Upload 4 files

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* 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
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tesla_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,12 @@
----
-title: Streamlit Qna Documents2
-emoji: 🐨
-colorFrom: purple
-colorTo: pink
-sdk: streamlit
-sdk_version: 1.42.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Streamlit Documentation Qna Chroma Anyscale
+emoji: ⚡
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 4.29.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,147 @@
+import os
+import uuid
+import json
+import gradio as gr
+
+from openai import OpenAI
+
+from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain_community.vectorstores import Chroma
+
+from huggingface_hub import CommitScheduler
+from pathlib import Path
+
+
+os.environ['OPEN_API_KEY']  = "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";
+client = OpenAI()
+#client = OpenAI(
+#base_url="https://api.openai.com/v1",
+#OpenAI.api_key = "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"
+#api_key=os.environ["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"]
+#)
+      
+embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
+
+streamlit_collection = 'streamlit'
+
+vectorstore_persisted = Chroma(
+    collection_name=streamlit_collection,
+    persist_directory='./streamlitdb',
+    embedding_function=embedding_model
+)
+
+retriever = vectorstore_persisted.as_retriever(
+    search_type='similarity',
+    search_kwargs={'k': 5}
+)
+
+# Prepare the logging functionality
+
+log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
+log_folder = log_file.parent
+
+scheduler = CommitScheduler(
+    repo_id="document-qna-chroma-anyscale-logs",
+    repo_type="dataset",
+    folder_path=log_folder,
+    path_in_repo="data",
+    every=2
+)
+
+qna_system_message = """
+You are an assistant to a coder. Your task is to provide relevant information about the Python package Streamlit.
+
+User input will include the necessary context for you to answer their questions. This context will begin with the token: ###Context.
+The context contains references to specific portions of documents relevant to the user's query, along with source links.
+The source for a context will begin with the token ###Source
+
+When crafting your response:
+1. Select the most relevant context or contexts to answer the question.
+2. Include the source links in your response.
+3. User questions will begin with the token: ###Question.
+4. If the question is irrelevant to streamlit respond with - "I am an assistant for streamlit Docs. I can only help you with questions related to streamlit"
+
+Please adhere to the following guidelines:
+- Answer only using the context provided.
+- Do not mention anything about the context in your final answer.
+- If the answer is not found in the context, it is very very important for you to respond with "I don't know. Please check the docs @ 'https://docs.streamlit.io/'"
+- Always quote the source when you use the context. Cite the relevant source at the end of your response under the section - Sources:
+- Do not make up sources. Use the links provided in the sources section of the context and nothing else. You are prohibited from providing other links/sources.
+
+Here is an example of how to structure your response:
+
+Answer:
+[Answer]
+
+Source
+[Source]
+"""
+
+qna_user_message_template = """
+###Context
+Here are some documents that are relevant to the question.
+{context}
+```
+{question}
+```
+"""
+
+# Define the predict function that runs when 'Submit' is clicked or when a API request is made
+def predict(user_input):
+
+    relevant_document_chunks = retriever.invoke(user_input)
+    context_list = [d.page_content for d in relevant_document_chunks]
+    context_for_query = ".".join(context_list)
+    
+    prompt = [
+        {'role':'system', 'content': qna_system_message},
+        {'role': 'user', 'content': qna_user_message_template.format(
+            context=context_for_query,
+            question=user_input
+            )
+        }
+    ]
+
+    try:
+        response = client.chat.completions.create(
+            model='gpt-4o-mini',
+            messages=prompt,
+            temperature=0
+        )
+
+        prediction = response.choices[0].message.content
+
+    except Exception as e:
+        prediction = e
+
+    # While the prediction is made, log both the inputs and outputs to a local log file
+    # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
+    # access
+    
+    with scheduler.lock:
+        with log_file.open("a") as f:
+            f.write(json.dumps(
+                {
+                    'user_input': user_input,
+                    'retrieved_context': context_for_query,
+                    'model_response': prediction
+                }
+            ))
+            f.write("\n")
+    
+    return prediction
+
+
+textbox = gr.Textbox(placeholder="Enter your query here", lines=6)
+
+# Create the interface
+demo = gr.Interface(
+    inputs=textbox, fn=predict, outputs="text",
+    title="Streamlit Q&A System",
+    description="This web API presents an interface to ask questions on streamlit documentation",
+    article="Note that questions that are not relevant to streamlit or not within the sample documents will be answered with 'I don't know. Please check the docs @ 'https://docs.streamlit.io/''",
+    concurrency_limit=20
+)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+openai==1.23.2
+chromadb==0.4.22
+langchain==0.1.9
+langchain-community==0.0.32
+sentence-transformers==2.3.1