2/3 examples don't seem to work

[thorgexyz]

Scenario

1. Downloading Repo
2. Installing dependencies + adding .env file
3. Starting demos according to examples/README.md

Actual result

✅ Conversation Chain
❌ Retrieval QA with Sources Chain
❌ Conversational Retrieval

Retrieval QA with Sources Chain:

thorge@Ts-MacBook-Air ~/w/f/examples (main)> uvicorn app.retrieval_
qa_chain:app --reload
INFO:     Will watch for changes in these directories: ['/Users/thorge/workdir/fastapi-async-langchain/examples']
INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
INFO:     Started reloader process [4004] using WatchFiles
ERROR:    Error loading ASGI app. Could not import module "app.retrieval_qa_chain"

Conversational Retrieval starts, but only returns 'ConversationalRetrievalChain' in terminal and in the Gradio UI

thorge@Ts-MacBook-Air ~/w/fastapi-async-langchain (main)> curl -N -
X POST \
                                                              -H "A
ccept: text/event-stream" -H "Content-Type: application/json" \
                                                              -d '{
"query": "Give me list of text splitters available with code sample
s" }' \
                                                              http:
//localhost:8000/chat
'ConversationalRetrievalChain'⏎  

[ajndkr]

Hi! I will check this out soon.

[thorgexyz]

For Retrieval QA with Sources Chain, just the Readme command is wrong. Should be uvicorn app.retrieval_qa_w_sources:app --reload

[ajndkr]

@thorgexyz will fix the README.

for Conversational Retrieval demo, you can try the following sample cURL request:

curl -N -X POST \
-H "Accept: text/event-stream" -H "Content-Type: application/json" \
-d '{
    "query": "Give me a code sample",
    "history": [
        [
            "What is a Text Splitter?",
            "Text Splitter is a module that is responsible for breaking up a document into smaller pieces, or chunks, that can be more easily processed."
        ],
        [
            "List all text splitter supported",
            "Langchain provides several different text splitters to help with processing text data. These include the Character Text Splitter, Hugging Face Length Function, Latex Text Splitter, Markdown Text Splitter, NLTK Text Splitter, Python Code Text Splitter, RecursiveCharacterTextSplitter, Spacy Text Splitter, tiktoken (OpenAI) Length Function, and TiktokenText Splitter."
        ]
    ]
}' \
http://localhost:8000/chat

I am already working on setting up project docs page. Will have it ready soon.