Spaces:
Running
Running
Commit ·
e9c63c4
1
Parent(s): 428aa76
Use free open models via Hugging Face Inference Providers with Sign in with Hugging Face; credit DevRubenArevalo
Browse files- .env.example +3 -4
- LIVE_COPY_FIXES.md +4 -3
- README.md +23 -4
- app.py +95 -43
- requirements.txt +1 -2
- test_api.py +17 -18
.env.example
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
# Optional:
|
| 3 |
-
#
|
| 4 |
-
# ANTHROPIC_MODEL=claude-haiku-5-5
|
|
|
|
| 1 |
+
# The Gradio app needs no API key: visitors sign in with Hugging Face and use their own free allowance.
|
| 2 |
+
# Optional: choose a different open chat model served by HF Inference Providers.
|
| 3 |
+
# HEALIXPATH_MODEL=openai/gpt-oss-20b
|
|
|
LIVE_COPY_FIXES.md
CHANGED
|
@@ -5,9 +5,10 @@ Do not push these to MCP-1st-Birthday/TeamHealix.
|
|
| 5 |
Changes vs the November 2025 submission:
|
| 6 |
- Pin Python deps so a fresh Space build is reproducible.
|
| 7 |
- Install `gradio[mcp]==5.49.1` and launch with `mcp_server=True` so the
|
| 8 |
-
MCP endpoint is `https://
|
| 9 |
-
-
|
| 10 |
-
|
|
|
|
| 11 |
- Remove an unused `subprocess` import.
|
| 12 |
|
| 13 |
The TypeScript MCP server under `src/` is a local demo (no official MCP
|
|
|
|
| 5 |
Changes vs the November 2025 submission:
|
| 6 |
- Pin Python deps so a fresh Space build is reproducible.
|
| 7 |
- Install `gradio[mcp]==5.49.1` and launch with `mcp_server=True` so the
|
| 8 |
+
MCP endpoint is `https://mackenzietechdocs-healixpath.hf.space/gradio_api/mcp/`.
|
| 9 |
+
- AI backend: the Anthropic client was removed. Generation uses open models through
|
| 10 |
+
Hugging Face Inference Providers with each visitor's own token (Sign in with Hugging Face),
|
| 11 |
+
so no API key or Space secret is needed. (The original model, `claude-3-haiku-20240307`, was retired on 20 April 2026.)
|
| 12 |
- Remove an unused `subprocess` import.
|
| 13 |
|
| 14 |
The TypeScript MCP server under `src/` is a local demo (no official MCP
|
README.md
CHANGED
|
@@ -7,6 +7,9 @@ sdk: gradio
|
|
| 7 |
sdk_version: 5.49.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: true
|
|
|
|
|
|
|
|
|
|
| 10 |
short_description: AI-powered persona storytelling engine for enterprise.
|
| 11 |
tags:
|
| 12 |
- mcp-hackathon
|
|
@@ -24,7 +27,23 @@ tags:
|
|
| 24 |
|
| 25 |
## About The Team
|
| 26 |
|
| 27 |
-
[@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
|
| 30 |
## The Posts
|
|
@@ -53,7 +72,7 @@ Designed to help product teams feel their users, not just document them.
|
|
| 53 |
|
| 54 |
## 🛠️ 2. MCP-Compatible Tools
|
| 55 |
|
| 56 |
-
Each tool is exposed through the MCP server (`src/index.ts`) and powered by
|
| 57 |
|
| 58 |
### 1. `list_personas`
|
| 59 |
Lists all available personas with their key attributes.
|
|
@@ -336,12 +355,12 @@ healixpath/
|
|
| 336 |
|
| 337 |
### Node.js MCP Server
|
| 338 |
```bash
|
| 339 |
-
cp .env.example .env #
|
| 340 |
npm install
|
| 341 |
npm run build
|
| 342 |
npm run start
|
| 343 |
```
|
| 344 |
-
`src/index.ts` boots the HealixPath MCP server, enumerates tools, and shows sample tool calls.
|
| 345 |
|
| 346 |
### Gradio Demo
|
| 347 |
```bash
|
|
|
|
| 7 |
sdk_version: 5.49.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: true
|
| 10 |
+
hf_oauth: true
|
| 11 |
+
hf_oauth_scopes:
|
| 12 |
+
- inference-api
|
| 13 |
short_description: AI-powered persona storytelling engine for enterprise.
