Update genesis/providers.py

genesis/providers.py

@@ -1,164 +1,257 @@
 # genesis/providers.py
+"""
+Providers module for GENESIS-AI
+Handles:
+1. Medical/Biological APIs (PubMed, ChEMBL, BioPortal, UMLS, NCBI)
+2. AI Text Generation (Gemini, OpenAI, Claude, DeepSeek)
+3. Image Generation (Gemini Vision, OpenAI DALL·E, Hugging Face Diffusion)
+4. Text-to-Speech (ElevenLabs + fallback)
+5. Graph DB Integration (Neo4j for pathways/funding)
+"""
+
 import os
+import json
 import requests
-import base64
-from typing import Optional
+import logging
+from neo4j import GraphDatabase
+from dotenv import load_dotenv
+
+# ========================
+# SECTION 1 — SETUP & LOGGING
+# ========================
+load_dotenv()
+logging.basicConfig(level=logging.INFO)
+
+# API KEYS from Hugging Face Secrets or local .env
+PUBMED_API_KEY = os.getenv("PUBMED_API_KEY")
+CHEMBL_API_KEY = os.getenv("CHEMBL_API_KEY")
+BIOPORTAL_API_KEY = os.getenv("BIOPORTAL_API_KEY")
+UMLS_API_KEY = os.getenv("UMLS_API_KEY")
+NCBI_API_KEY = os.getenv("NCBI_API_KEY")
 
-# Load secrets from environment
-DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY")
-GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-HF_API_KEY = os.getenv("HF_API_KEY")
-ELEVEN_LABS_API_KEY = os.getenv("ELEVEN_LABS_API_KEY")
-
-# ------------------------------
-# 1 — DEEPSEEK SUMMARIZER
-# ------------------------------
-def run_deepseek_summary(prompt: str) -> Optional[str]:
-    if not DEEPSEEK_API_KEY:
-        return None
-    try:
-        url = "https://api.deepseek.com/v1/chat/completions"
-        headers = {"Authorization": f"Bearer {DEEPSEEK_API_KEY}"}
-        payload = {
-            "model": "deepseek-chat",
-            "messages": [{"role": "user", "content": prompt}],
-            "temperature": 0.3
-        }
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        return resp.json()["choices"][0]["message"]["content"]
-    except Exception as e:
-        print(f"[DeepSeek] Failed: {e}")
-        return None
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+CLAUDE_API_KEY = os.getenv("CLAUDE_API_KEY")
+DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY")
 
+ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
 
-# ------------------------------
-# 2 — GEMINI SUMMARIZER
-# ------------------------------
-def run_gemini_summary(prompt: str) -> Optional[str]:
-    if not GEMINI_API_KEY:
-        return None
-    try:
-        url = f"https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key={GEMINI_API_KEY}"
-        headers = {"Content-Type": "application/json"}
-        payload = {"contents": [{"parts": [{"text": prompt}]}]}
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        return resp.json()["candidates"][0]["content"]["parts"][0]["text"]
-    except Exception as e:
-        print(f"[Gemini] Failed: {e}")
-        return None
+NEO4J_URI = os.getenv("NEO4J_URI")
+NEO4J_USER = os.getenv("NEO4J_USER")
+NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD")
 
+# Neo4j Driver
+neo4j_driver = GraphDatabase.driver(NEO4J_URI, auth=(NEO4J_USER, NEO4J_PASSWORD))
 
-# ------------------------------
-# 3 — OPENAI SUMMARIZER
-# ------------------------------
-def run_openai_summary(prompt: str) -> Optional[str]:
-    if not OPENAI_API_KEY:
-        return None
+
+def safe_request(url, headers=None, params=None, data=None, method="GET", json_data=None):
     try:
-        url = "https://api.openai.com/v1/chat/completions"
-        headers = {"Authorization": f"Bearer {OPENAI_API_KEY}"}
-        payload = {
-            "model": "gpt-4o-mini",
-            "messages": [{"role": "user", "content": prompt}],
-            "temperature": 0.3
-        }
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        return resp.json()["choices"][0]["message"]["content"]
+        if method == "GET":
+            r = requests.get(url, headers=headers, params=params, timeout=20)
+        elif method == "POST":
+            r = requests.post(url, headers=headers, data=data, json=json_data, timeout=30)
+        r.raise_for_status()
+        return r.json()
     except Exception as e:
-        print(f"[OpenAI] Failed: {e}")
+        logging.error(f"Request failed: {e}")
         return None
 
