Upload 16 files

pages/2_👩🏼‍🔬 Describe Domain.py

@@ -84,13 +84,23 @@ with tab_domain_perspectives:
 
     perspectives = st.session_state.get(
         "perspectives",
-        [st.text_input(f"Domain Perspective 0", value=DEFAULT_PERSPECTIVES[0])],
+        [DEFAULT_PERSPECTIVES[0]],
     )
+    perspectives_container = st.container()
 
-    if st.button("Add New Perspective"):
+    perspectives = [
+        perspectives_container.text_input(
+            f"Domain Perspective {i + 1}", value=perspective
+        )
+        for i, perspective in enumerate(perspectives)
+    ]
+
+    if st.button("Add Perspective", key="add_perspective"):
         n = len(perspectives)
         value = DEFAULT_PERSPECTIVES[n] if n < N_PERSPECTIVES else ""
-        perspectives.append(st.text_input(f"Domain Perspective {n}", value=""))
+        perspectives.append(
+            perspectives_container.text_input(f"Domain Perspective {n + 1}", value="")
+        )
         st.session_state["perspectives"] = perspectives
 
 
@@ -104,14 +114,19 @@ with tab_domain_topics:
         """Topics are the main themes or subjects that are relevant to the domain. For example, the domain of farming can have topics like soil health, crop rotation, or livestock management."""
     )
     topics = st.session_state.get(
-        "topics", [st.text_input(f"Domain Topic 0", value=DEFAULT_TOPICS[0])]
+        "topics",
+        [DEFAULT_TOPICS[0]],
     )
-    new_topic = st.button("Add New Topic")
+    topics_container = st.container()
+    topics = [
+        topics_container.text_input(f"Domain Topic {i + 1}", value=topic)
+        for i, topic in enumerate(topics)
+    ]
 
-    if new_topic:
+    if st.button("Add Topic", key="add_topic"):
         n = len(topics)
         value = DEFAULT_TOPICS[n] if n < N_TOPICS else ""
-        topics.append(st.text_input(f"Domain Topic {n}", value=value))
+        topics.append(topics_container.text_input(f"Domain Topics {n + 1}", value=""))
         st.session_state["topics"] = topics
 
 

pages/3_🌱 Generate Dataset.py

@@ -27,38 +27,57 @@ project_sidebar()
 st.header("🧑‍🌾 Domain Data Grower")
 st.divider()
 st.subheader("Step 3. Run the pipeline to generate synthetic data")
-st.write(
-    "Define the project details, including the project name, domain, and API credentials"
-)
-
+st.write("Define the project repos and models that the pipeline will use.")
 
+st.divider()
 ###############################################################
 # CONFIGURATION
 ###############################################################
 
-st.divider()
-
-st.markdown("### Pipeline Configuration")
+st.markdown("## Pipeline Configuration")
 
-st.write("🤗 Hub details to pull the seed data")
+st.markdown("#### 🤗 Hub details to pull the seed data")
 hub_username = st.text_input("Hub Username", HUB_USERNAME)
 project_name = st.text_input("Project Name", PROJECT_NAME)
 repo_id = f"{hub_username}/{project_name}"
 hub_token = st.text_input("Hub Token", type="password")
 
-st.write("🤖 Inference configuration")
+st.divider()
+
+st.markdown("#### 🤖 Inference configuration")
 
 st.write(
     "Add the url of the Huggingface inference API or endpoint that your pipeline should use. You can find compatible models here:"
 )
-st.link_button(
-    "🤗 Inference compaptible models on the hub",
-    "https://huggingface.co/models?pipeline_tag=text-generation&other=endpoints_compatible&sort=trending",
-)
 
-base_url = st.text_input("Base URL")
+with st.expander("🤗 Recommended Models"):
+    st.write("All inference endpoint compatible models can be found via the link below")
+    st.link_button(
+        "🤗 Inference compaptible models on the hub",
+        "https://huggingface.co/models?pipeline_tag=text-generation&other=endpoints_compatible&sort=trending",
+    )
+    st.write("🔋Projects with sufficient resources could take advantage of LLama3 70b")
+    st.code("https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-70B")
+
+    st.write("🪫Projects with less resources could take advantage of LLama 3 8b")
+    st.code("https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B")
+
+    st.write("🍃Projects with even less resources could take advantage of Phi-2")
+    st.code("https://api-inference.huggingface.co/models/microsoft/phi-2")
+
+    st.write("Note Hugggingface Pro gives access to more compute resources")
+    st.link_button(
+        "🤗 Huggingface Pro",
+        "https://huggingface.co/pricing",
+    )
+
 