|
| 14 |
tags:
|
| 15 |
- mcp-hackathon
|
|
|
|
| 27 |
|
| 28 |
## About The Team
|
| 29 |
|
| 30 |
+
HealixPath was built by **Mackenzie O'Brien** ([@mackenzietechdocs](https://huggingface.co/mackenzietechdocs), [GitHub](https://github.com/mso-docs)) and **co-author @DevRubenArevalo** ([Hugging Face](https://huggingface.co/DevRubenArevalo), [GitHub](https://github.com/DevRubenArevalo)). Together we are Team Healix, a two-person dev team looking to make robust AI applications for everyone.
|
| 31 |
+
|
| 32 |
+
The official November 2025 hackathon submission lives at [MCP-1st-Birthday/TeamHealix](https://huggingface.co/spaces/MCP-1st-Birthday/TeamHealix) and is kept unchanged. This Space is the live, maintained copy.
|
| 33 |
+
|
| 34 |
+
## Sign in with Hugging Face (free AI, no API key)
|
| 35 |
+
|
| 36 |
+
This live copy no longer uses any paid API key. Text generation runs on open models through [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers), using **your own** Hugging Face account:
|
| 37 |
+
|
| 38 |
+
1. Click **Sign in with Hugging Face** at the top of the app and approve the `inference-api` permission.
|
| 39 |
+
2. Generate stories, journeys, and personas. Each request is billed to your account's free monthly Inference Providers allowance. If you run out, Hugging Face will tell you; PRO accounts get a larger allowance.
|
| 40 |
+
3. Signed-out visitors can browse and search personas, but generation shows a "please sign in" message. The Space never falls back to its owner's token or any secret.
|
| 41 |
+
|
| 42 |
+
Model: [`openai/gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) (open weights, Apache 2.0, instruction-tuned). When running your own copy, set the `HEALIXPATH_MODEL` environment variable to any chat model served by Inference Providers.
|
| 43 |
+
|
| 44 |
+
**MCP clients:** the Gradio MCP endpoint is `https://mackenzietechdocs-healixpath.hf.space/gradio_api/mcp/`. Tools that generate text need a Hugging Face token with the "Make calls to Inference Providers" permission; send it as `Authorization: Bearer <your token>`.
|
| 45 |
+
|
| 46 |
+
**Running locally:** `pip install -r requirements.txt && python app.py`. Local OAuth sign-in needs a Space; the app does not read `HF_TOKEN`. Duplicate the Space to your account to get your own copy with sign-in enabled.
|
| 47 |
|
| 48 |
|
| 49 |
## The Posts
|
|
|
|
| 72 |
|
| 73 |
## 🛠️ 2. MCP-Compatible Tools
|
| 74 |
|
| 75 |
+
Each tool is exposed through the MCP server (`src/index.ts`) and powered by open models via Hugging Face Inference Providers in the Gradio app (the original hackathon build used Claude). Prompts request JSON-only output.
|
| 76 |
|
| 77 |
### 1. `list_personas`
|
| 78 |
Lists all available personas with their key attributes.
|
|
|
|
| 355 |
|
| 356 |
### Node.js MCP Server
|
| 357 |
```bash
|
| 358 |
+
cp .env.example .env # optional: only the original local Node demo used an Anthropic key
|
| 359 |
npm install
|
| 360 |
npm run build
|
| 361 |
npm run start
|
| 362 |
```
|
| 363 |
+
`src/index.ts` boots the HealixPath MCP server, enumerates tools, and shows sample tool calls. This local TypeScript demo is the original hackathon prototype; the live Gradio app does not use it.
|
| 364 |
|
| 365 |
### Gradio Demo
|
| 366 |
```bash
|
app.py
CHANGED
|
@@ -7,9 +7,10 @@ A web interface for generating AI-powered persona-driven narratives.
|
|
| 7 |
import gradio as gr
|
| 8 |
import json
|
| 9 |
import os
|
|
|
|
| 10 |
from pathlib import Path
|
| 11 |
from dotenv import load_dotenv
|
| 12 |
-
from
|
| 13 |
|
| 14 |
# Modern CSS styling
|
| 15 |
CUSTOM_CSS = """
|
|
@@ -540,10 +541,17 @@ persona_list = list(persona_options.keys())
|
|
| 540 |
persona_choices = [CUSTOM_PERSONA_LABEL] + persona_list
|
| 541 |
default_persona_choice = persona_list[0] if persona_list else CUSTOM_PERSONA_LABEL
|
| 542 |
|
| 543 |
-
#
|
| 544 |
-
|
| 545 |
-
|
| 546 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 547 |
|
| 548 |
def get_persona_context(persona_id: str, custom_persona: str = "") -> str:
|
| 549 |
"""Format persona data for prompt context."""
