added streaming fastapi template

packages/create-llama/templates/.gitignore

+__pycache__
+poetry.lock
+storage

packages/create-llama/templates/streaming/fastapi/README-template.md

+This is a [LlamaIndex](https://www.llamaindex.ai/) project using [FastAPI](https://fastapi.tiangolo.com/) bootstrapped with [`create-llama`](https://github.com/run-llama/LlamaIndexTS/tree/main/packages/create-llama).
+
+## Getting Started
+
+First, setup the environment:
+
+```
+poetry install
+poetry shell
+```
+
+Second, run the development server:
+
+```
+python main.py
+```
+
+Then call the API endpoint `/api/chat` to see the result:
+
+```
+curl --location 'localhost:8000/api/chat' \
+--header 'Content-Type: application/json' \
+--data '{ "messages": [{ "role": "user", "content": "Hello" }] }'
+```
+
+You can start editing the API by modifying `app/api/routers/chat.py`. The endpoint auto-updates as you save the file.
+
+Open [http://localhost:8000/docs](http://localhost:8000/docs) with your browser to see the Swagger UI of the API.
+
+## Learn More
+
+To learn more about LlamaIndex, take a look at the following resources:
+
+- [LlamaIndex Documentation](https://docs.llamaindex.ai) - learn about LlamaIndex.
+
+You can check out [the LlamaIndex GitHub repository](https://github.com/run-llama/llama_index) - your feedback and contributions are welcome!

packages/create-llama/templates/streaming/fastapi/app/api/routers/chat.py

+import logging
+import os
+from typing import List
+from fastapi import APIRouter, Depends, HTTPException, Request, status
+from llama_index import (
+    StorageContext,
+    load_index_from_storage,
+    SimpleDirectoryReader,
+    VectorStoreIndex,
+)
+from llama_index.llms.base import MessageRole
+from pydantic import BaseModel
+from sse_starlette.sse import EventSourceResponse
+
+STORAGE_DIR = "./storage"  # directory to cache the generated index
+DATA_DIR = "./data"  # directory containing the documents to index
+
+chat_router = r = APIRouter()
+
+
+class Message(BaseModel):
+    role: MessageRole
+    content: str
+
+
+class _ChatData(BaseModel):
+    messages: List[Message]
+
+
+def get_index():
+    logger = logging.getLogger("uvicorn")
+    # check if storage already exists
+    if not os.path.exists(STORAGE_DIR):
+        logger.info("Creating new index")
+        # load the documents and create the index
+        documents = SimpleDirectoryReader(DATA_DIR).load_data()
+        index = VectorStoreIndex.from_documents(documents)
+        # store it for later
+        index.storage_context.persist(STORAGE_DIR)
+        logger.info(f"Finished creating new index. Stored in {STORAGE_DIR}")
+    else:
+        # load the existing index
+        logger.info(f"Loading index from {STORAGE_DIR}...")
+        storage_context = StorageContext.from_defaults(persist_dir=STORAGE_DIR)
+        index = load_index_from_storage(storage_context)
+        logger.info(f"Finished loading index from {STORAGE_DIR}")
+    return index
+
+
+@r.post("/")
+async def chat(
+    request: Request, data: _ChatData, index: VectorStoreIndex = Depends(get_index)
+) -> Message:
+    # check preconditions
+    if len(data.messages) == 0:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="No messages provided",
+        )
+    lastMessage = data.messages.pop()
+    if lastMessage.role != MessageRole.USER:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="Last message must be from user",
+        )
+
+    # query chat engine
+    chat_engine = index.as_chat_engine()
+    response = chat_engine.stream_chat(lastMessage.content, data.messages)
+
+    # stream response
+    async def event_generator():
+        for token in response.response_gen:
+            # If client closes connection, stop sending events
+            if await request.is_disconnected():
+                break
+            yield token
+
+    return EventSourceResponse(event_generator())

packages/create-llama/templates/streaming/fastapi/gitignore

+__pycache__
+storage

packages/create-llama/templates/streaming/fastapi/main.py

+import os
+import uvicorn
+from app.api.routers.chat import chat_router
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI()
+
+origin = os.getenv("CORS_ORIGIN")
+if origin:
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=[origin],
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+app.include_router(chat_router, prefix="/api/chat")
+
+
+if __name__ == "__main__":
+    uvicorn.run(app="main:app", host="0.0.0.0", reload=True)

packages/create-llama/templates/streaming/fastapi/pyproject.toml

+[tool.poetry]
+name = "llamaindex-fastapi-streaming"
+version = "0.1.0"
+description = ""
+authors = ["Marcus Schiesser <mail@marcusschiesser.de>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.11,<3.12"
+fastapi = "^0.104.1"
+uvicorn = { extras = ["standard"], version = "^0.23.2" }
+llama-index = "^0.8.56"
+pypdf = "^3.17.0"
+sse-starlette = "^1.6.5"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"