pembot 0.0.4__tar.gz → 0.0.5__tar.gz

{pembot-0.0.4 → pembot-0.0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.0.4
+Version: 0.0.5
 Summary: A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 Author-email: cyto <aryan_sidhwani@protonmail.com>
 License-Expression: MIT

pembot-0.0.5/pembot/.git/COMMIT_EDITMSG

@@ -0,0 +1 @@
+fixed the output_dir bug; fixed the excel to json function; ran some tests on convertor; incremented the version on the package; removed dependency on schema / structure, and shifted required fields to a pickle file path in the cli args;

{pembot-0.0.4 → pembot-0.0.5}/pembot/.git/logs/HEAD

@@ -4,3 +4,4 @@ ac9c9018c62fa30dc142665c1b5a375f4e056880 72f047cda92abcd1ddc857f6461de605f866833
 72f047cda92abcd1ddc857f6461de605f8668331 e91172752e9a421ae463112d2b0506b37498c98d cyto <silverstone965@gmail.com> 1748881846 +0530	commit: added gemini to the embedders and llms ladders; redeclared the required fields;
 e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 cyto <silverstone965@gmail.com> 1749716350 +0530	commit: added a pem blog chunking module for updating from local, and, an embedding loop to embed all the blogs, with document id as the filter in the search, and the first line title as the filter in updation
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856653 +0530	commit: made arrangements for the cases when custom file bytes are to be processed to text output; handled a ollama running / crashing error
+eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937276 +0530	commit: fixed the output_dir bug; fixed the excel to json function; ran some tests on convertor; incremented the version on the package; removed dependency on schema / structure, and shifted required fields to a pickle file path in the cli args;

{pembot-0.0.4 → pembot-0.0.5}/pembot/.git/logs/refs/heads/main

@@ -4,3 +4,4 @@ ac9c9018c62fa30dc142665c1b5a375f4e056880 72f047cda92abcd1ddc857f6461de605f866833
 72f047cda92abcd1ddc857f6461de605f8668331 e91172752e9a421ae463112d2b0506b37498c98d cyto <silverstone965@gmail.com> 1748881846 +0530	commit: added gemini to the embedders and llms ladders; redeclared the required fields;
 e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 cyto <silverstone965@gmail.com> 1749716350 +0530	commit: added a pem blog chunking module for updating from local, and, an embedding loop to embed all the blogs, with document id as the filter in the search, and the first line title as the filter in updation
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856653 +0530	commit: made arrangements for the cases when custom file bytes are to be processed to text output; handled a ollama running / crashing error
+eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937276 +0530	commit: fixed the output_dir bug; fixed the excel to json function; ran some tests on convertor; incremented the version on the package; removed dependency on schema / structure, and shifted required fields to a pickle file path in the cli args;

{pembot-0.0.4 → pembot-0.0.5}/pembot/.git/logs/refs/remotes/origin/main

@@ -3,3 +3,4 @@ ac9c9018c62fa30dc142665c1b5a375f4e056880 72f047cda92abcd1ddc857f6461de605f866833
 72f047cda92abcd1ddc857f6461de605f8668331 e91172752e9a421ae463112d2b0506b37498c98d cyto <silverstone965@gmail.com> 1748881859 +0530	update by push
 e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 cyto <silverstone965@gmail.com> 1749716371 +0530	update by push
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856672 +0530	update by push
+eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937389 +0530	update by push

pembot-0.0.5/pembot/.git/refs/heads/main

@@ -0,0 +1 @@
+0bdb4169fc0f312b8698f1df17a258fff163aeaa

pembot-0.0.5/pembot/.git/refs/remotes/origin/main

@@ -0,0 +1 @@
+0bdb4169fc0f312b8698f1df17a258fff163aeaa

{pembot-0.0.4 → pembot-0.0.5}/pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.0.4'
+__version__ = '0.0.5'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

{pembot-0.0.4 → pembot-0.0.5}/pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.0.4
+  version: 0.0.5

{pembot-0.0.4 → pembot-0.0.5}/pembot/pdf2markdown/extract.py

@@ -24,8 +24,17 @@ import mimetypes
 
 warnings.filterwarnings("ignore")
 
-with open(Path("config/config.yaml").resolve(), "r", encoding="utf-8") as f:
-    config = yaml.safe_load(f)
+config= {}
+try:
+    with open(Path("config/config.yaml").resolve(), "r", encoding="utf-8") as f:
+        config = yaml.safe_load(f)
+except FileNotFoundError:
+    config= {
+        'OUTPUT_DIR': '.',
+        'PAGE_DELIMITER': '____NEXT PAGE____'
+    }
+except Exception as e:
+    print("unhandled while opening default config in pdf2markdown: ", e)
 
 
 class PDFExtractor(ABC):
@@ -62,7 +71,7 @@ class MarkdownPDFExtractor(PDFExtractor):
 
     BULLET_POINTS = "•◦▪▫●○"
 
-    def __init__(self, pdf_path, output_path= config["OUTPUT_DIR"], page_delimiter= config["PAGE_DELIMITER"], model_name: str | None= None):
+    def __init__(self, pdf_path, output_path= config.get("OUTPUT_DIR", '.'), page_delimiter= config.get("PAGE_DELIMITER", ''), model_name: str | None= None):
         super().__init__(pdf_path)
 
         if model_name is None:

{pembot-0.0.4 → pembot-0.0.5}/pembot/query.py

@@ -97,16 +97,22 @@ def rag_query_llm(db_client, llm_client, inference_client, user_query: str, docu
         str: The generated response from the Ollama model.
     """
 
-    models = llm_client.list()
-    found= False
     embed_locally= False
-
-    for model in models.models:
-        # print(model.model)
-        if model.model == model_name:
-            found= True
-        if model.model == embedding_model:
-            embed_locally= True
+    found= False
+    try:
+        models = llm_client.list()
+        for model in models.models:
+            # print(model.model)
+            if model.model == model_name:
+                found= True
+            if model.model == embedding_model:
+                embed_locally= True
+    except AttributeError as ae:
+        print("cant find ollama", ae)
+        print("continuing with other models")
+    except Exception as e:
+        print("unhandled error: ", e)
+        raise e
 
 
 

pembot-0.0.4/pembot/.git/COMMIT_EDITMSG

@@ -1 +0,0 @@
-made arrangements for the cases when custom file bytes are to be processed to text output; handled a ollama running / crashing error

pembot-0.0.4/pembot/.git/refs/heads/main

@@ -1 +0,0 @@
-eb75e1c49f1e5b79dca17ccdbec8067756523238

pembot-0.0.4/pembot/.git/refs/remotes/origin/main

@@ -1 +0,0 @@
-eb75e1c49f1e5b79dca17ccdbec8067756523238