Clean llm-app, and make streamlit ui more visible (#6528)

GitOrigin-RevId: 32d78c9faaa6482f3615bef0a98d8a93629aebdb

examples/pipelines/alert/README.md

@@ -33,7 +33,7 @@ Set your env variables in the .env file placed in this directory or in the root
 OPENAI_API_KEY=sk-...
 SLACK_ALERT_CHANNEL_ID=  # If unset, alerts will be printed to the terminal
 SLACK_ALERT_TOKEN=
-PATHWAY_DATA_DIR= # If unset, defaults to ../../data/magic-cola/live/
+PATHWAY_DATA_DIR= # If unset, defaults to ./data/live/
 PATHWAY_PERSISTENT_STORAGE= # Set this variable if you want to use caching
 ```
 
@@ -65,3 +65,9 @@ curl --data '{
   "query": "When does the magic cola campaign start? Alert me if the start date changes."
 }' http://localhost:8080/ | jq
 ```
+
+or use the Streamlit UI. Run:
+```bash
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
+```
+and then you can access the UI at `0.0.0.0:8501`.

examples/pipelines/alert/app.py

@@ -134,7 +134,7 @@ def decision_to_bool(decision: str) -> bool:
 
 def run(
     *,
-    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "../../data/magic-cola/live/"),
+    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "./data/live/"),
     api_key: str = os.environ.get("OPENAI_API_KEY", ""),
     host: str = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "0.0.0.0"),
     port: int = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", "8080")),

examples/pipelines/contextful/README.md

@@ -14,7 +14,7 @@ Set your env variables in the .env file placed in this directory or in the root
 
 ```bash
 OPENAI_API_KEY=sk-...
-PATHWAY_DATA_DIR= # If unset, defaults to ../../data/pathway-docs/
+PATHWAY_DATA_DIR= # If unset, defaults to ./data/
 PATHWAY_PERSISTENT_STORAGE= # Set this variable if you want to use caching
 ```
 
@@ -44,3 +44,9 @@ curl --data '{
   "query": "How to connect to Kafka in Pathway?"
 }' http://localhost:8080/ | jq
 ```
+
+or use the Streamlit UI. Run:
+```bash
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
+```
+and then you can access the UI at `0.0.0.0:8501`.

examples/pipelines/contextful/app.py

@@ -38,7 +38,7 @@ class QueryInputSchema(pw.Schema):
 
 def run(
     *,
-    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "../../data/pathway-docs/"),
+    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "./data/"),
     api_key: str = os.environ.get("OPENAI_API_KEY", ""),
     host: str = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "0.0.0.0"),
     port: int = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", "8080")),

examples/pipelines/contextful/ui/server.py

@@ -0,0 +1,54 @@
+import os
+
+import requests
+import streamlit as st
+from dotenv import load_dotenv
+
+with st.sidebar:
+    st.markdown(
+        "[View the source code on GitHub](https://github.com/pathwaycom/llm-app)"
+    )
+
+# Load environment variables
+load_dotenv()
+api_host = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "127.0.0.1")
+api_port = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", 8080))
+
+
+# Streamlit UI elements
+st.title("LLM App")
+
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+# React to user input
+if prompt := st.chat_input("How can I help you today?"):
+    # Display user message in chat message container
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    url = f"http://{api_host}:{api_port}/"
+    data = {"query": prompt, "user": "user"}
+
+    response = requests.post(url, json=data)
+
+    if response.status_code == 200:
+        response = response.json()
+        with st.chat_message("assistant"):
+            st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response})
+    else:
+        st.error(
+            f"Failed to send data to Discounts API. Status code: {response.status_code}"
+        )

examples/pipelines/contextful_geometric/README.md

@@ -19,7 +19,7 @@ Set your env variables in the .env file placed in this directory or in the root
 
 ```bash
 OPENAI_API_KEY=sk-...
-PATHWAY_DATA_DIR= # If unset, defaults to ../../data/pathway-docs/
+PATHWAY_DATA_DIR= # If unset, defaults to ./data/
 PATHWAY_PERSISTENT_STORAGE= # Set this variable if you want to use caching
 ```
 
@@ -49,3 +49,9 @@ curl --data '{
   "query": "How to connect to Kafka in Pathway?"
 }' http://localhost:8080/ | jq
 ```
+
+or use the Streamlit UI. Run:
+```bash
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
+```
+and then you can access the UI at `0.0.0.0:8501`.

examples/pipelines/contextful_geometric/app.py

@@ -46,7 +46,7 @@ class QueryInputSchema(pw.Schema):
 
 def run(
     *,
-    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "./examples/data/pathway-docs/"),
+    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "./data/"),
     api_key: str = os.environ.get("OPENAI_API_KEY", ""),
     host: str = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "0.0.0.0"),
     port: int = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", "8080")),

