llama-stack 0.3.4__py3-none-any.whl → 0.4.0__py3-none-any.whl

llama_stack/core/ui/modules/api.py

@@ -1,32 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import os
-
-from llama_stack_client import LlamaStackClient
-
-
-class LlamaStackApi:
-    def __init__(self):
-        self.client = LlamaStackClient(
-            base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:8321"),
-            provider_data={
-                "fireworks_api_key": os.environ.get("FIREWORKS_API_KEY", ""),
-                "together_api_key": os.environ.get("TOGETHER_API_KEY", ""),
-                "sambanova_api_key": os.environ.get("SAMBANOVA_API_KEY", ""),
-                "openai_api_key": os.environ.get("OPENAI_API_KEY", ""),
-                "tavily_search_api_key": os.environ.get("TAVILY_SEARCH_API_KEY", ""),
-            },
-        )
-
-    def run_scoring(self, row, scoring_function_ids: list[str], scoring_params: dict | None):
-        """Run scoring on a single row"""
-        if not scoring_params:
-            scoring_params = dict.fromkeys(scoring_function_ids)
-        return self.client.scoring.score(input_rows=[row], scoring_functions=scoring_params)
-
-
-llama_stack_api = LlamaStackApi()

llama_stack/core/ui/modules/utils.py

@@ -1,42 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import base64
-import os
-
-import pandas as pd
-import streamlit as st
-
-
-def process_dataset(file):
-    if file is None:
-        return "No file uploaded", None
-
-    try:
-        # Determine file type and read accordingly
-        file_ext = os.path.splitext(file.name)[1].lower()
-        if file_ext == ".csv":
-            df = pd.read_csv(file)
-        elif file_ext in [".xlsx", ".xls"]:
-            df = pd.read_excel(file)
-        else:
-            return "Unsupported file format. Please upload a CSV or Excel file.", None
-
-        return df
-
-    except Exception as e:
-        st.error(f"Error processing file: {str(e)}")
-        return None
-
-
-def data_url_from_file(file) -> str:
-    file_content = file.getvalue()
-    base64_content = base64.b64encode(file_content).decode("utf-8")
-    mime_type = file.type
-
-    data_url = f"data:{mime_type};base64,{base64_content}"
-
-    return data_url

llama_stack/core/ui/page/__init__.py

@@ -1,5 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.

llama_stack/core/ui/page/distribution/__init__.py

@@ -1,5 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.

llama_stack/core/ui/page/distribution/datasets.py

@@ -1,18 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def datasets():
-    st.header("Datasets")
-
-    datasets_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.datasets.list()}
-    if len(datasets_info) > 0:
-        selected_dataset = st.selectbox("Select a dataset", list(datasets_info.keys()))
-        st.json(datasets_info[selected_dataset], expanded=True)

llama_stack/core/ui/page/distribution/eval_tasks.py

@@ -1,20 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def benchmarks():
-    # Benchmarks Section
-    st.header("Benchmarks")
-
-    benchmarks_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.benchmarks.list()}
-
-    if len(benchmarks_info) > 0:
-        selected_benchmark = st.selectbox("Select an eval task", list(benchmarks_info.keys()), key="benchmark_inspect")
-        st.json(benchmarks_info[selected_benchmark], expanded=True)

llama_stack/core/ui/page/distribution/models.py

@@ -1,18 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def models():
-    # Models Section
-    st.header("Models")
-    models_info = {m.identifier: m.to_dict() for m in llama_stack_api.client.models.list()}
-
-    selected_model = st.selectbox("Select a model", list(models_info.keys()))
-    st.json(models_info[selected_model])

