Updated_v2

app.py

@@ -23,16 +23,16 @@ from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 import tiktoken
 from llama_index.core.callbacks import CallbackManager, TokenCountingHandler
 from llama_index.core.tools import QueryEngineTool, ToolMetadata
-from FunctionTools import ScriptureDescriptionToolSpec, MantraToolSpec
+from Tools import ScriptureDescriptionToolSpec, MantraToolSpec, PadaToolSpec
+
 
 # Print all loaded secrets
 all_secrets = st.secrets
-#st.write("All secrets:", all_secrets)
+
 
 # Access the specific secret
 try:
     openai_api_key = st.secrets["OPENAI_APIKEY_CS"]
-    #st.write("OpenAI API Key:", openai_api_key)
 except KeyError as e:
     st.error(f"KeyError: {e}")
 
@@ -42,12 +42,12 @@ try:
     #st.write("OpenAI API Key:", openai_api_key)
 except KeyError as e:
     st.error(f"KeyError: {e}")   
-#load keys
-#openai_api_key = st.secrets["OPENAI_APIKEY_CS"]
-#pinecone_api_key = st.secrets["PINECONE_API_KEY_SAM"]
+
+
+
 
 #llm
-llm_AI = OpenAI(temperature=0, model="gpt-4-1106-preview",api_key=openai_api_key, max_tokens=512)
+
 llm_AI4 = OpenAI(temperature=0, model="gpt-4-1106-preview",api_key=openai_api_key, max_tokens=512)
 token_counter = TokenCountingHandler(
     tokenizer=tiktoken.encoding_for_model("gpt-4-1106-preview").encode
@@ -71,12 +71,16 @@ pinecone_index = pc.Index("pod-index")
 vector_store_pine = PineconeVectorStore(pinecone_index=pinecone_index)
 storage_context_pine = StorageContext.from_defaults(vector_store=vector_store_pine)
 index_store = VectorStoreIndex.from_vector_store(vector_store_pine,storage_context=storage_context_pine)
-query_engine_vector = index_store.as_query_engine(similarity_top_k=5,vector_store_query_mode ='hybrid',alpha=0.6,inlcude_metadata = True)
+query_engine_vector = index_store.as_query_engine(similarity_top_k=10,vector_store_query_mode ='hybrid',alpha=0.6,inlcude_metadata = True)
+
+VEDAMANTRA_CSV_PATH = r"Data/veda_content_modified_v3.csv"
+PADA_CSV_PATH = r"Data/Data/term_data_processed_v2.csv"
+
 #pandas Engine
-df_veda_details = pd.read_csv("Data/veda_content_details.csv",encoding='utf-8')
-#df_pada_details = pd.read_csv("Data/term_grammar_v2.csv.csv",encoding='utf-8')
-query_engine_veda_details = PandasQueryEngine(df=df_veda_details)
-#query_engine_pada_details = PandasQueryEngine(df=df_pada_details)
+df_veda_details = pd.read_csv(VEDAMANTRA_CSV_PATH,encoding='utf-8')
+df_pada_details = pd.read_csv(PADA_CSV_PATH,encoding='utf-8')
+query_engine_veda = PandasQueryEngine(df=df_veda_details)
+query_engine_pada = PandasQueryEngine(df=df_pada_details)
 
 # Query Engine Tools
 query_engine_tools = [
@@ -85,7 +89,8 @@ query_engine_tools = [
         metadata=ToolMetadata(
             name="vector_engine",
             description=(
-                '''Helpful to get semantic information from the documents. These documents containing comprehensive information about the Vedas.\
+                '''
+                Helpful to get semantic information from the documents. These documents containing comprehensive information about the Vedas.\
                 They also covers various aspects, including general details about the Vedas, fundamental terminology associated with Vedic literature, \
                 and detailed information about Vedamantras for each Veda. The Vedamantra details encompass essential elements such as padapatha, rishi, chandah,\
                 devata, and swarah.This tool is very useful to answer general questions related to vedas.\
@@ -98,9 +103,9 @@ query_engine_tools = [
         ),
     ),
     QueryEngineTool(
-        query_engine=query_engine_veda_details,
+        query_engine=query_engine_veda,
         metadata=ToolMetadata(
-            name="pandas_veda_engine",
+            name="pandas_engine_vedas",
             description=(
                 '''A powerful tool designed to handle queries related to counting information about vedic content document. This document is a .csv file with different columns as follows:\
                 'mantra_id', 'scripture_name', 'KandahNumber', 'PrapatakNumber','AnuvakNumber', 'MantraNumber', 'DevataName', 'RishiName', 'SwarahName', 'ChandaName',\
@@ -115,21 +120,42 @@ query_engine_tools = [
                '''
             ),
         ),
+    ),
+    QueryEngineTool(
+        query_engine=query_engine_pada,
+        metadata=ToolMetadata(
+            name="pandas_engine_padas",
+            description=(
+                '''A powerful tool designed to handle queries related to counting information about pada or words from vedic documents. This document is a .csv file with different columns as follows:\
+                    'Pada', 'scripture_name', 'mantra_id', 'MantraNumber', 'AnuvakNumber', 'PrapatakNumber', 'KandahNumber', 'Pada_position', 'term_index', 'Segmentation', 'Morphology', 'ShuktaNumber',\
+                        'ArchikahNumber', 'AdhyayaNumber', 'MandalaNumber', 'ParyayaNumber' \
+                Always provide the final answer after excuting pandas query which is equivalent to user query.\
+                Sample Query:\
+                1. How many padas are there in RigVeda?\
+                2. How many padas present in both rigveda and samaveda?
+               '''
+            ),
+        ),
     )
     ]
-
 # tools
 mantra_tools = MantraToolSpec().to_tool_list()
 description_tools = ScriptureDescriptionToolSpec().to_tool_list()
-tools = [*mantra_tools,*description_tools,*query_engine_tools]
+pada_tools = PadaToolSpec().to_tool_list()
+tools = [*mantra_tools,*pada_tools,*description_tools,*query_engine_tools]
 
 # context
 context = """
   You are an expert on Vedas and related scriptures.\
   Your role is to respond to questions about vedic scriptures and associated information based on available sources.\
-  For every query, you must use either any one of the tool or use available history/context.\
-  User expect the responses based on vedic scriptures or related vedas.\ 
+  For every query, you must use tool first. If the input args, kwargs and tools for the given query is same as in the history or retrieved context is sufficient, then use the history as context.
   Please provide well-informed answers. Don't use prior knowledge.
+  If you are not sure about the answer, you can say that you don't have sufficient information.
+  Also, provide three followup questions based on the input query and the answer in the following format.\
+  You may also try the following questions:\n
+  1. Question1\n
+  2. Question2\n
+  3. Question3\n
 """
 
 # Function to create ReActAgent instance (change it based on your initialization logic)