Upload 8 files

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[server]
+enableCORS = false
+enableXsrfProtection = false

README.md

@@ -1,13 +1,97 @@
 ---
-title: WbRules
-emoji: 💻
-colorFrom: blue
-colorTo: blue
+title: Haystack Search Pipeline with Streamlit
+emoji: 👑
+colorFrom: indigo
+colorTo: indigo
 sdk: streamlit
-sdk_version: 1.26.0
+sdk_version: 1.23.0
 app_file: app.py
 pinned: false
-license: artistic-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Template Streamlit App for Haystack Search Pipelines
+
+This template [Streamlit](https://docs.streamlit.io/) app set up for simple [Haystack search applications](https://docs.haystack.deepset.ai/docs/semantic_search) which does _nothing_ in this state.
+
+See the ['How to use this template'](#how-to-use-this-template) instructions below to create a simple UI for your own Haystack search pipelines.
+
+Below you will also find instructions on how you could [push this to Hugging Face Spaces 🤗](#pushing-to-hugging-face-spaces-).
+
+## Installation and Running
+To run the bare application which does _nothing_:
+1. Install requirements: `pip install -r requirements.txt`
+2. Run the streamlit app: `streamlit run app.py`
+
+This will start up the app on `localhost:8501` where you will find a simple search bar. Before you start editing, you'll notice that the app will only show you instructions on what to edit:
+
+<img width="768" alt="image" src="https://github.com/deepset-ai/haystack-search-pipeline-streamlit/assets/15802862/f38bc0ef-3828-459b-9415-d7d84c6f7ce1">
+
+## How to use this template
+1. Create a new repository from this template or simply open it in a codespace to start playing around 💙
+2. Make sure your `requirements.txt` file includes the Haystack and Streamlit versions you would like to use.
+3. Complete the code to include your Haystack search pipeline and return the results.
+4. Make any UI edits you'd like to and [share with the Haystack community](https://haystack.deepeset.ai/community) 🥳
+
+### Repo structure
+- `./utils`: This is where we have 3 files: 
+    - `config.py`: This is empty in the current state. You may use this file if you'd like to make use of any secrets such as an OpenAI key, a token for an API and so on. An example of this is in [this demo project](https://github.com/TuanaCelik/should-i-follow/blob/main/utils/config.py).
+    - `haystack.py`: Here you will find some functions already set up for you to start creating your Haystack search pipeline. It includes 2 main functions called `start_haystack()` which is what we use to create a pipeline and cache it, and `query()` which is the function called by `app.py` once a user query is received.
+    - `ui.py`: Use this file for any UI and initial value setups.
+- `app.py`: This is the main Streamlit application file that we will run. In its current state it has a simple search bar, a 'Run' button, and a response that you can highlight answers with.
+
+### What to edit?
+1. Create your Haystack search pipeline in the `start_haystack()` function. For example and Extractive QA pipeline:
+
+```python
+#choose a document store and write documents to it
+document_store = InMemoryDocumentStore(use_bm25=True) 
+
+retriever = BM25Retriever(document_store=document_store)
+reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
+
+pipe = Pipeline()
+pipe.add_node(component=retriever, name="Retriever", inputs=['Query'])
+pipe.add_node(component=reader, name="Reader", inputs=["Reader])
+```
+2. Run your Haystack search pipeline in the `query()` function and return the `results`. E.g.
+```python
+params = {"Retriever": {"top_k": 5}}
+results = pipe.run(question, params=params)
+return results["answers"]
+```
+
+## Pushing to Hugging Face Spaces 🤗
+
+Below is an example GitHub action that will let you push your Streamlit app straight to the Hugging Face Hub as a Space.
+
+A few things to pay attention to:
+
+1. Create a New Space on Hugging Face with the Streamlit SDK.
+2. Create a Hugging Face token on your HF account.
+3. Create a secret on your GitHub repo called `HF_TOKEN` and put your Hugging Face token here.
+4. If you're using DocumentStores or APIs that require some keys/tokens, make sure these are provided as a secret for your HF Space too!
+5. This readme is set up to tell HF spaces that it's using streamlit and that the app is running on `app.py`, make any changes to the frontmatter of this readme to display the title, emoji etc you desire.
+6. Create a file in `.github/workflows/hf_sync.yml`. Here's an example that you can change with your own information, and an [example workflow](https://github.com/TuanaCelik/should-i-follow/blob/main/.github/workflows/hf_sync.yml) working for the [Should I Follow demo](https://huggingface.co/spaces/deepset/should-i-follow)
+
+```yaml
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push --force https://{YOUR_HF_USERNAME}:$HF_TOKEN@{YOUR_HF_SPACE_REPO} main
+```

app.py

@@ -0,0 +1,58 @@
+
+from annotated_text import annotation
+from json import JSONDecodeError
+import logging
+from markdown import markdown
+
+import streamlit as st
+
+from utils.haystack import query
+from utils.ui import reset_results, set_initial_state
+
+set_initial_state()
+
+st.write("# Start building out the content of your application here")
+
+# Search bar
+question = st.text_input("Ask a question", value=st.session_state.question, max_chars=100, on_change=reset_results)
+
+run_pressed = st.button("Run")
+
+run_query = (
+    run_pressed or question != st.session_state.question
+)
+
+# Get results for query
+if run_query and question:
+    reset_results()
+    st.session_state.question = question
+    with st.spinner("🔎    Running your pipeline"):
+        try:
+            st.session_state.results = query(question)
+        except JSONDecodeError as je:
+            st.error(
+                "👓    An error occurred reading the results. Is the document store working?"
+            )    
+        except Exception as e:
+            logging.exception(e)
+            st.error("🐞    An error occurred during the request.")
+        
+            
+
+if st.session_state.results:
+    st.write('## Do something with your results')
+    answers = st.session_state.results
+    
+    for count, answer in enumerate(answers):
+        if answer.answer:
+            text, context = answer.answer, answer.context
+            start_idx = context.find(text)
+            end_idx = start_idx + len(text)
+            st.write(
+                markdown(context[:start_idx] + str(annotation(body=text, label="ANSWER", background="#964448", color='#ffffff')) + context[end_idx:]),
+                unsafe_allow_html=True,
+            )
+        else:
+            st.info(
+                "🤔    Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
+            )

requirements.txt

@@ -0,0 +1,5 @@
+farm-haystack==1.17.1
+streamlit==1.23.0
+markdown
+st-annotated-text
+datasets

utils/haystack.py

@@ -0,0 +1,22 @@
+import streamlit as st
+
+from haystack import Pipeline
+from haystack.schema import Answer
+#Use this file to set up your Haystack pipeline and querying
+
+
+# cached to make index and models load only at start
+@st.cache_resource(show_spinner=False)
+def start_haystack():
+    #Use this function to contruct a pipeline
+    pipe = Pipeline()
+    return pipe
+
+pipe = start_haystack()
+
+@st.cache_data(show_spinner=True)
+def query(question):
+    print("Received question")
+    params = {}
+    # results = pipe.run(question, params=params)
+    return [Answer(answer="results", context="Call  pipe.run(question, params=params) and return results in /utils/haystack.py query()")]

utils/ui.py

@@ -0,0 +1,12 @@
+import streamlit as st
+
+def set_state_if_absent(key, value):
+    if key not in st.session_state:
+        st.session_state[key] = value
+
+def set_initial_state():
+    set_state_if_absent("question", "Ask something here?")
+    set_state_if_absent("results", None)
+
+def reset_results(*args):
+    st.session_state.results = None