llama_stack/core/ui/page/distribution/providers.py

@@ -1,27 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def providers():
-    st.header("🔍 API Providers")
-    apis_providers_lst = llama_stack_api.client.providers.list()
-    api_to_providers = {}
-    for api_provider in apis_providers_lst:
-        if api_provider.api in api_to_providers:
-            api_to_providers[api_provider.api].append(api_provider)
-        else:
-            api_to_providers[api_provider.api] = [api_provider]
-
-    for api in api_to_providers.keys():
-        st.markdown(f"###### {api}")
-        st.dataframe([x.to_dict() for x in api_to_providers[api]], width=500)
-
-
-providers()

llama_stack/core/ui/page/distribution/resources.py

@@ -1,48 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from streamlit_option_menu import option_menu
-
-from llama_stack.core.ui.page.distribution.datasets import datasets
-from llama_stack.core.ui.page.distribution.eval_tasks import benchmarks
-from llama_stack.core.ui.page.distribution.models import models
-from llama_stack.core.ui.page.distribution.scoring_functions import scoring_functions
-from llama_stack.core.ui.page.distribution.shields import shields
-
-
-def resources_page():
-    options = [
-        "Models",
-        "Shields",
-        "Scoring Functions",
-        "Datasets",
-        "Benchmarks",
-    ]
-    icons = ["magic", "shield", "file-bar-graph", "database", "list-task"]
-    selected_resource = option_menu(
-        None,
-        options,
-        icons=icons,
-        orientation="horizontal",
-        styles={
-            "nav-link": {
-                "font-size": "12px",
-            },
-        },
-    )
-    if selected_resource == "Benchmarks":
-        benchmarks()
-    elif selected_resource == "Datasets":
-        datasets()
-    elif selected_resource == "Models":
-        models()
-    elif selected_resource == "Scoring Functions":
-        scoring_functions()
-    elif selected_resource == "Shields":
-        shields()
-
-
-resources_page()

llama_stack/core/ui/page/distribution/scoring_functions.py

@@ -1,18 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def scoring_functions():
-    st.header("Scoring Functions")
-
-    scoring_functions_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.scoring_functions.list()}
-
-    selected_scoring_function = st.selectbox("Select a scoring function", list(scoring_functions_info.keys()))
-    st.json(scoring_functions_info[selected_scoring_function], expanded=True)

llama_stack/core/ui/page/distribution/shields.py

@@ -1,19 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def shields():
-    # Shields Section
-    st.header("Shields")
-
-    shields_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.shields.list()}
-
-    selected_shield = st.selectbox("Select a shield", list(shields_info.keys()))
-    st.json(shields_info[selected_shield])

llama_stack/core/ui/page/evaluations/__init__.py

@@ -1,5 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.

