Merge pull request #22 from openworm/development

 To v0.2.5

Author: pgleeson

.github/workflows/python-publish.yml

@@ -0,0 +1,33 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@release/v1

.gitignore

@@ -16,3 +16,4 @@ venv/
 /openworm_ai/corpus/wormatlas/ignore
 /openworm_ai/quiz/samples/GPT4o_10questions_general.json
 /openworm_ai/quiz/samples/GPT4o_10questions_science.json
+/dist

corpus/papers/test/SinhaEtAl2025.pdf.json

@@ -1,5 +1,5 @@
 # Version of the Python module.
-__version__ = "0.2.1"
+__version__ = "0.2.5"
 
 
 def print_(msg, print_it=True):

openworm_ai/__init__.py

@@ -263,9 +263,9 @@ def process_query(query, model, verbose=False):
             "What can you tell me about Alan Coulson?",
             "The NeuroPAL transgene is amazing. Give me some examples of fluorophores in it.",
         ]
-        """queries = [
-            "What can you tell me about Alan Coulson?",
-        ]"""
+        queries = [
+            "What are the main differences between NeuroML versions 1 and 2?",
+        ]
 
         print_("Processing %i queries" % len(queries))
 

openworm_ai/graphrag/GraphRAG_test.py

@@ -79,6 +79,10 @@ def convert_to_json(paper_ref, paper_info, output_dir):
             "corpus/papers/test/PrimerOnCElegans.pdf.json",
             "https://academic.oup.com/genetics/article/200/2/387/5936175",
         ],
+        "Sinha_et_al_2025": [
+            "corpus/papers/test/SinhaEtAl2025.pdf.json",
+            "https://elifesciences.org/articles/95135",
+        ],
     }
 
     # Loop through papers and process markdown sections

openworm_ai/parser/ParseLlamaIndexJson.py

@@ -6,16 +6,15 @@
 
 LLM_CMD_LINE_ARGS = {}
 
-LLM_GPT35 = "GPT3.5"
-LLM_GPT4 = "GPT4"
-LLM_GPT4o = "GPT4o"
+LLM_GPT35 = "gpt-3.5-turbo-instruct"
+LLM_CMD_LINE_ARGS["-gpt35"] = LLM_GPT35
+LLM_GPT4 = "gpt-4"
+LLM_GPT4o = "gpt-4o"
 
 LLM_LLAMA2 = "LLAMA2"
 LLM_CMD_LINE_ARGS["-l"] = LLM_LLAMA2
-LLM_GEMINI = "gemini-2.0-flash"
-LLM_CMD_LINE_ARGS["-g"] = LLM_GEMINI
-LLM_AI21 = "AI21"
-LLM_CMD_LINE_ARGS["-a"] = LLM_AI21
+LLM_GEMINI_2F = "gemini-2.0-flash"
+LLM_CMD_LINE_ARGS["-g"] = LLM_GEMINI_2F
 LLM_CLAUDE37 = "claude-3-7-sonnet-20250219"
 LLM_CMD_LINE_ARGS["-c"] = LLM_CLAUDE37
 LLM_COHERE = "Cohere"
@@ -57,12 +56,11 @@
 OPENAI_LLMS = [LLM_GPT35, LLM_GPT4, LLM_GPT4o]
 
 PREF_ORDER_LLMS = (
-    LLM_GEMINI,
+    LLM_GEMINI_2F,
     LLM_LLAMA2,
     LLM_GPT35,
     LLM_GPT4,
     LLM_GPT4o,
-    LLM_AI21,
     LLM_CLAUDE37,
     LLM_COHERE,
     LLM_OLLAMA_LLAMA32,
@@ -108,12 +106,6 @@ def get_gemini_api_key():
     return gemini_api_key
 
 
-def get_ai21_api_key():
-    ai21_api_key = os.environ.get["AI21_API_KEY"]
-
-    return ai21_api_key
-
-
 def get_anthropic_key():
     anthropic_api_key = os.environ.get("CLAUDE_API_KEY")
 
@@ -130,21 +122,27 @@ def get_llm(llm_ver, temperature):
     if llm_ver == LLM_GPT35:
         from langchain_openai import OpenAI
 
-        return OpenAI(temperature=temperature, openai_api_key=get_openai_api_key())
+        llm = OpenAI(
+            model_name=LLM_GPT35,
+            temperature=temperature,
+            openai_api_key=get_openai_api_key(),
+        )
+        # print(llm)
+        return llm
 
     elif llm_ver == LLM_GPT4:
         from langchain_openai import ChatOpenAI
 
         return ChatOpenAI(
-            model_name="gpt-4",
+            model_name=LLM_GPT4,
             openai_api_key=get_openai_api_key(),
             temperature=temperature,
         )
     elif llm_ver == LLM_GPT4o:
         from langchain_openai import ChatOpenAI
 
         return ChatOpenAI(
-            model_name="gpt-4o",
+            model_name=LLM_GPT4o,
             openai_api_key=get_openai_api_key(),
             temperature=temperature,
         )
@@ -165,20 +163,15 @@ def get_llm(llm_ver, temperature):
 
         llm = ChatLlamaAPI(client=llama)
 
-    elif llm_ver == LLM_GEMINI:
+    elif llm_ver == LLM_GEMINI_2F:
         from langchain_google_genai import ChatGoogleGenerativeAI
 
         return ChatGoogleGenerativeAI(
-            model="gemini-2.0-flash",
+            model=LLM_GEMINI_2F,
             google_api_key=get_gemini_api_key(),  # Retrieve API key
             temperature=temperature,
         )
 
-    elif llm_ver == LLM_AI21:
-        from langchain_ai21 import AI21LLM
-
-        llm = AI21LLM(model="j2-ultra")
-
     elif llm_ver == LLM_CLAUDE37:
         from langchain_anthropic import ChatAnthropic