|
|
@@ -630,32 +638,59 @@ def toggle_custom_persona(selected_value: str):
|
|
| 630 |
show_custom = selected_value == CUSTOM_PERSONA_LABEL
|
| 631 |
return gr.update(visible=show_custom, value="" if not show_custom else None)
|
| 632 |
|
| 633 |
-
def
|
| 634 |
-
"""
|
| 635 |
-
|
| 636 |
-
|
| 637 |
-
|
| 638 |
-
|
| 639 |
-
|
| 640 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 641 |
try:
|
| 642 |
-
|
| 643 |
-
|
| 644 |
-
|
| 645 |
-
system=system_prompt,
|
| 646 |
messages=[
|
| 647 |
-
{"role": "
|
| 648 |
-
|
|
|
|
|
|
|
|
|
|
| 649 |
)
|
| 650 |
-
return
|
| 651 |
except Exception as e:
|
| 652 |
return json.dumps({
|
| 653 |
-
"error":
|
| 654 |
-
"message":
|
| 655 |
}, indent=2)
|
| 656 |
|
| 657 |
-
def generate_user_story(product: str, persona_name: str, persona_override: str
|
|
|
|
| 658 |
"""Generate a user story for the given product and persona(s)."""
|
|
|
|
| 659 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 660 |
|
| 661 |
system_prompt = """You are an expert UX writer and product strategist.
|
|
@@ -674,7 +709,7 @@ Generate a user story for this persona using the product: {product}
|
|
| 674 |
|
| 675 |
Format as JSON with the keys: story, acceptance_criteria (array), risks (array)"""
|
| 676 |
|
| 677 |
-
response =
|
| 678 |
try:
|
| 679 |
data = json.loads(response)
|
| 680 |
if len(persona_contexts) > 1:
|
|
@@ -685,8 +720,10 @@ Format as JSON with the keys: story, acceptance_criteria (array), risks (array)"
|
|
| 685 |
|
| 686 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 687 |
|
| 688 |
-
def generate_experience_tale(problem: str, persona_name: str, persona_override: str
|
|
|
|
| 689 |
"""Generate a customer experience tale."""
|
|
|
|
| 690 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 691 |
|
| 692 |
system_prompt = """You are an expert in customer experience and user research.
|
|
@@ -706,7 +743,7 @@ Describe how this persona experiences this problem: {problem}
|
|
| 706 |
|
| 707 |
Format as JSON with keys: title, narrative, pain_points (array), opportunities (array)"""
|
| 708 |
|
| 709 |
-
response =
|
| 710 |
try:
|
| 711 |
data = json.loads(response)
|
| 712 |
if len(persona_contexts) > 1:
|
|
@@ -717,8 +754,10 @@ Format as JSON with keys: title, narrative, pain_points (array), opportunities (
|
|
| 717 |
|
| 718 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 719 |
|
| 720 |
-
def generate_feature_impact(feature: str, persona_name: str, persona_override: str
|
|
|
|
| 721 |
"""Generate a before/after feature impact story."""
|
|
|
|
| 722 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 723 |
|
| 724 |
system_prompt = """You are an expert at showing product impact through user narratives.
|
|
@@ -738,7 +777,7 @@ Show the before/after impact of this feature on the persona's experience: {featu
|
|
| 738 |
|
| 739 |
Format as JSON with keys: before_story, after_story, key_benefits (array), success_metrics (array)"""
|
| 740 |
|
| 741 |
-
response =
|
| 742 |
try:
|
| 743 |
data = json.loads(response)
|
| 744 |
if len(persona_contexts) > 1:
|
|
@@ -749,8 +788,10 @@ Format as JSON with keys: before_story, after_story, key_benefits (array), succe
|
|
| 749 |
|
| 750 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 751 |
|
| 752 |
-
def generate_journey_story(stage: str, product: str, persona_name: str, persona_override: str
|
|
|
|
| 753 |
"""Generate a journey map narrative."""
|
|
|
|
| 754 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 755 |
|
| 756 |
system_prompt = """You are an expert in customer journey mapping and experience design.