llama_stack/core/ui/page/evaluations/app_eval.py

@@ -1,143 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import json
-
-import pandas as pd
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-from llama_stack.core.ui.modules.utils import process_dataset
-
-
-def application_evaluation_page():
-    st.set_page_config(page_title="Evaluations (Scoring)", page_icon="🦙")
-    st.title("📊 Evaluations (Scoring)")
-
-    # File uploader
-    uploaded_file = st.file_uploader("Upload Dataset", type=["csv", "xlsx", "xls"])
-
-    if uploaded_file is None:
-        st.error("No file uploaded")
-        return
-
-    # Process uploaded file
-    df = process_dataset(uploaded_file)
-    if df is None:
-        st.error("Error processing file")
-        return
-
-    # Display dataset information
-    st.success("Dataset loaded successfully!")
-
-    # Display dataframe preview
-    st.subheader("Dataset Preview")
-    st.dataframe(df)
-
-    # Select Scoring Functions to Run Evaluation On
-    st.subheader("Select Scoring Functions")
-    scoring_functions = llama_stack_api.client.scoring_functions.list()
-    scoring_functions = {sf.identifier: sf for sf in scoring_functions}
-    scoring_functions_names = list(scoring_functions.keys())
-    selected_scoring_functions = st.multiselect(
-        "Choose one or more scoring functions",
-        options=scoring_functions_names,
-        help="Choose one or more scoring functions.",
-    )
-
-    available_models = llama_stack_api.client.models.list()
-    available_models = [m.identifier for m in available_models]
-
-    scoring_params = {}
-    if selected_scoring_functions:
-        st.write("Selected:")
-        for scoring_fn_id in selected_scoring_functions:
-            scoring_fn = scoring_functions[scoring_fn_id]
-            st.write(f"- **{scoring_fn_id}**: {scoring_fn.description}")
-            new_params = None
-            if scoring_fn.params:
-                new_params = {}
-                for param_name, param_value in scoring_fn.params.to_dict().items():
-                    if param_name == "type":
-                        new_params[param_name] = param_value
-                        continue
-
-                    if param_name == "judge_model":
-                        value = st.selectbox(
-                            f"Select **{param_name}** for {scoring_fn_id}",
-                            options=available_models,
-                            index=0,
-                            key=f"{scoring_fn_id}_{param_name}",
-                        )
-                        new_params[param_name] = value
-                    else:
-                        value = st.text_area(
-                            f"Enter value for **{param_name}** in {scoring_fn_id} in valid JSON format",
-                            value=json.dumps(param_value, indent=2),
-                            height=80,
-                        )
-                        try:
-                            new_params[param_name] = json.loads(value)
-                        except json.JSONDecodeError:
-                            st.error(f"Invalid JSON for **{param_name}** in {scoring_fn_id}")
-
-                st.json(new_params)
-            scoring_params[scoring_fn_id] = new_params
-
-        # Add run evaluation button & slider
-        total_rows = len(df)
-        num_rows = st.slider("Number of rows to evaluate", 1, total_rows, total_rows)
-
-        if st.button("Run Evaluation"):
-            progress_text = "Running evaluation..."
-            progress_bar = st.progress(0, text=progress_text)
-            rows = df.to_dict(orient="records")
-            if num_rows < total_rows:
-                rows = rows[:num_rows]
-
-            # Create separate containers for progress text and results
-            progress_text_container = st.empty()
-            results_container = st.empty()
-            output_res = {}
-            for i, r in enumerate(rows):
-                # Update progress
-                progress = i / len(rows)
-                progress_bar.progress(progress, text=progress_text)
-
-                # Run evaluation for current row
-                score_res = llama_stack_api.run_scoring(
-                    r,
-                    scoring_function_ids=selected_scoring_functions,
-                    scoring_params=scoring_params,
-                )
-
-                for k in r.keys():
-                    if k not in output_res:
-                        output_res[k] = []
-                    output_res[k].append(r[k])
-
-                for fn_id in selected_scoring_functions:
-                    if fn_id not in output_res:
-                        output_res[fn_id] = []
-                    output_res[fn_id].append(score_res.results[fn_id].score_rows[0])
-
-                # Display current row results using separate containers
-                progress_text_container.write(f"Expand to see current processed result ({i + 1} / {len(rows)})")
-                results_container.json(
-                    score_res.to_json(),
-                    expanded=2,
-                )
-
-            progress_bar.progress(1.0, text="Evaluation complete!")
-
-            # Display results in dataframe
-            if output_res:
-                output_df = pd.DataFrame(output_res)
-                st.subheader("Evaluation Results")
-                st.dataframe(output_df)
-
-
-application_evaluation_page()

