Update genesis/pipeline.py

genesis/pipeline.py

@@ -1,103 +1,78 @@
+# genesis/pipeline.py
+"""
+GENESIS-AI Research Pipeline
+Coordinates ontology expansion, literature retrieval, summaries, citations, structure fetching, graphDB storage, and narration.
+"""
+
 import os
-import re
 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 .molecule_viewer import fetch_structure
 from .narration import narrate_text
-from .graphdb import write_topic_and_papers
 from .providers import (
     run_deepseek_summary,
     run_gemini_polish,
     run_openai_image,
-    run_hf_image,
     pubmed_fallback_search
 )
+from .graphdb import write_topic_and_papers
 
-# Environment variables
-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")
+# ENV
 ELEVEN_LABS_API_KEY = os.getenv("ELEVEN_LABS_API_KEY")
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
 NEO4J_URI = os.getenv("NEO4J_URI")
 
 SYNBIO_MODE = True
 
-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, "
-        "biosensors, and biosecurity. Integrate literature, molecular structures, market trends, "
-        "and policy/regulatory outlook. Produce a structured, citation-rich report."
+def synthetic_biology_prompt_inject(query, expanded_terms):
+    """Injects domain-specific bias toward synthetic biology research."""
+    context = (
+        "You are an expert in synthetic biology. Focus on CRISPR, metabolic engineering, "
+        "living therapeutics, protein design, biosensors, and biosecurity. Include literature, "
+        "structures, market trends, and regulatory insights with citations."
     )
-    return f"{synbio_context}\n\nQuery: {query}\nExpanded terms: {', '.join(expanded_terms)}"
+    return f"{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)
+def research_once(query, graph_preview=True, narration=True):
+    """Runs the GENESIS-AI pipeline for a given research query."""
+    
+    # 1. Expand ontology
+    expanded_terms = expand_terms_with_ontology(query)
 
-    # 2. Inject synthetic biology context
+    # 2. Domain injection
     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)
+    # 3. Summarize (DeepSeek)
+    summary_raw = run_deepseek_summary(enriched_query)
 
-    # 4. Polish with Gemini
-    polished_summary = run_gemini_polish(raw_summary)
+    # 4. Polish (Gemini)
+    summary_polished = run_gemini_polish(summary_raw)
 
-    # 5. Extract citations
-    citations = extract_citations(polished_summary)
-    if not citations:
-        fallback_cites = pubmed_fallback_search(query, NCBI_API_KEY, NCBI_EMAIL)
-        citations.extend(fallback_cites)
+    # 5. Citations
+    citations = pubmed_fallback_search(query)
 
-    # 6. Fetch molecular structures
-    structures = fetch_structures_for_terms(expanded_terms)
+    # 6. Structures
+    structures = [fetch_structure(term) for term in expanded_terms]
 
-    # 7. Generate visual diagram
-    visual_image_url = run_openai_image(query)
-    if not visual_image_url:
-        print("[Image] Falling back to Hugging Face Stable Diffusion...")
-        visual_image_url = run_hf_image(f"Scientific diagram about {query}")
+    # 7. Visual (OpenAI Image)
+    image_url = run_openai_image(query)
 
-    # 8. Write to Neo4j
+    # 8. GraphDB
     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
+    # 9. Narration
+    audio_url = narrate_text(summary_polished) if narration and ELEVEN_LABS_API_KEY else None
 
-    # 10. Return structured output
+    # 10. Output
     return {
         "timestamp": datetime.utcnow().isoformat(),
         "query": query,
         "expanded_terms": expanded_terms,
-        "summary": polished_summary,
+        "summary": summary_polished,
         "citations": citations,
         "structures": structures,
-        "visual_image_url": visual_image_url,
+        "image_url": image_url,
         "audio_url": audio_url
     }