update default public config

app.py

@@ -19,6 +19,7 @@ from spinoza_project.source.frontend.gradio_utils import (
     get_init_prompt,
     get_synthesis_prompt,
     get_qdrants,
+    get_qdrants_public,
     start_agents,
     end_agents,
     next_call,
@@ -50,11 +51,17 @@ llm = get_llm_api()
 
 ## Loading BDDs
 print("Loading Databases")
-if os.getenv("EKI_OPENAI_EMB_DEPLOYMENT_NAME"):
+qdrants = get_qdrants(config)
+
+if os.getenv("EKI_OPENAI_LLM_DEPLOYMENT_NAME"):
     bdd_presse = get_vectorstore_api("presse")
     bdd_afp = get_vectorstore_api("afp")
 
-qdrants = get_qdrants(config)
+else:
+    qdrants_public = get_qdrants_public(config, "momenaca/hackathon_spinoza")
+    qdrants = {**qdrants, **qdrants_public}
+    bdd_presse = None
+    bdd_afp = None
 
 ## Loading Assets
 css, source_information = get_assets()
@@ -79,7 +86,11 @@ def reformulate_questions(
 
 
 def retrieve_sources(
-    *questions, qdrants=qdrants, bdd_presse=bdd_presse, bdd_afp=bdd_afp, config=config
+    *questions,
+    qdrants=qdrants,
+    bdd_presse=bdd_presse,
+    bdd_afp=bdd_afp,
+    config=config,
 ):
     formated_sources, text_sources = get_sources(
         questions, qdrants, bdd_presse, bdd_afp, config

spinoza_project/config_public.yaml

@@ -10,14 +10,12 @@ tabs:
     * *Des études et recherches sur des impacts locaux*\n
     * *Des documents institutionnels (analyses demandées par la France & rapports d'activité)*\n
     * *Les plans de transition sectoriels pour les secteurs industriels les plus émetteurs : (verre, papier, ciment, acier, aluminium, chimie, sucre)*"
-  Hackathon: "*Créez votre propre agent personnalisé.*"
 
 source_mapping:
   GIEC et IPBES: "Science"
   Textes Juridiques: "Loi"
   Organismes publics: "Organismes publics"
   ADEME: "ADEME"
-  Hackathon: "Hackathon"
 
 prompt_naming:
   Science: "Science"
@@ -25,7 +23,6 @@ prompt_naming:
   Organismes publics: "Organismes publics"
   ADEME: "ADEME"
   Presse: "Presse"
-  Hackathon: "Hackathon"
 
 query_preprompt: "query: "
 passage_preprompt: "passage: "

spinoza_project/source/frontend/gradio_utils.py

@@ -13,7 +13,7 @@ from spinoza_project.source.backend.document_store import pickle_to_document_sto
 
 
 def get_config():
-    if os.getenv("EKI_OPENAI_EMB_DEPLOYMENT_NAME"):
+    if os.getenv("EKI_OPENAI_LLM_DEPLOYMENT_NAME"):
         with open("./spinoza_project/config.yaml") as f:
             return yaml.full_load(f)
 
@@ -58,7 +58,23 @@ def get_qdrants(config):
             )
         )
         for tab in config["prompt_naming"]
-        if tab != "Presse" and tab != "AFP"
+        if tab in ["Science", "Loi", "Organismes publics", "ADEME"]
+    }
+
+    return qdrants
+
+
+def get_qdrants_public(config, repo_id):
+    qdrants = {
+        tab: pickle_to_document_store(
+            hf_hub_download(
+                repo_id=repo_id,
+                filename=f"database_{tab}.pickle",
+                repo_type="dataset",
+            )
+        )
+        for tab in config["prompt_naming"]
+        if tab not in ["Science", "Loi", "Organismes publics", "ADEME", "Presse", "AFP"]
     }
 
     return qdrants