llama_stack/core/ui/page/evaluations/native_eval.py

@@ -1,253 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import json
-
-import pandas as pd
-import streamlit as st
-
-from llama_stack.core.ui.modules.api import llama_stack_api
-
-
-def select_benchmark_1():
-    # Select Benchmarks
-    st.subheader("1. Choose An Eval Task")
-    benchmarks = llama_stack_api.client.benchmarks.list()
-    benchmarks = {et.identifier: et for et in benchmarks}
-    benchmarks_names = list(benchmarks.keys())
-    selected_benchmark = st.selectbox(
-        "Choose an eval task.",
-        options=benchmarks_names,
-        help="Choose an eval task. Each eval task is parameterized by a dataset, and list of scoring functions.",
-    )
-    with st.expander("View Eval Task"):
-        st.json(benchmarks[selected_benchmark], expanded=True)
-
-    st.session_state["selected_benchmark"] = selected_benchmark
-    st.session_state["benchmarks"] = benchmarks
-    if st.button("Confirm", key="confirm_1"):
-        st.session_state["selected_benchmark_1_next"] = True
-
-
-def define_eval_candidate_2():
-    if not st.session_state.get("selected_benchmark_1_next", None):
-        return
-
-    st.subheader("2. Define Eval Candidate")
-    st.info(
-        """
-        Define the configurations for the evaluation candidate model or agent used for generation.
-        Select "model" if you want to run generation with inference API, or "agent" if you want to run generation with agent API through specifying AgentConfig.
-        """
-    )
-    with st.expander("Define Eval Candidate", expanded=True):
-        # Define Eval Candidate
-        candidate_type = st.radio("Candidate Type", ["model", "agent"])
-
-        available_models = llama_stack_api.client.models.list()
-        available_models = [model.identifier for model in available_models]
-        selected_model = st.selectbox(
-            "Choose a model",
-            available_models,
-            index=0,
-        )
-
-        # Sampling Parameters
-        st.markdown("##### Sampling Parameters")
-        temperature = st.slider(
-            "Temperature",
-            min_value=0.0,
-            max_value=1.0,
-            value=0.0,
-            step=0.1,
-            help="Controls the randomness of the response. Higher values make the output more creative and unexpected, lower values make it more conservative and predictable",
-        )
-        top_p = st.slider(
-            "Top P",
-            min_value=0.0,
-            max_value=1.0,
-            value=0.95,
-            step=0.1,
-        )
-        max_tokens = st.slider(
-            "Max Tokens",
-            min_value=0,
-            max_value=4096,
-            value=512,
-            step=1,
-            help="The maximum number of tokens to generate",
-        )
-        repetition_penalty = st.slider(
-            "Repetition Penalty",
-            min_value=1.0,
-            max_value=2.0,
-            value=1.0,
-            step=0.1,
-            help="Controls the likelihood for generating the same word or phrase multiple times in the same sentence or paragraph. 1 implies no penalty, 2 will strongly discourage model to repeat words or phrases.",
-        )
-        if candidate_type == "model":
-            if temperature > 0.0:
-                strategy = {
-                    "type": "top_p",
-                    "temperature": temperature,
-                    "top_p": top_p,
-                }
-            else:
-                strategy = {"type": "greedy"}
-
-            eval_candidate = {
-                "type": "model",
-                "model": selected_model,
-                "sampling_params": {
-                    "strategy": strategy,
-                    "max_tokens": max_tokens,
-                    "repetition_penalty": repetition_penalty,
-                },
-            }
-        elif candidate_type == "agent":
-            system_prompt = st.text_area(
-                "System Prompt",
-                value="You are a helpful AI assistant.",
-                help="Initial instructions given to the AI to set its behavior and context",
-            )
-            tools_json = st.text_area(
-                "Tools Configuration (JSON)",
-                value=json.dumps(
-                    [
-                        {
-                            "type": "brave_search",
-                            "engine": "brave",
-                            "api_key": "ENTER_BRAVE_API_KEY_HERE",
-                        }
-                    ]
-                ),
-                help="Enter tool configurations in JSON format. Each tool should have a name, description, and parameters.",
-                height=200,
-            )
-            try:
