mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
4209457bdc
Add Redis langserve template! Eventually will add semantic caching to this too. But I was struggling to get that to work for some reason with the LCEL implementation here. - **Description:** Introduces the Redis LangServe template. A simple RAG based app built on top of Redis that allows you to chat with company's public financial data (Edgar 10k filings) - **Issue:** None - **Dependencies:** The template contains the poetry project requirements to run this template - **Tag maintainer:** @baskaryan @Spartee - **Twitter handle:** @tchutch94 **Note**: this requires the commit here that deletes the `_aget_relevant_documents()` method from the Redis retriever class that wasn't implemented. That was breaking the langserve app. --------- Co-authored-by: Sam Partee <sam.partee@redis.com>
89 lines
1.9 KiB
Plaintext
89 lines
1.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "681a5d1e",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Connect to RAG App\n",
|
|
"\n",
|
|
"Assuming you are already running this server:\n",
|
|
"```bash\n",
|
|
"langserve start\n",
|
|
"```"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 37,
|
|
"id": "d774be2a",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Nike's revenue in 2023 was $51.2 billion. \n",
|
|
"\n",
|
|
"Source: 'data/nke-10k-2023.pdf', Start Index: '146100'\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from langserve.client import RemoteRunnable\n",
|
|
"\n",
|
|
"rag_redis = RemoteRunnable('http://localhost:8000/rag-redis')\n",
|
|
"\n",
|
|
"print(rag_redis.invoke(\"What was Nike's revenue in 2023?\"))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 43,
|
|
"id": "07ae0005",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"As of May 31, 2023, Nike had approximately 83,700 employees worldwide. This information can be found in the first piece of context provided. (source: data/nke-10k-2023.pdf, start_index: 32532)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(rag_redis.invoke(\"How many employees work at Nike?\"))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4a6b9f00",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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",
|
|
"version": "3.10.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|