Duplicate from mutukrish/eng-to-mql

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,14 @@
+---
+title: Eng To Mql
+emoji: 🏃
+colorFrom: yellow
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: mutukrish/eng-to-mql
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,197 @@
+import streamlit as st
+import os
+import openai
+from pymongo import MongoClient
+from datetime import datetime
+import random
+
+# Schema Versions
+# 1. First version, using text-davinci-003 model
+# 2. Switched to gpt-3.5-turbo model
+# 3. Logging the model as well
+
+
+# you need to set your OpenAI API key as environment variable
+openai.api_key = st.secrets["API_KEY"]
+
+MOVIES_EXAMPLE_DOC = """{
+  _id: ObjectId("573a1390f29313caabcd4135"),
+  genres: [ 'Short' ],
+  runtime: 1,
+  cast: [ 'Charles Kayser', 'John Ott' ],
+  num_mflix_comments: 0,
+  title: 'Blacksmith Scene',
+  countries: [ 'USA' ],
+  released: ISODate("1893-05-09T00:00:00.000Z"),
+  directors: [ 'William K.L. Dickson' ],
+  rated: 'UNRATED',
+  awards: { wins: 1, nominations: 0, text: '1 win.' },
+  lastupdated: '2015-08-26 00:03:50.133000000',
+  year: 1893,
+  imdb: { rating: 6.2, votes: 1189, id: 5 },
+  type: 'movie',
+  tomatoes: {
+    viewer: { rating: 3, numReviews: 184, meter: 32 },
+    lastUpdated: ISODate("2015-06-28T18:34:09.000Z")
+  }
+}"""
+
+MOVIES_EXAMPLE_QUESTIONS = [
+    (
+        "How many fantasy or horror movies from the USA with an imdb rating "
+        "greater than 6.0 are there in this dataset?"
+    ),
+    (
+        "Which movies were released on a Monday and have a higher tomato rating "
+        "than IMDB rating? Keep in mind that IMDB goes from 1-10 and tomatoes "
+        "only from 1-5, so you need to normalise the ratings to do a fair comparison."
+    ),
+    "What movies should I watch to learn more about Japanse culture?",
+    (
+        "How many movies were released in each decade? Write decade as a string, e.g. "
+        "'1920-1929'. Sort ascending by decade."
+    ),
+    (
+        "Find movies that are suitable to watch with my kids, both by genre and their "
+        "parental guidance rating. Just recommend good movies."
+    ),
+]
+
+BASE_CHAT_MESSAGES = [
+    {
+        "role": "system",
+        "content": "You are an expert English to MongoDB aggregation pipeline translation system."
+        "You will accept an example document from a collection and an English question, and return an aggregation "
+        "pipeline that can answer the question. Do not explain the query or add any additional comments, only "
+        "return a single code block with the aggregation pipeline without the aggregate command.",
+    }
+]
+
+MODEL_NAME = "gpt-3.5-turbo"
+
+
+@st.cache
+def ask_model(doc, question):
+    """This is the call to the OpenAI API. It creates a prompt from the document
+    and question and returns the endpoint's response."""
+
+    messages = BASE_CHAT_MESSAGES + [
+        {
+            "role": "user",
+            "content": f"Example document: {doc.strip()}\n\nQuestion: {question.strip()}\n\n",
+        }
+    ]
+
+    return openai.ChatCompletion.create(
+        model=MODEL_NAME,
+        messages=messages,
+        temperature=0,
+        max_tokens=1000,
+        top_p=1.0,
+    )
+
+
+def extract_pipeline(response):
+    content = response["choices"][0]["message"]["content"].strip("\n `")
+    return content
+
+
+st.set_page_config(layout="wide")
+
+# initialise session state
+if not "response" in st.session_state:
+    st.session_state.response = None
+if not "_id" in st.session_state:
+    st.session_state._id = None
+if not "feedback" in st.session_state:
+    st.session_state.feedback = False
+if not "default_question" in st.session_state:
+    st.session_state.default_question = random.choice(MOVIES_EXAMPLE_QUESTIONS)
+
+# DB access
+
+
+st.markdown(
+    """# English to MQL Demo
+
+This demo app uses OpenAI's GPT-4 (gpt-4) model to generate a MongoDB
+aggregation pipeline from an English question and example document.
+
+🚧 The app is experimental and may return incorrect results. Do not enter any sensitive information! 🚧
+"""
+)
+
+
+# two-column layout
+col_left, col_right = st.columns(2, gap="large")
+
+with col_left:
+    st.markdown("### Example Document and Question")
+    # wrap textareas in form
+    with st.form("text_inputs"):
+        doc = st.text_area(
+            "Enter example document from collection, e.g. db.collection.findOne()",
+            value=MOVIES_EXAMPLE_DOC,
+            height=300,
+        )
+
+        # question textarea
+        question = st.text_area(
+            label="Ask question in English",
+            value=st.session_state.default_question,
+        )
+
+        # submit button
+        submitted = st.form_submit_button("Translate", type="primary")
+        if submitted:
+            st.session_state._id = None
+            st.session_state.feedback = False
+            st.session_state.response = ask_model(doc, question)
+
+
+with col_right:
+    st.markdown("### Generated MQL")
+
+    # show response
+    response = st.session_state.response
+    if response:
+        pipeline = extract_pipeline(response)
+        # print result as code block
+        st.code(
+            pipeline,
+            language="javascript",
+        )
+
+        # feedback form
+        with st.empty():
+            if st.session_state.feedback:
+                st.write("✅ Thank you for your feedback.")
+
+            elif st.session_state._id:
+                with st.form("feedback_inputs"):
+                    radio = st.radio("Is the result correct?", ("Yes", "No"))
+                    feedback = st.text_area(
+                        "If not, please tell us what the issue is:",
+                    )
+
+                    # submit button
+                    feedback_submit = st.form_submit_button(
+                        "Submit Feedback", type="secondary"
+                    )
+                    if feedback_submit:
+                        st.session_state.feedback = {
+                            "correct": radio == "Yes",
+                            "comment": feedback,
+                        }
+
+            else:
+                doc = {
+                    "ts": datetime.now(),
+                    "doc": doc,
+                    "question": question,
+                    "generated_mql": pipeline,
+                    "response": response,
+                    "version": 3,
+                    "model": MODEL_NAME,
+                }
+

requirements.txt

@@ -0,0 +1,4 @@
+openai==0.27.0
+streamlit==1.17.0
+pymongo==4.3.3
+watchdog==3.0.0