Multimodal Retrieval Augmented Generation (RAG) using the Gemini API in Agent Platform Reviews

Karan R. · Reviewed 18 days ago

kalidhass d. · Reviewed 18 days ago

Kamalesh J. · Reviewed 18 days ago

Sanjay C. · Reviewed 18 days ago

Sameeha G. · Reviewed 18 days ago

MONISHA G. · Reviewed 18 days ago

GOKUL G. · Reviewed 18 days ago

The first cell of "Search similar text with text query" generates error below. ValueError Traceback (most recent call last) Cell In[17], line 2 1 # Matching user text query with "chunk_embedding" to find relevant chunks. ----> 2 matching_results_text = get_similar_text_from_query( 3 query, 4 text_metadata_df, 5 column_name="text_embedding_chunk", File ~/utils/intro_multimodal_rag_utils.py:880, in get_similar_text_from_query(query, text_metadata_df, column_name, top_n, chunk_text, print_citation) 877 query_vector = get_user_query_text_embeddings(query) 879 # Calculate cosine similarity between query text and metadata text --> 880 cosine_scores = text_metadata_df.apply( 881 lambda row: get_cosine_score( 882 row, 883 column_name, 884 query_vector, 885 ), 886 axis=1, 887 ) 889 # Get top N cosine scores and their indices 890 top_n_indices = cosine_scores.nlargest(top_n).index.tolist() File /opt/micromamba/lib/python3.12/site-packages/pandas/core/frame.py:12437, in DataFrame.apply(self, func, axis, raw, result_type, args, by_row, engine, engine_kwargs, **kwargs) 12433 engine_kwargs=engine_kwargs, 12434 args=args, 12435 kwargs=kwargs, 12436 ) > 12437 return op.apply().__finalize__(self, method="apply") 12438 elif hasattr(engine, "__pandas_udf__"): 12439 if result_type is not None: 12440 raise NotImplementedError( File /opt/micromamba/lib/python3.12/site-packages/pandas/core/apply.py:1015, in FrameApply.apply(self) 1012 elif self.raw: 1013 return self.apply_raw(engine=self.engine, engine_kwargs=self.engine_kwargs) -> 1015 return self.apply_standard() File /opt/micromamba/lib/python3.12/site-packages/pandas/core/apply.py:1167, in FrameApply.apply_standard(self) 1165 def apply_standard(self): 1166 if self.engine == "python": -> 1167 results, res_index = self.apply_series_generator() 1168 else: 1169 results, res_index = self.apply_series_numba() File /opt/micromamba/lib/python3.12/site-packages/pandas/core/apply.py:1183, in FrameApply.apply_series_generator(self) 1180 results = {} 1182 for i, v in enumerate(series_gen): -> 1183 results[i] = self.func(v, *self.args, **self.kwargs) 1184 if isinstance(results[i], ABCSeries): 1185 # If we have a view on v, we need to make a copy because 1186 # series_generator will swap out the underlying data 1187 results[i] = results[i].copy(deep=False) File ~/utils/intro_multimodal_rag_utils.py:881, in get_similar_text_from_query.<locals>.<lambda>(row) 877 query_vector = get_user_query_text_embeddings(query) 879 # Calculate cosine similarity between query text and metadata text 880 cosine_scores = text_metadata_df.apply( --> 881 lambda row: get_cosine_score( 882 row, 883 column_name, 884 query_vector, 885 ), 886 axis=1, 887 ) 889 # Get top N cosine scores and their indices 890 top_n_indices = cosine_scores.nlargest(top_n).index.tolist() File ~/utils/intro_multimodal_rag_utils.py:633, in get_cosine_score(dataframe, column_name, input_text_embed) 620 """ 621 Calculates the cosine similarity between the user query embedding and the dataframe embedding for a specific column. 622 (...) 629 The cosine similarity score (rounded to two decimal places) between the user query embedding and the dataframe embedding. 630 """ 632 val = dataframe[column_name] --> 633 if pd.isna(val) or (isinstance(val, (list, np.ndarray)) and len(val) == 0): 634 return 0.0 635 return float(np.dot(val, input_text_embed)) ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

KOJI I. · Reviewed 18 days ago

INDHUMATHI S. · Reviewed 18 days ago

VIDHYA S. · Reviewed 18 days ago

Swetha K. · Reviewed 18 days ago

Geovani C. · Reviewed 19 days ago

Frank V. · Reviewed 19 days ago

Arnab G. · Reviewed 19 days ago

Prerana R. · Reviewed 19 days ago

Priya D. · Reviewed 19 days ago

Bala G. · Reviewed 19 days ago

Kalpana R. · Reviewed 19 days ago

vedha s a. · Reviewed 19 days ago

Rahul N. · Reviewed 19 days ago

Stefan N. · Reviewed 19 days ago

Lavanya G. · Reviewed 19 days ago

SAI S. · Reviewed 19 days ago

Boobalan R. · Reviewed 19 days ago

Misbah F. · Reviewed 19 days ago