updated the files

Dockerfile

@@ -1,28 +1,27 @@
 # Use the official Python 3.9 image
 FROM python:3.9
- 
+
 # Set the working directory to /code
 WORKDIR /code
- 
+
 # Copy the current directory contents into the container at /code
 COPY ./requirements.txt /code/requirements.txt
- 
+
 # Install requirements.txt 
 RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
- 
+
 # Set up a new user named "user" with user ID 1000
 RUN useradd -m -u 1000 user
 # Switch to the "user" user
 USER user
 # Set home to the user's home directory
 ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH
- 
+	PATH=/home/user/.local/bin:$PATH
+
 # Set the working directory to the user's home directory
 WORKDIR $HOME/app
- 
+
 # Copy the current directory contents into the container at $HOME/app setting the owner to the user
 COPY --chown=user . $HOME/app
- 
-# Start the FastAPI app on port 7860, the default port expected by Spaces
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,8 +1,8 @@
 ---
 title: Text Generation
-emoji: 💻
-colorFrom: purple
-colorTo: green
+emoji: 🌍
+colorFrom: green
+colorTo: yellow
 sdk: docker
 pinned: false
 license: mit

main.py

@@ -0,0 +1,50 @@
+from fastapi import FastAPI
+# from transformers import pipeline
+from txtai.embeddings import Embeddings
+from txtai.pipeline import Extractor
+
+# NOTE - we configure docs_url to serve the interactive Docs at the root path
+# of the app. This way, we can use the docs as a landing page for the app on Spaces.
+app = FastAPI(docs_url="/")
+
+# Create embeddings model with content support
+embeddings = Embeddings({"path": "sentence-transformers/all-MiniLM-L6-v2", "content": True})
+embeddings.load('index')
+
+# Create extractor instance
+extractor = Extractor(embeddings, "google/flan-t5-base")
+
+# pipe = pipeline("text2text-generation", model="google/flan-t5-small")
+
+
+# @app.get("/generate")
+# def generate(text: str):
+#     """
+#     Using the text2text-generation pipeline from `transformers`, generate text
+#     from the given input text. The model used is `google/flan-t5-small`, which
+#     can be found [here](https://huggingface.co/google/flan-t5-small).
+#     """
+#     output = pipe(text)
+#     return {"output": output[0]["generated_text"]}
+
+
+def prompt(question):
+  return f"""Answer the following question using only the context below. Say 'no answer' when the question can't be answered.
+            Question: {question}
+            Context: """
+
+
+def search(query, question=None):
+  # Default question to query if empty
+  if not question:
+    question = query
+
+  return extractor([("answer", query, prompt(question), False)])[0][1]
+
+
+@app.get("/rag")
+def rag(question: str):
+    # question = "what is the document about?"
+    answer = search(question)
+    # print(question, answer)
+    return {answer}

requirements.txt

@@ -3,4 +3,5 @@ requests==2.27.*
 uvicorn[standard]==0.17.*
 sentencepiece==0.1.*
 torch==1.11.*
-transformers==4.*
+transformers==4.*
+txtai==6.0.*