|
|
@@ -772,7 +813,7 @@ Describe this persona's experience at the '{stage}' stage of their journey with
|
|
| 772 |
|
| 773 |
Format as JSON with keys: stage, narrative, touchpoints (array), emotions (array), breakdowns (array), opportunities (array)"""
|
| 774 |
|
| 775 |
-
response =
|
| 776 |
try:
|
| 777 |
data = json.loads(response)
|
| 778 |
if len(persona_contexts) > 1:
|
|
@@ -865,16 +906,18 @@ def show_persona_details(persona_index: int):
|
|
| 865 |
return json.dumps(p, indent=2)
|
| 866 |
return "Persona not found"
|
| 867 |
|
| 868 |
-
def generate_personas_func(description: str, count: int
|
| 869 |
-
|
|
|
|
|
|
|
| 870 |
if not description or not description.strip():
|
| 871 |
return json.dumps({"error": "Please provide a description"}, indent=2)
|
| 872 |
|
| 873 |
if count < 1 or count > 5:
|
| 874 |
return json.dumps({"error": "Count must be between 1 and 5"}, indent=2)
|
| 875 |
|
| 876 |
-
if not
|
| 877 |
-
return json.dumps({"error": "
|
| 878 |
|
| 879 |
system_prompt = """You are a persona generation expert. Generate realistic, diverse user personas based on the provided description.
|
| 880 |
|
|
@@ -952,14 +995,10 @@ Requirements:
|
|
| 952 |
Return format: [persona1, persona2, ...]"""
|
| 953 |
|
| 954 |
try:
|
| 955 |
-
|
| 956 |
-
|
| 957 |
-
|
| 958 |
-
|
| 959 |
-
)
|
| 960 |
-
|
| 961 |
-
response_text = response.content[0].text if response.content else ""
|
| 962 |
-
|
| 963 |
# Clean up response (remove markdown code blocks if present)
|
| 964 |
cleaned_response = response_text.strip()
|
| 965 |
if cleaned_response.startswith("```json"):
|
|
@@ -989,6 +1028,19 @@ with gr.Blocks(title="HealixPath - AI Persona Storytelling", css=CUSTOM_CSS) as
|
|
| 989 |
"""
|
| 990 |
)
|
| 991 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 992 |
gr.HTML(
|
| 993 |
"""
|
| 994 |
<div class="card-container" style="margin-bottom: 26px;">
|
|
@@ -1259,7 +1311,7 @@ with gr.Blocks(title="HealixPath - AI Persona Storytelling", css=CUSTOM_CSS) as
|
|
| 1259 |
<div style="text-align: center; margin-top: 32px; padding: 16px; border-top: 1px solid var(--line); color: var(--text-dim);">
|
| 1260 |
<p style="font-size: 13px; margin: 0;">
|
| 1261 |
HealixPath - AI-powered persona storytelling engine<br>
|
| 1262 |
-
<span style="color: var(--muted);">
|
| 1263 |
</p>
|
| 1264 |
</div>
|
| 1265 |
"""
|
|
|
|
| 7 |
import gradio as gr
|
| 8 |
import json
|
| 9 |
import os
|
| 10 |
+
import re
|
| 11 |
from pathlib import Path
|
| 12 |
from dotenv import load_dotenv
|
| 13 |
+
from huggingface_hub import InferenceClient
|
| 14 |
|
| 15 |
# Modern CSS styling
|
| 16 |
CUSTOM_CSS = """
|
|
|
|
| 541 |
persona_choices = [CUSTOM_PERSONA_LABEL] + persona_list
|
| 542 |
default_persona_choice = persona_list[0] if persona_list else CUSTOM_PERSONA_LABEL
|
| 543 |
|
| 544 |
+
# Free AI backend: Hugging Face Inference Providers.
|
| 545 |
+
# Every generation runs on the *visitor's* Hugging Face account (Sign in with Hugging Face),
|
| 546 |
+
# so it uses the visitor's own free monthly allowance. The Space never uses its own token,
|
| 547 |
+
# a Space secret, or a paid API key for inference.
|
| 548 |
+
MODEL = os.getenv("HEALIXPATH_MODEL", "openai/gpt-oss-20b")
|
| 549 |
+
|
| 550 |
+
SIGN_IN_MESSAGE = (
|
| 551 |
+
"Please sign in with Hugging Face (button at the top of the page) to generate. "
|
| 552 |
+
"Generations use your own free Hugging Face Inference Providers allowance."
