed/dashscope/BUILD

@@ -0,0 +1 @@
+python_sources()

llama-index-integrations/indices/llama-index-indices-managed-dashscope/llama_index/indices/managed/dashscope/__init__.py

@@ -0,0 +1,5 @@
+from llama_index.indices.managed.dashscope.base import DashScopeCloudIndex
+from llama_index.indices.managed.dashscope.retriever import DashScopeCloudRetriever
+
+
+__all__ = ["DashScopeCloudIndex", "DashScopeCloudRetriever"]

llama-index-integrations/indices/llama-index-indices-managed-dashscope/llama_index/indices/managed/dashscope/api_utils.py

@@ -0,0 +1,122 @@
+import json
+from typing import List, Optional
+
+from llama_index.indices.managed.dashscope.transformations import (
+    DashScopeConfiguredTransformation,
+)
+from llama_index.core.schema import BaseNode, TransformComponent
+
+
+def default_transformations() -> List[TransformComponent]:
+    """Default transformations."""
+    from llama_index.node_parser.dashscope import DashScopeJsonNodeParser
+    from llama_index.embeddings.dashscope import (
+        DashScopeEmbedding,
+        DashScopeTextEmbeddingModels,
+        DashScopeTextEmbeddingType,
+    )
+
+    node_parser = DashScopeJsonNodeParser()
+    document_embedder = DashScopeEmbedding(
+        model_name=DashScopeTextEmbeddingModels.TEXT_EMBEDDING_V2,
+        text_type=DashScopeTextEmbeddingType.TEXT_TYPE_DOCUMENT,
+    )
+    return [
+        node_parser,
+        document_embedder,
+    ]
+
+
+def get_pipeline_create(
+    name: str,
+    transformations: Optional[List[TransformComponent]] = None,
+    documents: Optional[List[BaseNode]] = None,
+) -> dict:
+    configured_transformations: List[DashScopeConfiguredTransformation] = []
+    for transformation in transformations:
+        try:
+            configured_transformations.append(
+                DashScopeConfiguredTransformation.from_component(transformation)
+            )
+        except ValueError:
+            raise ValueError(f"Unsupported transformation: {type(transformation)}")
+
+    configured_transformation_items: List[Dict] = []
+    for item in configured_transformations:
+        configured_transformation_items.append(
+            {
+                "component": json.loads(item.component.json()),
+                "configurable_transformation_type": item.configurable_transformation_type.name,
+            }
+        )
+    data_sources = [
+        {
+            "source_type": "DATA_CENTER_FILE",
+            "component": {
+                "doc_ids": [doc.node_id for doc in documents],
+            },
+        }
+    ]
+    return {
+        "name": name,
+        "pipeline_type": "MANAGED_SHARED",
+        "configured_transformations": configured_transformation_items,
+        "data_sources": data_sources,
+        "data_sinks": [
+            {
+                "sink_type": "ES",
+            }
+        ],
+        # for debug
+        "data_type": "structured",
+        "config_model": "recommend",
+    }
+
+
+def get_doc_insert(
+    transformations: Optional[List[TransformComponent]] = None,
+    documents: Optional[List[BaseNode]] = None,
+) -> dict:
+    configured_transformations: List[DashScopeConfiguredTransformation] = []
+    for transformation in transformations:
+        try:
+            configured_transformations.append(
+                DashScopeConfiguredTransformation.from_component(transformation)
+            )
+        except ValueError:
+            raise ValueError(f"Unsupported transformation: {type(transformation)}")
+
+    configured_transformation_items: List[Dict] = []
+    for item in configured_transformations:
+        configured_transformation_items.append(
+            {
+                "component": json.loads(item.component.json()),
+                "configurable_transformation_type": item.configurable_transformation_type.name,
+            }
+        )
+    data_sources = [
+        {
+            "source_type": "DATA_CENTER_FILE",
+            "component": {
+                "doc_ids": [doc.node_id for doc in documents],
+            },
+        }
+    ]
+    return {
+        "configured_transformations": configured_transformation_items,
+        "data_sources": data_sources,
+    }
+
+
+def get_doc_delete(ref_doc_ids: List[str]) -> dict:
+    data_sources = [
+        {
+            "source_type": "DATA_CENTER_FILE",
+            "component": {
+                "doc_ids": ref_doc_ids,
+            },
+        }
+    ]
+    return {
+        "data_sources": data_sources,
+    }