-                tools = json.loads(tools_json)
-            except json.JSONDecodeError:
-                st.error("Invalid JSON format for tools configuration")
-                tools = []
-            eval_candidate = {
-                "type": "agent",
-                "config": {
-                    "model": selected_model,
-                    "instructions": system_prompt,
-                    "tools": tools,
-                    "tool_choice": "auto",
-                    "tool_prompt_format": "json",
-                    "input_shields": [],
-                    "output_shields": [],
-                    "enable_session_persistence": False,
-                },
-            }
-        st.session_state["eval_candidate"] = eval_candidate
-
-    if st.button("Confirm", key="confirm_2"):
-        st.session_state["selected_eval_candidate_2_next"] = True
-
-
-def run_evaluation_3():
-    if not st.session_state.get("selected_eval_candidate_2_next", None):
-        return
-
-    st.subheader("3. Run Evaluation")
-    # Add info box to explain configurations being used
-    st.info(
-        """
-        Review the configurations that will be used for this evaluation run, make any necessary changes, and then click the "Run Evaluation" button.
-        """
-    )
-    selected_benchmark = st.session_state["selected_benchmark"]
-    benchmarks = st.session_state["benchmarks"]
-    eval_candidate = st.session_state["eval_candidate"]
-
-    dataset_id = benchmarks[selected_benchmark].dataset_id
-    rows = llama_stack_api.client.datasets.iterrows(
-        dataset_id=dataset_id,
-    )
-    total_rows = len(rows.data)
-    # Add number of examples control
-    num_rows = st.number_input(
-        "Number of Examples to Evaluate",
-        min_value=1,
-        max_value=total_rows,
-        value=5,
-        help="Number of examples from the dataset to evaluate. ",
-    )
-
-    benchmark_config = {
-        "type": "benchmark",
-        "eval_candidate": eval_candidate,
-        "scoring_params": {},
-    }
-
-    with st.expander("View Evaluation Task", expanded=True):
-        st.json(benchmarks[selected_benchmark], expanded=True)
-    with st.expander("View Evaluation Task Configuration", expanded=True):
-        st.json(benchmark_config, expanded=True)
-
-    # Add run button and handle evaluation
-    if st.button("Run Evaluation"):
-        progress_text = "Running evaluation..."
-        progress_bar = st.progress(0, text=progress_text)
-        rows = rows.data
-        if num_rows < total_rows:
-            rows = rows[:num_rows]
-
-        # Create separate containers for progress text and results
-        progress_text_container = st.empty()
-        results_container = st.empty()
-        output_res = {}
-        for i, r in enumerate(rows):
-            # Update progress
-            progress = i / len(rows)
-            progress_bar.progress(progress, text=progress_text)
-            # Run evaluation for current row
-            eval_res = llama_stack_api.client.eval.evaluate_rows(
-                benchmark_id=selected_benchmark,
-                input_rows=[r],
-                scoring_functions=benchmarks[selected_benchmark].scoring_functions,
-                benchmark_config=benchmark_config,
-            )
-
-            for k in r.keys():
-                if k not in output_res:
-                    output_res[k] = []
-                output_res[k].append(r[k])
-
-            for k in eval_res.generations[0].keys():
-                if k not in output_res:
-                    output_res[k] = []
-                output_res[k].append(eval_res.generations[0][k])
-
-            for scoring_fn in benchmarks[selected_benchmark].scoring_functions:
-                if scoring_fn not in output_res:
-                    output_res[scoring_fn] = []
-                output_res[scoring_fn].append(eval_res.scores[scoring_fn].score_rows[0])
-
-            progress_text_container.write(f"Expand to see current processed result ({i + 1} / {len(rows)})")
-            results_container.json(eval_res, expanded=2)
-
-        progress_bar.progress(1.0, text="Evaluation complete!")
-        # Display results in dataframe
-        if output_res:
-            output_df = pd.DataFrame(output_res)
-            st.subheader("Evaluation Results")
-            st.dataframe(output_df)
-
-
-def native_evaluation_page():
-    st.set_page_config(page_title="Evaluations (Generation + Scoring)", page_icon="🦙")
-    st.title("📊 Evaluations (Generation + Scoring)")
-
-    select_benchmark_1()
-    define_eval_candidate_2()
-    run_evaluation_3()
-
-
-native_evaluation_page()

llama_stack/core/ui/page/playground/__init__.py

@@ -1,5 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.