|
| 553 |
+
)
|
| 554 |
+
|
| 555 |
|
| 556 |
def get_persona_context(persona_id: str, custom_persona: str = "") -> str:
|
| 557 |
"""Format persona data for prompt context."""
|
|
|
|
| 638 |
show_custom = selected_value == CUSTOM_PERSONA_LABEL
|
| 639 |
return gr.update(visible=show_custom, value="" if not show_custom else None)
|
| 640 |
|
| 641 |
+
def resolve_token(oauth_token=None, request=None):
|
| 642 |
+
"""Return the visitor's own Hugging Face token, or None.
|
| 643 |
+
|
| 644 |
+
Order: the OAuth token from "Sign in with Hugging Face", then a Bearer token the
|
| 645 |
+
caller sent in the Authorization header (for MCP clients that pass their own token).
|
| 646 |
+
Never falls back to a Space-level token or secret.
|
| 647 |
+
"""
|
| 648 |
+
token = getattr(oauth_token, "token", None)
|
| 649 |
+
if token:
|
| 650 |
+
return token
|
| 651 |
+
try:
|
| 652 |
+
auth = request.headers.get("authorization", "") if request is not None else ""
|
| 653 |
+
except Exception:
|
| 654 |
+
auth = ""
|
| 655 |
+
if auth.lower().startswith("bearer ") and auth[7:].strip():
|
| 656 |
+
return auth[7:].strip()
|
| 657 |
+
return None
|
| 658 |
+
|
| 659 |
+
|
| 660 |
+
def _strip_code_fence(text: str) -> str:
|
| 661 |
+
text = (text or "").strip()
|
| 662 |
+
if text.startswith("```"):
|
| 663 |
+
text = re.sub(r"^```[a-zA-Z]*\s*", "", text)
|
| 664 |
+
text = re.sub(r"\s*```$", "", text).strip()
|
| 665 |
+
return text
|
| 666 |
+
|
| 667 |
+
|
| 668 |
+
def generate_text(system_prompt: str, user_prompt: str, token, max_tokens: int = 1500) -> str:
|
| 669 |
+
"""Call an open model through HF Inference Providers with the visitor's token."""
|
| 670 |
+
if not token:
|
| 671 |
+
return json.dumps({"error": "Sign in required", "message": SIGN_IN_MESSAGE}, indent=2)
|
| 672 |
try:
|
| 673 |
+
client = InferenceClient(api_key=token)
|
| 674 |
+
result = client.chat_completion(
|
| 675 |
+
model=MODEL,
|
|
|
|
| 676 |
messages=[
|
| 677 |
+
{"role": "system", "content": system_prompt},
|
| 678 |
+
{"role": "user", "content": user_prompt},
|
| 679 |
+
],
|
| 680 |
+
max_tokens=max_tokens,
|
| 681 |
+
temperature=0.7,
|
| 682 |
)
|
| 683 |
+
return _strip_code_fence(result.choices[0].message.content or "")
|
| 684 |
except Exception as e:
|
| 685 |
return json.dumps({
|
| 686 |
+
"error": type(e).__name__,
|
| 687 |
+
"message": f"Hugging Face Inference Providers call failed: {e}",
|
| 688 |
}, indent=2)
|
| 689 |
|
| 690 |
+
def generate_user_story(product: str, persona_name: str, persona_override: str,
|
| 691 |
+
oauth_token: gr.OAuthToken | None = None, request: gr.Request = None):
|
| 692 |
"""Generate a user story for the given product and persona(s)."""
|
| 693 |
+
token = resolve_token(oauth_token, request)
|
| 694 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 695 |
|
| 696 |
system_prompt = """You are an expert UX writer and product strategist.
|
|
|
|
| 709 |
|
| 710 |
Format as JSON with the keys: story, acceptance_criteria (array), risks (array)"""
|
| 711 |
|
| 712 |
+
response = generate_text(system_prompt, user_prompt, token)
|
| 713 |
try:
|
| 714 |
data = json.loads(response)
|
| 715 |
if len(persona_contexts) > 1:
|
|
|
|
| 720 |
|
| 721 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 722 |
|
| 723 |
+
def generate_experience_tale(problem: str, persona_name: str, persona_override: str,
|
| 724 |
+
oauth_token: gr.OAuthToken | None = None, request: gr.Request = None):
|
| 725 |
"""Generate a customer experience tale."""
