Update genesis/pipeline.py

genesis/pipeline.py

@@ -1,31 +1,25 @@
 # genesis/pipeline.py
 import os
 import re
-from typing import Dict, Any, List
 from datetime import datetime
+from typing import Dict, Any, List
 
 from .ontology import expand_terms_with_ontology
 from .structures import fetch_structures_for_terms
 from .narration import narrate_text
 from .graphdb import write_topic_and_papers
 from .providers import run_deepseek_summary, run_gemini_polish, run_openai_image, pubmed_fallback_search
-# genesis/pipeline.py
-from .providers import run_deepseek_summary, run_gemini_polish, run_gemini_image, pubmed_fallback_search
 
-# ===== ENV VARIABLES =====
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 UMLS_API_KEY = os.getenv("UMLS_API_KEY")
 BIOPORTAL_API_KEY = os.getenv("BIOPORTAL_API_KEY")
 NCBI_API_KEY = os.getenv("NCBI_API_KEY")
 NCBI_EMAIL = os.getenv("NCBI_EMAIL")
 ELEVEN_LABS_API_KEY = os.getenv("ELEVEN_LABS_API_KEY")
-NEO4J_USER = os.getenv("NEO4J_USER")
-NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD")
 NEO4J_URI = os.getenv("NEO4J_URI")
 
-SYNBIO_MODE = True  # force synthetic biology bias for demo
+SYNBIO_MODE = True
 
-# ===== DEMO PRESETS =====
 DEMO_QUERIES = [
     "Map all CRISPR-based living therapeutics in clinical trials since 2020",
     "Graph metabolic engineering pathways for bio-based drug production",
@@ -34,29 +28,21 @@ DEMO_QUERIES = [
     "AI-driven biosensor design for early cancer detection"
 ]
 
-
 def extract_citations(text: str) -> List[Dict[str, str]]:
-    """Extract citations from model output."""
     citations = []
     doi_pattern = r"(10\.\d{4,9}/[-._;()/:A-Z0-9]+)"
     pmid_pattern = r"PMID:\s*(\d+)"
     url_pattern = r"(https?://[^\s)]+)"
-
     for match in re.finditer(doi_pattern, text, re.IGNORECASE):
         citations.append({"type": "DOI", "id": match.group(1), "url": f"https://doi.org/{match.group(1)}"})
-
     for match in re.finditer(pmid_pattern, text, re.IGNORECASE):
         citations.append({"type": "PMID", "id": match.group(1), "url": f"https://pubmed.ncbi.nlm.nih.gov/{match.group(1)}/"})
-
     for match in re.finditer(url_pattern, text, re.IGNORECASE):
         if not any(c["url"] == match.group(1) for c in citations):
             citations.append({"type": "URL", "id": "", "url": match.group(1)})
-
     return citations
 
-
 def synthetic_biology_prompt_inject(query: str, expanded_terms: List[str]) -> str:
-    """Bias prompt toward synthetic biology domain."""
     synbio_context = (
         "You are an expert synthetic biologist and AI researcher. "
         "Focus on CRISPR, metabolic engineering, living therapeutics, protein design, "
@@ -65,43 +51,18 @@ def synthetic_biology_prompt_inject(query: str, expanded_terms: List[str]) -> st
     )
     return f"{synbio_context}\n\nQuery: {query}\nExpanded terms: {', '.join(expanded_terms)}"
 
-
 def research_once(query: str, graph_preview: bool = True, narration: bool = True) -> Dict[str, Any]:
-    """Main synthetic biology research pipeline."""
-    # 1. Expand query with ontology
     expanded_terms = expand_terms_with_ontology(query, UMLS_API_KEY, BIOPORTAL_API_KEY)
-
-    # 2. Inject synthetic biology context
     enriched_query = synthetic_biology_prompt_inject(query, expanded_terms) if SYNBIO_MODE else query
-
-    # 3. Run DeepSeek summarization
     raw_summary = run_deepseek_summary(enriched_query)
-
-    # 4. Polish with Gemini
     polished_summary = run_gemini_polish(raw_summary)
-
-    # 5. Extract citations
-    citations = extract_citations(polished_summary)
-    if not citations:
-        # fallback: run PubMed search
-        fallback_cites = pubmed_fallback_search(query, NCBI_API_KEY, NCBI_EMAIL)
-        citations.extend(fallback_cites)
-
-    # 6. Fetch molecular structures
+    citations = extract_citations(polished_summary) or pubmed_fallback_search(query, NCBI_API_KEY, NCBI_EMAIL)
     structures = fetch_structures_for_terms(expanded_terms)
-
-    # 7. Generate visual diagram with OpenAI image model
-    visual_image_url = run_openai_image(query) if OPENAI_API_KEY else None
-
-    # 8. Write to Neo4j graph
+    visual_image_url = run_openai_image(query)
     if graph_preview and NEO4J_URI:
         write_topic_and_papers(query, citations, expanded_terms)
-
-    # 9. Narrate executive summary
     audio_url = narrate_text(polished_summary) if narration and ELEVEN_LABS_API_KEY else None
-
-    # 10. Build output package
-    report = {
+    return {
         "timestamp": datetime.utcnow().isoformat(),
         "query": query,
         "expanded_terms": expanded_terms,
@@ -111,4 +72,3 @@ def research_once(query: str, graph_preview: bool = True, narration: bool = True
         "visual_image_url": visual_image_url,
         "audio_url": audio_url
     }
-    return report