Duplicate from RyanDA/US_History_QA

.gitattributes

@@ -0,0 +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
+db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+---
+title: US History QA
+emoji: 📖
+colorFrom: blue
+colorTo: gray
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+license: bigscience-openrail-m
+duplicated_from: RyanDA/US_History_QA
+---
+# Overview
+This is a basic Question-Answer style of chain using a database created from OpenStax's free US History textbook. 
+The question is embedded as a vector, the database retrieves the nearest vectors in the database, and that is then input into GPT-3.5-turbo to generate a cohesive answer.
+This entire workflow is visible via the app.py file.
+
+# Citation Information
+Access the US History textbook (used in the database) for free at https://openstax.org/books/us-history/pages/1-introduction 
+I do not claim any of their content as my own.

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+import openai
+import os
+
+openai.api_key = os.environ["OPENAI_API_KEY"]
+
+embedding = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+vectordb = Chroma(persist_directory='db',
+                  embedding_function=embedding)
+retriever = vectordb.as_retriever(search_kwargs={"k": 4})
+
+def answer(message):
+    ctx = retriever.get_relevant_documents(message)
+
+    prompt = """Use the following pieces of context to answer the question at the end. 
+    If you don't know the answer, just say that you don't know, don't try to 
+    make up an answer.
+
+    {context}
+
+    Question: {question}
+    Helpful Answer: """.format(context = " ".join([doc.page_content for doc in ctx]), question = message)
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages= [
+            {'role': 'user', 'content': prompt}
+        ],
+        temperature=0
+    )
+    sources = "\n\nSources:\n" + "\n".join([doc.metadata['source'] for doc in ctx])
+
+    ans = response['choices'][0]['message']['content'] + sources
+    return ans
+
+iface = gr.Interface(fn=answer, inputs="text", outputs="text")
+iface.launch()

db/305cbbe9-9334-4981-9f05-c90242c205d5/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c177925075bdef4e93a52e9c88ebf3984cd22ad2e99c68395b6a40d3a5559141
+size 3352000

db/305cbbe9-9334-4981-9f05-c90242c205d5/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa74df29146ea4379b9d410d6f80c1e7a588b871a2adba5ba7981b85b3c975ed
+size 100

db/305cbbe9-9334-4981-9f05-c90242c205d5/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c93375249ccb1889e8c85a557e79a4d042f168fdd755dc4f4f8a943c1c25536
+size 113989

db/305cbbe9-9334-4981-9f05-c90242c205d5/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0599094165cf85af6d6020b52957285948d1e15063d3e0f7f2428b1a54e122b8
+size 8000

db/305cbbe9-9334-4981-9f05-c90242c205d5/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137d697b2215372fe3747170478353e7965cd2692b58bac2eaa13c5baabbe511
+size 17316

db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e3d06dec869903f3c65a48d685ce2cbf72fec5f358bb1c198fbe9a3ef59b93
+size 20537344

requirements.txt

@@ -0,0 +1,6 @@
+unstructured
+langchain
+sentence_transformers
+chromadb
+gradio
+openai