|
| 726 |
+
token = resolve_token(oauth_token, request)
|
| 727 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 728 |
|
| 729 |
system_prompt = """You are an expert in customer experience and user research.
|
|
|
|
| 743 |
|
| 744 |
Format as JSON with keys: title, narrative, pain_points (array), opportunities (array)"""
|
| 745 |
|
| 746 |
+
response = generate_text(system_prompt, user_prompt, token)
|
| 747 |
try:
|
| 748 |
data = json.loads(response)
|
| 749 |
if len(persona_contexts) > 1:
|
|
|
|
| 754 |
|
| 755 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 756 |
|
| 757 |
+
def generate_feature_impact(feature: str, persona_name: str, persona_override: str,
|
| 758 |
+
oauth_token: gr.OAuthToken | None = None, request: gr.Request = None):
|
| 759 |
"""Generate a before/after feature impact story."""
|
| 760 |
+
token = resolve_token(oauth_token, request)
|
| 761 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 762 |
|
| 763 |
system_prompt = """You are an expert at showing product impact through user narratives.
|
|
|
|
| 777 |
|
| 778 |
Format as JSON with keys: before_story, after_story, key_benefits (array), success_metrics (array)"""
|
| 779 |
|
| 780 |
+
response = generate_text(system_prompt, user_prompt, token)
|
| 781 |
try:
|
| 782 |
data = json.loads(response)
|
| 783 |
if len(persona_contexts) > 1:
|
|
|
|
| 788 |
|
| 789 |
return json.dumps(results if len(results) > 1 else results[0], indent=2)
|
| 790 |
|
| 791 |
+
def generate_journey_story(stage: str, product: str, persona_name: str, persona_override: str,
|
| 792 |
+
oauth_token: gr.OAuthToken | None = None, request: gr.Request = None):
|
| 793 |
"""Generate a journey map narrative."""
|
| 794 |
+
token = resolve_token(oauth_token, request)
|
| 795 |
_, persona_contexts = build_persona_profile(persona_name, persona_override)
|
| 796 |
|
| 797 |
system_prompt = """You are an expert in customer journey mapping and experience design.
|
|
|
|
| 813 |
|
| 814 |
Format as JSON with keys: stage, narrative, touchpoints (array), emotions (array), breakdowns (array), opportunities (array)"""
|
| 815 |
|
| 816 |
+
response = generate_text(system_prompt, user_prompt, token)
|
| 817 |
try:
|
| 818 |
data = json.loads(response)
|
| 819 |
if len(persona_contexts) > 1:
|
|
|
|
| 906 |
return json.dumps(p, indent=2)
|
| 907 |
return "Persona not found"
|
| 908 |
|
| 909 |
+
def generate_personas_func(description: str, count: int,
|
| 910 |
+
oauth_token: gr.OAuthToken | None = None, request: gr.Request = None):
|
| 911 |
+
"""Generate random personas based on description using an open model via Hugging Face."""
|
| 912 |
+
token = resolve_token(oauth_token, request)
|
| 913 |
if not description or not description.strip():
|
| 914 |
return json.dumps({"error": "Please provide a description"}, indent=2)
|
| 915 |
|
| 916 |
if count < 1 or count > 5:
|
| 917 |
return json.dumps({"error": "Count must be between 1 and 5"}, indent=2)
|
| 918 |
|
| 919 |
+
if not token:
|
| 920 |
+
return json.dumps({"error": "Sign in required", "message": SIGN_IN_MESSAGE}, indent=2)
|
| 921 |
|
| 922 |
system_prompt = """You are a persona generation expert. Generate realistic, diverse user personas based on the provided description.
|
| 923 |
|
|
|
|
| 995 |
Return format: [persona1, persona2, ...]"""
|
| 996 |
|
| 997 |
try:
|
| 998 |
+
response_text = generate_text(system_prompt, user_prompt, token, max_tokens=4096)
|
| 999 |
+
if response_text.lstrip().startswith("{") and '"error"' in response_text[:40]:
|
| 1000 |
+
return response_text
|
| 1001 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1002 |
# Clean up response (remove markdown code blocks if present)
|
| 1003 |
cleaned_response = response_text.strip()
|
| 1004 |
if cleaned_response.startswith("```json"):
|
|
|
|
| 1028 |
"""
|
| 1029 |
)
|
| 1030 |
|
| 1031 |
+
with gr.Row():
|
| 1032 |
+
gr.LoginButton(value="Sign in with Hugging Face")
|
| 1033 |
+
signin_status = gr.Markdown(
|
| 1034 |
+
"**Signed out.** " + SIGN_IN_MESSAGE
|
| 1035 |
+
)
|
| 1036 |
+
|
| 1037 |
+
def show_signin_status(profile: gr.OAuthProfile | None):
|
| 1038 |
+
if profile is None:
|
| 1039 |
+
return "**Signed out.** " + SIGN_IN_MESSAGE
|
| 1040 |
+
return f"**Signed in as {profile.username}.** Generations use your own free Hugging Face allowance."
