add readme

README.md

@@ -1,3 +1,17 @@
+---
+title: ClaimCheck.AI - Agentic Fact Verification
+emoji: 🔍
+colorFrom: blue
+colorTo: green
+sdk: docker
+sdk_version: "4.36.0"
+app_file: app/main.py
+pinned: false
+license: mit
+python_version: 3.9
+suggested_hardware: cpu-basic
+---
+
 # ClaimCheck.AI — Agentic Fact Verification for Calls
 
 **ClaimCheck.AI** is an multi-agent AI platform that turns meeting audio (Zoom/phone) into an evidence-backed report:
@@ -10,7 +24,6 @@
 ## ✨ Why it matters
 
 High-stakes calls contain promises and metrics (SLA, compliance, finance). ClaimCheck.AI verifies statements against your **trusted KB** so decisions are grounded in facts—not memory.
-git branch -M main
 
 ---
 
@@ -43,24 +56,15 @@ claim-check/
 
 ---
 
-## 🧪 Quick start
+## 🚀 Deploy on Hugging Face Spaces
 
-### 1) Python env
-```bash
-python -m venv .venv
-source .venv/bin/activate
-pip install -r requirements.txt
-```
+This app is configured to run on Hugging Face Spaces. The configuration header at the top of this README handles the deployment settings.
 
-### 2) Configure IBM (edit `.env`)
-Copy the sample and fill in values from your IBM Cloud / watsonx project.
+### Environment Variables for Spaces
 
-```bash
-cp .env.sample .env
-```
+You'll need to set these secrets in your Hugging Face Space settings:
 
-**Required env keys:**
-```
+```bash
 # IBM Core
 WATSONX_BASE_URL=https://us-south.ml.cloud.ibm.com
 WATSONX_PROJECT_ID=<your-watsonx-project-id>
@@ -68,14 +72,14 @@ WATSONX_API_KEY=<your-ibm-cloud-api-key>
 IBM_API_VERSION=2023-05-29
 
 # Models
-IBM_EMBEDDINGS_MODEL_ID=ibm/granite-embedding-107m-multilingual   # 384-dim
-IBM_RERANK_MODEL_ID=ibm/slate-30m-english-rtrvr-v2                 # optional
+IBM_EMBEDDINGS_MODEL_ID=ibm/granite-embedding-107m-multilingual
+IBM_RERANK_MODEL_ID=ibm/slate-30m-english-rtrvr-v2
 IBM_VERIFIER_MODEL_ID=ibm/granite-3-8b-instruct
 IBM_SUMMARY_MODEL_ID=ibm/granite-3-8b-instruct
 IBM_CLAIM_MODEL_ID=ibm/granite-3-8b-instruct
 
 # Speech to Text (IBM)
-IBM_STT_URL=<your-ibm-stt-instance-url>   # e.g. https://api.us-south.speech-to-text.watson.cloud.ibm.com/instances/XXXX
+IBM_STT_URL=<your-ibm-stt-instance-url>
 IBM_STT_APIKEY=<your-ibm-stt-api-key>
 
 # Whisper fallback (optional)
@@ -84,6 +88,24 @@ WHISPER_DEVICE=cpu
 WHISPER_COMPUTE_TYPE=int8
 ```
 
+---
+
+## 🧪 Quick start (Local Development)
+
+### 1) Python env
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+### 2) Configure IBM (edit `.env`)
+Copy the sample and fill in values from your IBM Cloud / watsonx project.
+
+```bash
+cp .env.sample .env
+```
+
 ### 3) Seed the KB
 Put your facts in `kb/snippets.jsonl` (one JSON per line). Example:
 
@@ -95,10 +117,10 @@ If you change the KB, rebuild the index by deleting the `kb/index/` folder.
 
 ### 4) Run the API
 ```bash
-uvicorn app.main:app --reload
+uvicorn app.main:app --reload --host 0.0.0.0 --port 7860
 ```
 
-### 5) Run the UI
+### 5) Run the UI (Local Only)
 ```bash
 cd ui/claimcheck-ui
 pnpm install
@@ -110,17 +132,20 @@ pnpm dev
 
 **Transcript path (no audio):**
 ```bash
-curl -X POST http://127.0.0.1:8000/process-transcript   -H "Content-Type: application/json"   -d '{"text":"We achieved 99.99% uptime in Q2. P95 latency under 200 ms globally. Default retention is 30 days."}'
+curl -X POST http://127.0.0.1:7860/process-transcript \
+  -H "Content-Type: application/json" \
+  -d '{"text":"We achieved 99.99% uptime in Q2. P95 latency under 200 ms globally. Default retention is 30 days."}'
 ```
 
 **Audio path (IBM STT):**
 ```bash
-curl -X POST http://127.0.0.1:8000/process-audio   -F "file=@data/audio/demo_call.wav"
+curl -X POST http://127.0.0.1:7860/process-audio \
+  -F "file=@data/audio/demo_call.wav"
 ```
 
 **Health:**
 ```bash
-curl http://127.0.0.1:8000/health/ibm
+curl http://127.0.0.1:7860/health/ibm
 ```
 
 ---
@@ -139,7 +164,6 @@ ClaimCheck.AI combines modern **agentic AI** orchestration with core NLP, IR, an
 | Verifier      | Evaluate support/refute status       | `granite-3-8b-instruct`                       | Fact Verification, Retrieval-Augmented Generation (RAG) |
 | Summarizer    | Generate exec summary + action items | `granite-3-8b-instruct`                       | Abstractive Summarization, Plan Extraction |
 
-
 ---
 
 ## 🛡️ Notes on data & security
@@ -156,7 +180,16 @@ ClaimCheck.AI combines modern **agentic AI** orchestration with core NLP, IR, an
 - **JSON parse errors** → we use a robust extractor; check server logs `[RAW OUTPUT]`.
 - **Rebuild index** → Incorrect evidence showing up in the evidence drawer
 ```bash
- rm -f kb/index/kb.index kb/index/kb_meta.json
+rm -f kb/index/kb.index kb/index/kb_meta.json
 python -c "from app.agents.retriever import _build_or_load; _build_or_load(); print('rebuild done')"
 ```
 
+---
+
+## 📄 License
+
+MIT License - see LICENSE file for details.
+
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference