Merge pull request #5 from izam-mohammed/main

update develop

.gitignore

@@ -162,3 +162,4 @@ cython_debug/
 # artifacts in the process
 artifacts/
 streamlit_files/
+*.sqlite

README.md

@@ -54,8 +54,12 @@ These installation instructions assume that you have conda installed and added t
    streamlit run app.py
    ```
 
-### pipelines
+6. Run the Trulens server for check the performance
+   ```bash
+   python trulens_evaluate.py
+   ```
 
+### pipelines
 
 - Visualizations 
 - Prompt Creation
@@ -67,10 +71,10 @@ These installation instructions assume that you have conda installed and added t
 
 
 - [Izam Mohammed](github.com/izam-mohammed)
-- [Vishu Prasad]()
+- [Vishu Prakash](github.com/vishnuprksh)
 - [Afsal](https://github.com/AfsalAfzz-Pro)
 - [Josekutty](github.com/jkutty-7)
-- [AbduRahiman]()
+- [AbduRahiman](https://github.com/abdurahiman-offc)
 - [Amal](https://github.com/Amallmmd)
 
 

app.py

@@ -6,15 +6,22 @@
 from gemInsights import logger
 from markdown import markdown
 
+
 if not os.path.isdir("streamlit_files"):
     os.makedirs(os.path.join(os.getcwd(), "streamlit_files"), exist_ok=True)
 
 dataframe = None
 st.title("GemInsights")
-file = st.file_uploader("Pick a dataframe", type=["csv"], accept_multiple_files=False)
+file = st.file_uploader(
+    "Pick a dataframe", type=["csv", "xlsx"], accept_multiple_files=False
+)
 
 if file is not None:
-    dataframe = pd.read_csv(file)
+    _, extension = os.path.splitext(file.name)
+    if extension == ".csv":
+        dataframe = pd.read_csv(file)
+    else:
+        dataframe = pd.read_excel(file)
     st.write(dataframe.head())
     st.write(f"updated a dataframe with shape {dataframe.shape}")
 

config/config.yaml

@@ -16,7 +16,8 @@ prompt_generation:
   data_path: artifacts/data_ingestion/data.csv
   visualization_path: artifacts/data_visualization/
   data_information_file: artifacts/data_ingestion/data_info.json
-  prompt_file_name: prompt.joblib
+  prompt_file_name: prompt.txt
+  images_file_name: images.joblib
 
 prompting:
   root_dir: artifacts/prompting
@@ -25,4 +26,6 @@ prompting:
   candidates_file_name: candidates.json
   project_name: ultra-heading-407815
   project_location: us-central1
-  prompt_file_path: artifacts/prompt_generation/prompt.joblib
+  prompt_file_path: artifacts/prompt_generation/prompt.txt
+  images_file_path: artifacts/prompt_generation/images.joblib
+  trulens_db_name: gemInsights.sqlite

main_prompt.txt

@@ -0,0 +1,3 @@
+Act as a data analyst. 
+Here is the complete information and visualization images of a dataset. 
+give valuable insights from the data point wise

requirements.txt

@@ -14,4 +14,6 @@ PyYAML
 autoviz
 ipython
 google-cloud-aiplatform
--e .
+markdown
+litellm
+-e .

research/00_data_ingestion.ipynb

@@ -8,7 +8,7 @@
     {
      "data": {
       "text/plain": [
-       "'/home/izam/coding/hackathon'"
+       "'/home/izam/coding/GemInsights'"
       ]
      },
      "execution_count": 1,
@@ -131,21 +131,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2023-12-21 13:24:17,901: INFO: common: yaml file: config/config.yaml loaded successfully]\n",
-      "[2023-12-21 13:24:17,903: INFO: common: yaml file: params.yaml loaded successfully]\n",
-      "[2023-12-21 13:24:17,903: INFO: common: created directory at: artifacts]\n",
-      "[2023-12-21 13:24:17,904: INFO: common: created directory at: artifacts/data_ingestion]\n",
-      "[2023-12-21 13:24:17,908: INFO: 1086895689: loaded the dataframe with shape (891, 12)]\n",
-      "[2023-12-21 13:24:17,914: INFO: 1086895689: saved the data in artifacts/data_ingestion/data.csv]\n",
-      "[2023-12-21 13:24:17,915: INFO: common: json file loaded succesfully from: streamlit_files/additional_data.json]\n",
-      "[2023-12-21 13:24:17,915: INFO: common: json file saved at: artifacts/data_ingestion/data_info.json]\n"
+      "[2023-12-22 00:28:12,608: INFO: common: yaml file: config/config.yaml loaded successfully]\n",
+      "[2023-12-22 00:28:12,610: INFO: common: yaml file: params.yaml loaded successfully]\n",
+      "[2023-12-22 00:28:12,611: INFO: common: created directory at: artifacts]\n",
+      "[2023-12-22 00:28:12,611: INFO: common: created directory at: artifacts/data_ingestion]\n",
+      "[2023-12-22 00:28:12,630: INFO: 1086895689: loaded the dataframe with shape (7043, 22)]\n",
+      "[2023-12-22 00:28:12,661: INFO: 1086895689: saved the data in artifacts/data_ingestion/data.csv]\n",
+      "[2023-12-22 00:28:12,663: INFO: common: json file loaded succesfully from: streamlit_files/additional_data.json]\n",
+      "[2023-12-22 00:28:12,664: INFO: common: json file saved at: artifacts/data_ingestion/data_info.json]\n"
      ]
     }
    ],
@@ -185,7 +185,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.18"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,