+# ========================
+# SECTION 2 — MEDICAL & BIOLOGY API CLIENTS
+# ========================
 
-# ------------------------------
-# 4 — GEMINI IMAGE GENERATOR
-# ------------------------------
-def run_gemini_image(prompt: str) -> Optional[str]:
-    if not GEMINI_API_KEY:
-        return None
-    try:
-        # Gemini image generation (beta)
-        url = f"https://generativelanguage.googleapis.com/v1beta/models/imagegeneration:generateImage?key={GEMINI_API_KEY}"
-        payload = {"prompt": prompt, "size": "1024x1024"}
-        headers = {"Content-Type": "application/json"}
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        data = resp.json()
-        if "data" in data and len(data["data"]) > 0:
-            return data["data"][0]["url"]
-        return None
-    except Exception as e:
-        print(f"[Gemini Image] Failed: {e}")
-        return None
+def run_pubmed_literature(query, max_results=5):
+    url = f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
+    params = {
+        "db": "pubmed",
+        "term": query,
+        "retmode": "json",
+        "retmax": max_results,
+        "api_key": PUBMED_API_KEY
+    }
+    data = safe_request(url, params=params)
+    if not data:
+        return []
+    ids = data.get("esearchresult", {}).get("idlist", [])
+    results = []
+    for pmid in ids:
+        fetch_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
+        fetch_params = {"db": "pubmed", "id": pmid, "retmode": "json"}
+        summary = safe_request(fetch_url, params=fetch_params)
+        if summary:
+            results.append(summary)
+    return results
 
 
-# ------------------------------
-# 5 — OPENAI IMAGE GENERATOR
-# ------------------------------
-def run_openai_image(prompt: str) -> Optional[str]:
-    if not OPENAI_API_KEY:
-        return None
-    try:
-        url = "https://api.openai.com/v1/images/generations"
-        headers = {"Authorization": f"Bearer {OPENAI_API_KEY}"}
-        payload = {"model": "gpt-image-1", "prompt": prompt, "size": "1024x1024"}
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        return resp.json()["data"][0]["url"]
-    except Exception as e:
-        print(f"[OpenAI Image] Failed: {e}")
-        return None
+def run_chembl_search(molecule_name):
+    url = f"https://www.ebi.ac.uk/chembl/api/data/molecule"
+    params = {"molecule_synonyms__icontains": molecule_name, "format": "json"}
+    return safe_request(url, params=params)
 
 
-# ------------------------------
-# 6 — HF STABLE DIFFUSION IMAGE
-# ------------------------------
-def run_hf_image(prompt: str) -> Optional[str]:
-    if not HF_API_KEY:
-        return None
-    try:
-        url = "https://api-inference.huggingface.co/models/stabilityai/stable-diffusion-2"
-        headers = {"Authorization": f"Bearer {HF_API_KEY}"}
-        payload = {"inputs": prompt}
-        resp = requests.post(url, headers=headers, json=payload, timeout=120)
-        resp.raise_for_status()
-        if resp.headers.get("content-type") == "image/png":
-            filename = f"generated_{hash(prompt)}.png"
-            with open(filename, "wb") as f:
-                f.write(resp.content)
-            return filename
-        return None
-    except Exception as e:
-        print(f"[HF Image] Failed: {e}")
-        return None
+def run_bioportal_ontology(term):
+    url = f"https://data.bioontology.org/search"
+    params = {"q": term, "apikey": BIOPORTAL_API_KEY}
+    return safe_request(url, params=params)
 