examples/pipelines/contextful_geometric/ui/server.py

@@ -0,0 +1,54 @@
+import os
+
+import requests
+import streamlit as st
+from dotenv import load_dotenv
+
+with st.sidebar:
+    st.markdown(
+        "[View the source code on GitHub](https://github.com/pathwaycom/llm-app)"
+    )
+
+# Load environment variables
+load_dotenv()
+api_host = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "127.0.0.1")
+api_port = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", 8080))
+
+
+# Streamlit UI elements
+st.title("LLM App")
+
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+# React to user input
+if prompt := st.chat_input("How can I help you today?"):
+    # Display user message in chat message container
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    url = f"http://{api_host}:{api_port}/"
+    data = {"query": prompt, "user": "user"}
+
+    response = requests.post(url, json=data)
+
+    if response.status_code == 200:
+        response = response.json()
+        with st.chat_message("assistant"):
+            st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response})
+    else:
+        st.error(
+            f"Failed to send data to Discounts API. Status code: {response.status_code}"
+        )

examples/pipelines/contextful_parsing/README.md

@@ -9,7 +9,7 @@ Set your env variables in the .env file placed in this directory or in the root
 
 ```bash
 OPENAI_API_KEY=sk-...
-PATHWAY_DATA_DIR= # If unset, defaults to ../../data/finance/
+PATHWAY_DATA_DIR= # If unset, defaults to ./data/
 PATHWAY_PERSISTENT_STORAGE= # Set this variable if you want to use caching
 ```
 
@@ -42,11 +42,8 @@ curl --data '{
 }' http://localhost:8080/ | jq
 ```
 
-Or start streamlit UI:
-
-First go to `ui` directory with `cd ui/`
-and run:
-
+or use the Streamlit UI. Run:
 ```bash
-streamlit run server.py
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
 ```
+and then you can access the UI at `0.0.0.0:8501`.

examples/pipelines/contextful_parsing/app.py

@@ -13,16 +13,7 @@
 for documents in the corpus. A prompt is built from the relevant documentations pages
 and sent to the OpenAI GPT-4 chat service for processing.
 
-Usage:
-In the root of this repository run:
-`poetry run ./run_examples.py unstructured`
-or, if all dependencies are managed manually rather than using poetry
-`python examples/pipelines/unstructured/app.py`
-
-You can also run this example directly in the environment with llm_app installed.
-
-In another terminal, navigate to `examples/pipelines/unstructured/ui` and run
-`streamlit run server.py`. You can interact with the app at `localhost:8501`
+Please check the README.md in this directory for how-to-run instructions.
 """
 
 import os
@@ -45,7 +36,7 @@ class QueryInputSchema(pw.Schema):
 
 def run(
     *,
-    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "../../data/finance/"),
+    data_dir: str = os.environ.get("PATHWAY_DATA_DIR", "./data/"),
     api_key: str = os.environ.get("OPENAI_API_KEY", ""),
     host: str = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "0.0.0.0"),
     port: int = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", "8080")),

examples/pipelines/contextful_s3/README.md

@@ -43,3 +43,9 @@ curl --data '{
   "query": "How to connect to Kafka in Pathway?"
 }' http://localhost:8080/ | jq
 ```
+
+or use the Streamlit UI. Run:
+```bash
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
+```
+and then you can access the UI at `0.0.0.0:8501`.

examples/pipelines/contextful_s3/app.py

@@ -13,16 +13,7 @@
 for documents in the corpus. A prompt is built from the relevant documentations pages
 and sent to the OpenAI chat service for processing.
 
-Usage:
-In the root of this repository run:
-`poetry run ./run_examples.py contextful-s3`
-or, if all dependencies are managed manually rather than using poetry
-`python examples/pipelines/contextful_s3/app.py`
-
-You can also run this example directly in the environment with llm_app installed.
-
-To call the REST API:
-curl --data '{"user": "user", "query": "How to connect to Kafka in Pathway?"}' http://localhost:8080/ | jq
+Please check the README.md in this directory for how-to-run instructions.
 """
 
 import os

examples/pipelines/contextful_s3/ui/server.py

@@ -0,0 +1,54 @@
+import os
+
+import requests
+import streamlit as st
+from dotenv import load_dotenv
+
+with st.sidebar:
+    st.markdown(
+        "[View the source code on GitHub](https://github.com/pathwaycom/llm-app)"
+    )
+
+# Load environment variables
+load_dotenv()
+api_host = os.environ.get("PATHWAY_REST_CONNECTOR_HOST", "127.0.0.1")
+api_port = int(os.environ.get("PATHWAY_REST_CONNECTOR_PORT", 8080))
+
+
+# Streamlit UI elements
+st.title("LLM App")
+
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+# React to user input
+if prompt := st.chat_input("How can I help you today?"):
+    # Display user message in chat message container
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    url = f"http://{api_host}:{api_port}/"
+    data = {"query": prompt, "user": "user"}
+
+    response = requests.post(url, json=data)
+
+    if response.status_code == 200:
+        response = response.json()
+        with st.chat_message("assistant"):
+            st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response})
+    else:
+        st.error(
+            f"Failed to send data to Discounts API. Status code: {response.status_code}"
+        )

examples/pipelines/contextless/README.md

@@ -38,3 +38,9 @@ curl --data '{
   "query": "How to connect to Kafka in Pathway?"
 }' http://localhost:8080/ | jq
 ```
+
+or use the Streamlit UI. Run:
+```bash
+streamlit run ui/server.py --server.port 8501 --server.address 0.0.0.0
+```
+and then you can access the UI at `0.0.0.0:8501`.