|
| 1041 |
+
|
| 1042 |
+
demo.load(show_signin_status, inputs=None, outputs=signin_status)
|
| 1043 |
+
|
| 1044 |
gr.HTML(
|
| 1045 |
"""
|
| 1046 |
<div class="card-container" style="margin-bottom: 26px;">
|
|
|
|
| 1311 |
<div style="text-align: center; margin-top: 32px; padding: 16px; border-top: 1px solid var(--line); color: var(--text-dim);">
|
| 1312 |
<p style="font-size: 13px; margin: 0;">
|
| 1313 |
HealixPath - AI-powered persona storytelling engine<br>
|
| 1314 |
+
<span style="color: var(--muted);">Open models via Hugging Face Inference Providers & Gradio</span>
|
| 1315 |
</p>
|
| 1316 |
</div>
|
| 1317 |
"""
|
requirements.txt
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
gradio[mcp]==5.49.1
|
| 2 |
-
anthropic==2.8.0
|
| 3 |
pydantic==2.11.10
|
| 4 |
python-dotenv==1.2.4
|
|
|
|
| 1 |
+
gradio[mcp,oauth]==5.49.1
|
|
|
|
| 2 |
pydantic==2.11.10
|
| 3 |
python-dotenv==1.2.4
|
test_api.py
CHANGED
|
@@ -1,28 +1,27 @@
|
|
| 1 |
#!/usr/bin/env python3
|
| 2 |
-
|
| 3 |
-
from dotenv import load_dotenv
|
| 4 |
-
from anthropic import Anthropic
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
print(f
|
|
|
|
| 13 |
|
| 14 |
-
if
|
| 15 |
try:
|
| 16 |
-
|
| 17 |
-
response = client.messages.create(
|
| 18 |
model=model,
|
|
|
|
| 19 |
max_tokens=100,
|
| 20 |
-
messages=[{'role': 'user', 'content': 'Say hello'}]
|
| 21 |
)
|
| 22 |
-
print(
|
| 23 |
-
print(f
|
| 24 |
except Exception as e:
|
| 25 |
-
print(f
|
| 26 |
-
print(f
|
| 27 |
else:
|
| 28 |
-
print('
|
|
|
|
| 1 |
#!/usr/bin/env python3
|
| 2 |
+
"""Dev-only smoke test: calls the HealixPath model with a token you supply via HF_TOKEN.
|
|
|
|
|
|
|
| 3 |
|
| 4 |
+
The app itself never reads HF_TOKEN; visitors sign in with Hugging Face instead.
|
| 5 |
+
"""
|
| 6 |
+
import os
|
| 7 |
+
from huggingface_hub import InferenceClient
|
| 8 |
|
| 9 |
+
model = os.getenv("HEALIXPATH_MODEL", "openai/gpt-oss-20b")
|
| 10 |
+
token = os.getenv("HF_TOKEN")
|
| 11 |
+
print(f"Model: {model}")
|
| 12 |
+
print(f"HF_TOKEN set: {bool(token)}")
|
| 13 |
|
| 14 |
+
if token:
|
| 15 |
try:
|
| 16 |
+
result = InferenceClient(api_key=token).chat_completion(
|
|
|
|
| 17 |
model=model,
|
| 18 |
+
messages=[{"role": "user", "content": "Say hello"}],
|
| 19 |
max_tokens=100,
|
|
|
|
| 20 |
)
|
| 21 |
+
print("API call successful")
|
| 22 |
+
print(f"Response: {result.choices[0].message.content}")
|
| 23 |
except Exception as e:
|
| 24 |
+
print(f"API error: {type(e).__name__}")
|
| 25 |
+
print(f"Message: {e}")
|
| 26 |
else:
|
| 27 |
+
print("Set HF_TOKEN (needs the 'Make calls to Inference Providers' permission) to run this check.")
|