 
-# ------------------------------
-# 7 — ELEVENLABS TEXT-TO-SPEECH
-# ------------------------------
-def narrate_text_elevenlabs(text: str) -> Optional[str]:
-    if not ELEVEN_LABS_API_KEY:
-        return None
-    try:
-        url = "https://api.elevenlabs.io/v1/text-to-speech"
-        headers = {
-            "xi-api-key": ELEVEN_LABS_API_KEY,
-            "Content-Type": "application/json"
-        }
-        payload = {
-            "text": text,
-            "voice": "Bella",  # You can make this configurable
-            "model_id": "eleven_monolingual_v1"
-        }
-        resp = requests.post(url, headers=headers, json=payload, timeout=60)
-        resp.raise_for_status()
-        filename = f"narration_{hash(text)}.mp3"
-        with open(filename, "wb") as f:
-            f.write(resp.content)
-        return filename
-    except Exception as e:
-        print(f"[ElevenLabs] Failed: {e}")
-        return None
+def run_umls_search(term):
+    url = f"https://uts-ws.nlm.nih.gov/rest/search/current"
+    params = {"string": term, "apiKey": UMLS_API_KEY}
+    return safe_request(url, params=params)
+
+
+def run_ncbi_gene_lookup(gene_id):
+    url = f"https://api.ncbi.nlm.nih.gov/gene/{gene_id}"
+    headers = {"api-key": NCBI_API_KEY}
+    return safe_request(url, headers=headers)
+
+
+# ========================
+# SECTION 3 — AI TEXT GENERATION PROVIDERS
+# ========================
+
+def ai_generate_text(prompt, model="gemini"):
+    """Fallback order: Gemini → OpenAI → Claude → DeepSeek"""
+    if model == "gemini" and GEMINI_API_KEY:
+        resp = safe_request(
+            f"https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key={GEMINI_API_KEY}",
+            method="POST",
+            json_data={"contents": [{"parts": [{"text": prompt}]}]}
+        )
+        if resp:
+            return resp.get("candidates", [{}])[0].get("content", {}).get("parts", [{}])[0].get("text", "")
+
+    if OPENAI_API_KEY:
+        try:
+            import openai
+            openai.api_key = OPENAI_API_KEY
+            completion = openai.ChatCompletion.create(
+                model="gpt-4o",
+                messages=[{"role": "user", "content": prompt}]
+            )
+            return completion.choices[0].message["content"]
+        except Exception as e:
+            logging.error(f"OpenAI error: {e}")
+
+    if CLAUDE_API_KEY:
+        resp = safe_request(
+            "https://api.anthropic.com/v1/messages",
+            headers={"x-api-key": CLAUDE_API_KEY, "Content-Type": "application/json"},
+            method="POST",
+            json_data={"model": "claude-3-opus-20240229", "messages": [{"role": "user", "content": prompt}], "max_tokens": 500}
+        )
+        if resp:
+            return resp.get("content", [{}])[0].get("text", "")
+
+    if DEEPSEEK_API_KEY:
+        resp = safe_request(
+            "https://api.deepseek.com/v1/chat/completions",
+            headers={"Authorization": f"Bearer {DEEPSEEK_API_KEY}", "Content-Type": "application/json"},
+            method="POST",
+            json_data={"model": "deepseek-chat", "messages": [{"role": "user", "content": prompt}]}
+        )
+        if resp:
+            return resp.get("choices", [{}])[0].get("message", {}).get("content", "")
+
+    return "No AI provider available or all failed."
+
+
+# ========================
+# SECTION 4 — IMAGE GENERATION PROVIDERS
+# ========================
+
+def ai_generate_image(prompt):
+    """Fallback: Gemini Vision → OpenAI → Hugging Face"""
+    if GEMINI_API_KEY:
+        resp = safe_request(
+            f"https://generativelanguage.googleapis.com/v1beta/models/gemini-pro-vision:generateImage?key={GEMINI_API_KEY}",
+            method="POST",
+            json_data={"prompt": prompt}
+        )
+        if resp:
+            return resp
+
+    if OPENAI_API_KEY:
+        try:
+            import openai
+            openai.api_key = OPENAI_API_KEY
+            image = openai.Image.create(model="dall-e-3", prompt=prompt, size="1024x1024")
+            return image.data[0].url
+        except Exception as e:
+            logging.error(f"OpenAI Image error: {e}")
+
+    # Hugging Face fallback
+    HF_TOKEN = os.getenv("HF_TOKEN")
+    if HF_TOKEN:
+        resp = safe_request(
+            "https://api-inference.huggingface.co/models/stabilityai/stable-diffusion-2",
+            headers={"Authorization": f"Bearer {HF_TOKEN}"},
+            method="POST",
+            json_data={"inputs": prompt}
+        )
+        if resp:
+            return resp
+
+    return None
+
+
+# ========================
+# SECTION 5 — TEXT-TO-SPEECH PROVIDERS
+# ========================
+
+def run_tts(text, voice="Rachel"):
+    if ELEVENLABS_API_KEY:
+        url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice}"
+        headers = {"xi-api-key": ELEVENLABS_API_KEY, "Content-Type": "application/json"}
+        resp = requests.post(url, headers=headers, json={"text": text, "voice_settings": {"stability": 0.5, "similarity_boost": 0.8}})
+        if resp.status_code == 200:
+            return resp.content
+    return None
+
+
+# ========================
+# SECTION 6 — NEO4J GRAPH FUNCTIONS
+# ========================
+
+def query_funding_network(keyword):
+    with neo4j_driver.session() as session:
+        result = session.run(
+            """
+            MATCH (c:Company)-[r:RECEIVED_FUNDING_FROM]->(i:Investor)
+            WHERE toLower(c.name) CONTAINS toLower($keyword)
+            RETURN c.name as company, collect(i.name) as investors
+            """,
+            keyword=keyword
+        )
+        return [dict(record) for record in result]
+
+
+def query_pathway_graph(pathway):
+    with neo4j_driver.session() as session:
+        result = session.run(
+            """
+            MATCH (p:Pathway {name: $pathway})-[r:INVOLVES]->(g:Gene)
+            RETURN p.name as pathway, collect(g.name) as genes
+            """,
+            pathway=pathway
+        )
+        return [dict(record) for record in result]
+
+
+# ========================
+# SECTION 7 — EXPORTS
+# ========================
+
+__all__ = [
+    "run_pubmed_literature",
+    "run_chembl_search",
+    "run_bioportal_ontology",
+    "run_umls_search",
+    "run_ncbi_gene_lookup",
+    "ai_generate_text",
+    "ai_generate_image",
+    "run_tts",
+    "query_funding_network",
+    "query_pathway_graph"
+]