Skip to content

Terry/qa template #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Sep 18, 2025
Merged

Terry/qa template #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a3e396e
fix
zhaotai Sep 18, 2025
fbe0083
fix
zhaotai Sep 18, 2025
57f0784
change readme
zhaotai Sep 18, 2025
68a1617
update readme
zhaotai Sep 18, 2025
a044c09
chore: pass empty filter to hatch run
zhaotai Sep 18, 2025
8b84904
chore: pin click 8.1.7 for hatch
zhaotai Sep 18, 2025
1d312bf
chore: remove hatch filter now that click is pinned
zhaotai Sep 18, 2025
25d72c8
fix: ensure dotenv import precedes client import
zhaotai Sep 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions .github/workflows/check-regeneration.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,7 @@ jobs:
- name: Activate pnpm version
working-directory: test-proj/ui
run: corepack prepare --activate


- name: Run UI checks
run: pnpm run all-check
working-directory: test-proj/ui
working-directory: test-proj/ui
2 changes: 0 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,6 @@ This application uses LlamaDeploy. For more information see [the docs](https://d

1. install `uv` if you haven't `brew install uv`
2. run `uvx llamactl serve`
3. Visit http://localhost:4501/docs and see workflow APIs


# Organization

Expand Down
1 change: 1 addition & 0 deletions pyproject.toml.jinja
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ build-backend = "hatchling.build"

[dependency-groups]
dev = [
"click==8.1.7",
"hatch>=1.14.1",
"pytest>=8.4.2",
"ruff>=0.13.0",
Expand Down
16 changes: 9 additions & 7 deletions src/{{ project_name_snake }}/qa_workflows.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,16 @@
import logging
import os
import tempfile

import httpx
from dotenv import load_dotenv
from llama_cloud.types import RetrievalMode
import tempfile
from llama_index.core import Settings
from llama_index.core.chat_engine.types import BaseChatEngine, ChatMode
from llama_index.core.memory import ChatMemoryBuffer
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from llama_cloud_services import LlamaCloudIndex
from workflows import Workflow, step, Context
from workflows.events import (
StartEvent,
Expand All @@ -15,12 +21,6 @@
)
from workflows.retry_policy import ConstantDelayRetryPolicy

from llama_cloud_services import LlamaCloudIndex
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core.memory import ChatMemoryBuffer

from .clients import (
LLAMA_CLOUD_API_KEY,
LLAMA_CLOUD_BASE_URL,
Expand All @@ -30,6 +30,8 @@
LLAMA_CLOUD_PROJECT_ID,
)

load_dotenv()
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what's this for? Doesn't really hurt, but this is automatically handled by llama deploy

[tool.llamadeploy]
env-files = [".env"]

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OPENAI_API_KEY somehow not able to be passed. That's why I add it back

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

image

Seems found the root cause? Now we only read env_files, but config here is env-files



logger = logging.getLogger(__name__)

Expand Down
5 changes: 2 additions & 3 deletions test-proj/.copier-answers.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
# Changes here will be overwritten by Copier; NEVER EDIT MANUALLY
_commit: '2405947'
_commit: c9f43f6
_src_path: .
llama_org_id: asdf
llama_project_id: asdf
project_name: test-proj
project_title: Test Proj
2 changes: 0 additions & 2 deletions test-proj/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,6 @@ This application uses LlamaDeploy. For more information see [the docs](https://d

1. install `uv` if you haven't `brew install uv`
2. run `uvx llamactl serve`
3. Visit http://localhost:4501/docs and see workflow APIs


# Organization

Expand Down
1 change: 1 addition & 0 deletions test-proj/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ build-backend = "hatchling.build"

[dependency-groups]
dev = [
"click==8.1.7",
"hatch>=1.14.1",
"pytest>=8.4.2",
"ruff>=0.13.0",
Expand Down
16 changes: 9 additions & 7 deletions test-proj/src/test_proj/qa_workflows.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,16 @@
import logging
import os
import tempfile

import httpx
from dotenv import load_dotenv
from llama_cloud.types import RetrievalMode
import tempfile
from llama_index.core import Settings
from llama_index.core.chat_engine.types import BaseChatEngine, ChatMode
from llama_index.core.memory import ChatMemoryBuffer
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from llama_cloud_services import LlamaCloudIndex
from workflows import Workflow, step, Context
from workflows.events import (
StartEvent,
Expand All @@ -15,12 +21,6 @@
)
from workflows.retry_policy import ConstantDelayRetryPolicy

from llama_cloud_services import LlamaCloudIndex
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core.memory import ChatMemoryBuffer

from .clients import (
LLAMA_CLOUD_API_KEY,
LLAMA_CLOUD_BASE_URL,
Expand All @@ -30,6 +30,8 @@
LLAMA_CLOUD_PROJECT_ID,
)

load_dotenv()


logger = logging.getLogger(__name__)

Expand Down
1 change: 1 addition & 0 deletions test-proj/ui/src/libs/config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,3 @@
export const APP_TITLE = "Test Proj";
export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
export const INDEX_NAME = "document_qa_index";
12 changes: 2 additions & 10 deletions test-proj/ui/src/pages/Home.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import ChatBot from "../components/ChatBot";
import { WorkflowTrigger } from "@llamaindex/ui";
import { APP_TITLE } from "../libs/config";
import { APP_TITLE, INDEX_NAME } from "../libs/config";

export default function Home() {
return (
Expand All @@ -20,18 +20,10 @@ export default function Home() {
<div className="flex mb-4">
<WorkflowTrigger
workflowName="upload"
inputFields={[
{
key: "index_name",
label: "Index Name",
placeholder: "e.g. document_qa_index",
required: true,
},
]}
customWorkflowInput={(files, fieldValues) => {
return {
file_id: files[0].fileId,
index_name: fieldValues.index_name,
index_name: INDEX_NAME,
};
}}
/>
Expand Down
3 changes: 3 additions & 0 deletions ui/src/libs/config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
export const APP_TITLE = "Test Project";
export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
export const INDEX_NAME = "document_qa_index";
1 change: 1 addition & 0 deletions ui/src/libs/config.ts.jinja
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,3 @@
export const APP_TITLE = "{{ project_title }}";
export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
export const INDEX_NAME = "document_qa_index";
12 changes: 2 additions & 10 deletions ui/src/pages/Home.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import ChatBot from "../components/ChatBot";
import { WorkflowTrigger } from "@llamaindex/ui";
import { APP_TITLE } from "../libs/config";
import { APP_TITLE, INDEX_NAME } from "../libs/config";

export default function Home() {
return (
Expand All @@ -20,18 +20,10 @@ export default function Home() {
<div className="flex mb-4">
<WorkflowTrigger
workflowName="upload"
inputFields={[
{
key: "index_name",
label: "Index Name",
placeholder: "e.g. document_qa_index",
required: true,
},
]}
customWorkflowInput={(files, fieldValues) => {
return {
file_id: files[0].fileId,
index_name: fieldValues.index_name,
index_name: INDEX_NAME,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

shouldn't this just entirely be managed on the server? I don't see a reason it needs to be parameterized

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just want to be as less change as possible to ship...

};
}}
/>
Expand Down