-st.write("🔬 Argilla API details to push the generated dataset")
+base_url = st.text_input(
+    label="Base URL for the Inference API",
+    value="https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta",
+)
+st.divider()
+st.markdown("#### 🔬 Argilla API details to push the generated dataset")
 argilla_url = st.text_input("Argilla API URL", ARGILLA_URL)
 argilla_api_key = st.text_input("Argilla API Key", "owner.apikey")
 argilla_dataset_name = st.text_input("Argilla Dataset Name", project_name)
@@ -68,7 +87,7 @@ st.divider()
 # LOCAL
 ###############################################################
 
-st.markdown("### Run the pipeline")
+st.markdown("## Run the pipeline")
 
 st.write(
     "Once you've defined the pipeline configuration, you can run the pipeline from your local machine."
@@ -101,10 +120,15 @@ if st.button("💻 Run pipeline locally", key="run_pipeline_local"):
         ]
     ):
         with st.spinner("Pulling seed data from the Hub..."):
-            seed_data = pull_seed_data_from_repo(
-                repo_id=f"{hub_username}/{project_name}",
-                hub_token=hub_token,
-            )
+            try:
+                seed_data = pull_seed_data_from_repo(
+                    repo_id=f"{hub_username}/{project_name}",
+                    hub_token=hub_token,
+                )
+            except Exception:
+                st.error(
+                    "Seed data not found. Please make sure you pushed the data seed in Step 2."
+                )
 
             domain = seed_data["domain"]
             perspectives = seed_data["perspectives"]
@@ -177,17 +201,22 @@ if CODELESS_DISTILABEL:
             ]
         ):
             with st.spinner("Pulling seed data from the Hub..."):
-                seed_data = pull_seed_data_from_repo(
-                    repo_id=f"{hub_username}/{project_name}",
-                    hub_token=hub_token,
-                )
+                try:
+                    seed_data = pull_seed_data_from_repo(
+                        repo_id=f"{hub_username}/{project_name}",
+                        hub_token=hub_token,
+                    )
+                except Exception as e:
+                    st.error(
+                        "Seed data not found. Please make sure you pushed the data seed in Step 2."
+                    )
+
                 domain = seed_data["domain"]
                 perspectives = seed_data["perspectives"]
                 topics = seed_data["topics"]
                 examples = seed_data["examples"]
                 domain_expert_prompt = seed_data["domain_expert_prompt"]
 
-            with st.spinner("Serializing the pipeline configuration..."):
                 serialize_pipeline(
                     argilla_api_key=argilla_api_key,
                     argilla_dataset_name=argilla_dataset_name,

pipeline.yaml

@@ -54,7 +54,7 @@ pipeline:
         model_id: null
         endpoint_name: null
         endpoint_namespace: null
-        base_url: https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2
+        base_url: https://api-inference.huggingface.co/models/microsoft/phi-2
         tokenizer_id: null
         model_display_name: null
         use_openai_client: false
@@ -163,7 +163,7 @@ pipeline:
         model_id: null
         endpoint_name: null
         endpoint_namespace: null
-        base_url: https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2
+        base_url: https://api-inference.huggingface.co/models/microsoft/phi-2
         tokenizer_id: null
         model_display_name: null
         use_openai_client: false
@@ -390,7 +390,7 @@ pipeline:
         model_id: null
         endpoint_name: null
         endpoint_namespace: null
-        base_url: https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2
+        base_url: https://api-inference.huggingface.co/models/microsoft/phi-2
         tokenizer_id: null
         model_display_name: null
         use_openai_client: false

utils.py

@@ -18,15 +18,16 @@ def project_sidebar():
         )
         st.stop()
 
+    st.sidebar.subheader(f"A Data Growing Project in the domain of {PROJECT_NAME}")
     st.sidebar.markdown(
-        """
-        ## 🌱 Domain Data Grower
-        
+        """        
         This space helps you create a dataset seed for building diverse domain-specific datasets for aligning models.
         """
     )
-    st.sidebar.subheader(f"Project Details: {PROJECT_NAME}")
     st.sidebar.link_button(f"📚 Dataset Repo", DATASET_URL)
     st.sidebar.link_button(f"🤖 Argilla Space", ARGILLA_URL)
     st.sidebar.divider()
     st.sidebar.link_button("🧑‍🌾 New Project", DIBT_PARENT_APP_URL)
+    st.sidebar.link_button(
+        "🤗 Get your Hub Token", "https://huggingface.co/settings/tokens"
+    )