diff --git a/packages/create-llama/templates/types/simple/fastapi/app/utils/index.py b/packages/create-llama/templates/types/simple/fastapi/app/utils/index.py
index 0ee09b19d0526dca77420f7519d25c71f2f04670..530935b7ec84c93bafee5e4d37265f4e4411fd65 100644
--- a/packages/create-llama/templates/types/simple/fastapi/app/utils/index.py
+++ b/packages/create-llama/templates/types/simple/fastapi/app/utils/index.py
@@ -15,9 +15,10 @@ STORAGE_DIR = "./storage" # directory to cache the generated index
DATA_DIR = "./data" # directory containing the documents to index
service_context = ServiceContext.from_defaults(
- llm=OpenAI("gpt-3.5-turbo")
+ llm=OpenAI(model="gpt-3.5-turbo")
)
+
def get_index():
logger = logging.getLogger("uvicorn")
# check if storage already exists
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/README-template.md b/packages/create-llama/templates/types/simple/fastapi_auth/README-template.md
new file mode 100644
index 0000000000000000000000000000000000000000..f0b92bdfce648a374bd2723fee4ceec69605db69
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/README-template.md
@@ -0,0 +1,42 @@
+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.
+
+The API allows CORS for all origins to simplify development. You can change this behavior by setting the `ENVIRONMENT` environment variable to `prod`:
+
+```
+ENVIRONMENT=prod uvicorn main:app
+```
+
+## 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!
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/__init__.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/api/__init__.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/api/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/api/routers/__init__.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/api/routers/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/api/routers/chat.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/api/routers/chat.py
new file mode 100644
index 0000000000000000000000000000000000000000..81f602edbeae66c5850b30a6183c009ab4b1e014
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/app/api/routers/chat.py
@@ -0,0 +1,56 @@
+from typing import List
+
+from app.utils.index import get_index
+from fastapi import APIRouter, Depends, HTTPException, status
+from llama_index import VectorStoreIndex
+from llama_index.llms.base import MessageRole, ChatMessage
+from pydantic import BaseModel
+
+chat_router = r = APIRouter()
+
+
+class _Message(BaseModel):
+ role: MessageRole
+ content: str
+
+
+class _ChatData(BaseModel):
+ messages: List[_Message]
+
+
+class _Result(BaseModel):
+ result: _Message
+
+
+@r.post("")
+async def chat(
+ data: _ChatData,
+ index: VectorStoreIndex = Depends(get_index),
+) -> _Result:
+ # check preconditions and get last message
+ 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",
+ )
+ # convert messages coming from the request to type ChatMessage
+ messages = [
+ ChatMessage(
+ role=m.role,
+ content=m.content,
+ )
+ for m in data.messages
+ ]
+
+ # query chat engine
+ chat_engine = index.as_chat_engine()
+ response = chat_engine.chat(lastMessage.content, messages)
+ return _Result(
+ result=_Message(role=MessageRole.ASSISTANT, content=response.response)
+ )
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/utils/__init__.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/utils/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/app/utils/index.py b/packages/create-llama/templates/types/simple/fastapi_auth/app/utils/index.py
new file mode 100644
index 0000000000000000000000000000000000000000..43472724877e48853c6bd5df0c19ca9a0aa9371d
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/app/utils/index.py
@@ -0,0 +1,38 @@
+import logging
+import os
+
+from llama_index import (
+ SimpleDirectoryReader,
+ ServiceContext,
+ StorageContext,
+ VectorStoreIndex,
+ load_index_from_storage,
+)
+
+
+STORAGE_DIR = "./storage" # directory to cache the generated index
+DATA_DIR = "./data" # directory containing the documents to index
+
+service_context = ServiceContext.from_defaults(
+ llm=OpenAI(model="gpt-3.5-turbo")
+)
+
+
+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, service_context=service_context)
+ # 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, service_context=service_context)
+ logger.info(f"Finished loading index from {STORAGE_DIR}")
+ return index
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/data/101.pdf b/packages/create-llama/templates/types/simple/fastapi_auth/data/101.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..ae5acffd5398b7c59e2df9e6dead2d99128b719c
Binary files /dev/null and b/packages/create-llama/templates/types/simple/fastapi_auth/data/101.pdf differ
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/gitignore b/packages/create-llama/templates/types/simple/fastapi_auth/gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..069fcb4020566da83dbc398c06dce5bbe92aface
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/gitignore
@@ -0,0 +1,2 @@
+__pycache__
+storage
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/main.py b/packages/create-llama/templates/types/simple/fastapi_auth/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..9dc1a0afb6634f319538e8545bdd647693dffbfb
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/main.py
@@ -0,0 +1,31 @@
+import logging
+import os
+import uvicorn
+from app.api.routers.chat import chat_router
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from dotenv import load_dotenv
+
+load_dotenv()
+
+app = FastAPI()
+
+environment = os.getenv("ENVIRONMENT", "dev") # Default to 'development' if not set
+
+
+if environment == "dev":
+ logger = logging.getLogger("uvicorn")
+ logger.warning("Running in development mode - allowing CORS for all origins")
+ app.add_middleware(
+ CORSMiddleware,
+ allow_origins=["*"],
+ 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)
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/pyproject.toml b/packages/create-llama/templates/types/simple/fastapi_auth/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..59d182bbb47a8d0ee06de3550f2c7fbf954a3901
--- /dev/null
+++ b/packages/create-llama/templates/types/simple/fastapi_auth/pyproject.toml
@@ -0,0 +1,19 @@
+[tool.poetry]
+name = "llamaindex-fastapi"
+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"
+python-dotenv = "^1.0.0"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
diff --git a/packages/create-llama/templates/types/simple/fastapi_auth/tests/__init__.py b/packages/create-llama/templates/types/simple/fastapi_auth/tests/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/packages/create-llama/templates/types/streaming/fastapi/app/utils/index.py b/packages/create-llama/templates/types/streaming/fastapi/app/utils/index.py
index 0ee09b19d0526dca77420f7519d25c71f2f04670..cb16cdba37897fc203bdd0358c5f088628375a3f 100644
--- a/packages/create-llama/templates/types/streaming/fastapi/app/utils/index.py
+++ b/packages/create-llama/templates/types/streaming/fastapi/app/utils/index.py
@@ -15,7 +15,7 @@ STORAGE_DIR = "./storage" # directory to cache the generated index
DATA_DIR = "./data" # directory containing the documents to index
service_context = ServiceContext.from_defaults(
- llm=OpenAI("gpt-3.5-turbo")
+ llm=OpenAI(model="gpt-3.5-turbo")
)
def get_index():