add baidu-qianfan llm (#14414)

docs/docs/examples/llm/qianfan.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "introduction",
+   "metadata": {},
+   "source": [
+    "# Client of Baidu Intelligent Cloud's Qianfan LLM Platform\n",
+    "\n",
+    "Baidu Intelligent Cloud's Qianfan LLM Platform offers API services for all Baidu LLMs, such as ERNIE-3.5-8K and ERNIE-4.0-8K. It also provides a small number of open-source LLMs like Llama-2-70b-chat.\n",
+    "\n",
+    "Before using the chat client, you need to activate the LLM service on the Qianfan LLM Platform console's [online service](https://console.bce.baidu.com/qianfan/ais/console/onlineService) page. Then, Generate an Access Key and a Secret Key in the [Security Authentication](https://console.bce.baidu.com/iam/#/iam/accesslist) page of the console."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "installation",
+   "metadata": {},
+   "source": [
+    "## Installation\n",
+    "\n",
+    "Install the necessary package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "installation-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index-llms-qianfan"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "initialization",
+   "metadata": {},
+   "source": [
+    "## Initialization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "initialization-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.qianfan import Qianfan\n",
+    "import asyncio\n",
+    "\n",
+    "access_key = \"XXX\"\n",
+    "secret_key = \"XXX\"\n",
+    "model_name = \"ERNIE-Speed-8K\"\n",
+    "endpoint_url = \"https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed\"\n",
+    "context_window = 8192\n",
+    "llm = Qianfan(access_key, secret_key, model_name, endpoint_url, context_window)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "sync-chat",
+   "metadata": {},
+   "source": [
+    "## Synchronous Chat\n",
+    "\n",
+    "Generate a chat response synchronously using the `chat` method:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "sync-chat-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.base.llms.types import ChatMessage\n",
+    "\n",
+    "messages = [\n",
+    "    ChatMessage(role=\"user\", content=\"Tell me a joke.\"),\n",
+    "]\n",
+    "chat_response = llm.chat(messages)\n",
+    "print(chat_response.message.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "sync-stream-chat",
+   "metadata": {},
+   "source": [
+    "## Synchronous Stream Chat\n",
+    "\n",
+    "Generate a streaming chat response synchronously using the `stream_chat` method:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "sync-stream-chat-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    ChatMessage(role=\"system\", content=\"You are a helpful assistant.\"),\n",
+    "    ChatMessage(role=\"user\", content=\"Tell me a story.\"),\n",
+    "]\n",
+    "content = \"\"\n",
+    "for chat_response in llm.stream_chat(messages):\n",
+    "    content += chat_response.delta\n",
+    "    print(chat_response.delta, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "async-chat",
+   "metadata": {},
+   "source": [
+    "## Asynchronous Chat\n",
+    "\n",
+    "Generate a chat response asynchronously using the `achat` method:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "async-chat-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def async_chat():\n",
+    "    messages = [\n",
+    "        ChatMessage(role=\"user\", content=\"Tell me an async joke.\"),\n",
+    "    ]\n",
+    "    chat_response = await llm.achat(messages)\n",
+    "    print(chat_response.message.content)\n",
+    "\n",
+    "\n",
+    "asyncio.run(async_chat())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "async-stream-chat",
+   "metadata": {},
+   "source": [
+    "## Asynchronous Stream Chat\n",
+    "\n",
+    "Generate a streaming chat response asynchronously using the `astream_chat` method:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "async-stream-chat-code",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def async_stream_chat():\n",
+    "    messages = [\n",
+    "        ChatMessage(role=\"system\", content=\"You are a helpful assistant.\"),\n",
+    "        ChatMessage(role=\"user\", content=\"Tell me an async story.\"),\n",
+    "    ]\n",
+    "    content = \"\"\n",
+    "    response = await llm.astream_chat(messages)\n",
+    "    async for chat_response in response:\n",
+    "        content += chat_response.delta\n",
+    "        print(chat_response.delta, end=\"\")\n",
+    "\n",
+    "\n",
+    "asyncio.run(async_stream_chat())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

llama-index-integrations/llms/llama-index-llms-qianfan/.gitignore

@@ -0,0 +1,153 @@
+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

llama-index-integrations/llms/llama-index-llms-qianfan/BUILD

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

llama-index-integrations/llms/llama-index-llms-qianfan/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/llms/llama-index-llms-qianfan/README.md

@@ -0,0 +1,26 @@
+# LlamaIndex Llms Integration: Baidu Qianfan
+
+Baidu Intelligent Cloud's Qianfan LLM Platform offers API services for all Baidu LLMs, such as ERNIE-3.5-8K and ERNIE-4.0-8K. It also provides a small number of open-source LLMs like Llama-2-70b-chat.
+
+Before using the chat client, you need to activate the LLM service on the Qianfan LLM Platform console's [online service](https://console.bce.baidu.com/qianfan/ais/console/onlineService) page. Then, Generate an Access Key and a Secret Key in the [Security Authentication](https://console.bce.baidu.com/iam/#/iam/accesslist) page of the console.
+
+## Installation
+
+Install the necessary package:
+
+```
+pip install llama-index-llms-qianfan
+```
+
+## Initialization
+
+```python
+from llama_index.llms.qianfan import Qianfan
+
+access_key = "XXX"
+secret_key = "XXX"
+model_name = "ERNIE-Speed-8K"
+endpoint_url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
+context_window = 8192
+llm = Qianfan(access_key, secret_key, model_name, endpoint_url, context_window)
+```