Realtime AI RAG app

.gitattributes

@@ -1,3 +1,4 @@
+*.sqlite3 filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,14 @@
 ---
-title: Real Time RAG
+title: Real Time RAG Application
 emoji: 📉
-colorFrom: pink
-colorTo: pink
+colorFrom: green
+colorTo: yellow
 sdk: gradio
 sdk_version: 4.42.0
 app_file: app.py
 pinned: false
 license: apache-2.0
+description: Real-time AI App with Groq API and LangChain
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Starwars_Vectordb/c4319e40-03fd-4cf7-b946-82b84e796825/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95042e844cfb77b20e578cf65635282a99d7c4dd20e589ac062f38bc389f8e58
+size 4236000

Starwars_Vectordb/c4319e40-03fd-4cf7-b946-82b84e796825/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc596bc1909f7cc610d5839236c90513b4fbad06776c253fa1b21bfd712e940
+size 100

Starwars_Vectordb/c4319e40-03fd-4cf7-b946-82b84e796825/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ed7b91d9d7ca5434195ba03bfe5aeacbb387ea140381f7df3c1c02cd3dd8b0
+size 4000

Starwars_Vectordb/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0962e37a1d9b0257f9b24ddd980ae20301e347edba66bb0ef9d84c15a0dbe8d
+size 3264512

app.py

@@ -0,0 +1,73 @@
+import os
+import gradio as gr
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain_groq import ChatGroq
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from langchain_core.prompts import PromptTemplate
+
+# Load the API key from environment variables
+groq_api_key = os.getenv("Groq_API_Key")
+
+# Initialize the language model with the specified model and API key
+llm = ChatGroq(model="llama-3.1-70b-versatile", api_key=groq_api_key)
+
+# Initialize the embedding model
+embed_model = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+
+# Load the vector store from a local directory
+vectorstore = Chroma(
+    "Starwars_Vectordb",
+    embedding=embed_model,
+)
+
+# Convert the vector store to a retriever
+retriever = vectorstore.as_retriever()
+
+# Define the prompt template for the language model
+template = """You are a Star Wars assistant for answering questions. 
+    Use the provided context to answer the question. 
+    If you don't know the answer, say so. Explain your answer in detail. 
+    Do not discuss the context in your response; just provide the answer directly.
+
+    Context: {context}
+
+    Question: {question}
+    
+    Answer:"""
+
+rag_prompt = PromptTemplate.from_template(template)
+
+# Create the RAG (Retrieval-Augmented Generation) chain
+rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | rag_prompt
+    | llm
+    | StrOutputParser()
+)
+
+# Define the function to stream the RAG memory
+def rag_memory_stream(text):
+    partial_text = ""
+    for new_text in rag_chain.stream(text):
+        partial_text += new_text
+        # Yield the updated conversation history
+        yield partial_text
+
+# Set up the Gradio interface
+title = "Real-time AI App with Groq API and LangChain"
+demo = gr.Interface(
+    title=title,
+    fn=rag_memory_stream,
+    inputs="text",
+    outputs="text",
+    live=True,
+    batch=True,
+    max_batch_size=10000,
+    concurrency_limit=16,
+)
+
+# Launch the Gradio interface
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+langchain
+langchain-community 
+langchainhub 
+langchain-chroma 
+langchain-groq
+langchain-huggingface