update(10)

src/app.py

@@ -275,7 +275,7 @@ if st.session_state.page == "Enrich Companies":
                     response = qservice.query()
                     print(response)
                     print("Initial extraction is done. Now cleaning the JSON...")
-                    with open("data/uncleaned_companies.json", "r") as f:
+                    with open("/tmp/data/uncleaned_companies.json", "r") as f:
                         data = json.load(f)
 
                     cleaned_data = clean_json.clean_json_f(data)
@@ -314,7 +314,7 @@ if st.session_state.page == "Enrich Companies":
                     res = lead_scorer.scrape_and_augment(
                         own_comp_info, own_comp_web_url
                     )
-                    with open("src/data/lead_conditions.json", "w") as f:
+                    with open(os.path.join(DATA_DIR, "lead_conditions.json"), "w") as f:
                         json.dump(res, f, indent=2)
 
                     scored_leads = lead_scorer.score(enhanced_data, res)
@@ -413,13 +413,13 @@ if st.session_state.page == "IntelliSCORE":
                             res = lead_scorer.scrape_and_augment(
                                 additional_info, comp_url
                             )
-                            with open("src/data/lead_conditions.json", "w") as f:
+                            with open(os.path.join(DATA_DIR, "lead_conditions.json"), "w") as f:
                                 json.dump(res, f, indent=2)
                             st.success("Scrapping Completed!")
                             if res and "error" not in res:
                                 st.session_state.lead_conditions = True
 
-                        with open("src/data/lead_conditions.json", "r") as f:
+                        with open(os.path.join(DATA_DIR, "lead_conditions.json"), "r") as f:
                             lead_cond = json.load(f)
                         with st.spinner("Scoring the leads..."):
                             scored_leads = lead_scorer.score(leads, lead_cond)
@@ -430,7 +430,7 @@ if st.session_state.page == "IntelliSCORE":
 
                     else:
                         st.text("Skipping url scrapping...")
-                        with open("src/data/lead_conditions.json", "r") as f:
+                        with open(os.path.join(DATA_DIR, "lead_conditions.json"), "r") as f:
                             lead_cond = json.load(f)
                         with st.spinner("Scoring the leads..."):
                             scored_leads = lead_scorer.score(leads, lead_cond)

src/post_extraction_tools/data_quality_enhancer.py

@@ -124,7 +124,7 @@ def enhancer(data: object, embedder) -> list:
 
 
 def add_ind_key(data: list, embedder) -> list:
-    with open("src/data/key_industry_embeddings.json", "r") as f:
+    with open("/tmp/data/key_industry_embeddings.json", "r") as f:
         key_ind_embs = json.load(f)["industry_embeddings"]
     for c in data:
         if "key_industry" not in c:

src/post_extraction_tools/lead_scoring.py

@@ -113,8 +113,7 @@ class LeadScoring:
                 
                 lead['score'] = score
                 # scored_leads.append(lead)
-                root_dir = os.path.dirname(os.path.abspath(__file__))
-                data_folder = os.path.join(root_dir, "..", "data")
+                data_folder = "/tmp/data"
                 os.makedirs(data_folder, exist_ok=True)
 
                 file_path = os.path.join(data_folder, "all_cleaned_companies.json")

src/post_extraction_tools/website_adder.py

@@ -160,8 +160,7 @@ def wiki_search_mode(companies):
     else:
         print("All companies already have website URLs. Skipping wikisearch mode...")
     print("Saving results...")
-    root_dir = os.path.dirname(os.path.abspath(__file__))
-    data_folder = os.path.join(root_dir, "..", "data")
+    data_folder = "/tmp/data"
     os.makedirs(data_folder, exist_ok=True)
 
     file_path = os.path.join(data_folder, "all_cleaned_companies.json")

src/services/queryService.py

@@ -110,7 +110,7 @@ class QService:
         # filename = f"companies_{self.industry_type}_{self.location}.json".replace(" ", "_").lower()
         filename = "uncleaned_companies.json"
         try:
-            with open(f"data/{filename}", 'w', encoding="utf-8") as f:
+            with open(f"/tmp/data/{filename}", 'w', encoding="utf-8") as f:
                 f.write(json_output)
                 print(f"Data successfully written to {filename}")
         except Exception as e: