I am trying to replicate the Self Query search example as below:
from langchain_chroma import Chromafrom langchain_core.documents import Documentfrom langchain_openai import OpenAIEmbeddingsdocs = [ Document( page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose", metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"}, ), Document( page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...", metadata={"year": 2010, "director": "Christopher Nolan", "rating": 8.2}, ), Document( page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea", metadata={"year": 2006, "director": "Satoshi Kon", "rating": 8.6}, ), Document( page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them", metadata={"year": 2019, "director": "Greta Gerwig", "rating": 8.3}, ), Document( page_content="Toys come alive and have a blast doing so", metadata={"year": 1995, "genre": "animated"}, ), Document( page_content="Three men walk into the Zone, three men walk out of the Zone", metadata={"year": 1979,"director": "Andrei Tarkovsky","genre": "thriller","rating": 9.9, }, ),]vectorstore = Chroma.from_documents(docs, OpenAIEmbeddings())from langchain.chains.query_constructor.base import AttributeInfofrom langchain.retrievers.self_query.base import SelfQueryRetrieverfrom langchain_openai import ChatOpenAImetadata_field_info = [ AttributeInfo( name="genre", description="The genre of the movie. One of ['science fiction', 'comedy', 'drama', 'thriller', 'romance', 'action', 'animated']", type="string", ), AttributeInfo( name="year", description="The year the movie was released", type="integer", ), AttributeInfo( name="director", description="The name of the movie director", type="string", ), AttributeInfo( name="rating", description="A 1-10 rating for the movie", type="float" ),]document_content_description = "Brief summary of a movie"llm = ChatOpenAI(temperature=0)retriever = SelfQueryRetriever.from_llm( llm, vectorstore, document_content_description, metadata_field_info,)# This example only specifies a filterretriever.invoke("I want to watch a movie rated higher than 8.5")Above works. I then tried instead using open source llm using llamacpp as below:
llm = LlamaCpp( model_path="D:\\opensrc_llms_downloads/llama-2-7b-chat.Q8_0.gguf", temperature=0.2, top_p=0.9, callback_manager=callback_manager, verbose=True, return_full_text=False,# repeat_last_n=56, max_tokens=256, ## change this to control the no of tokens generated in output n_ctx=4096, # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room repetition_penalty=1.18,# model_kwargs={"stopping_criteria":['Answer:',"\n","\n\n"]},# stop=["\n","\n\n"] #, "Answer:"] )But i get up ending the error as below:
OutputParserException: Parsing textraised following error:Received unrecognized function contains. Valid functions are [<Operator.AND: 'and'>, <Operator.OR: 'or'>, <Operator.NOT: 'not'>, <Comparator.EQ: 'eq'>, <Comparator.NE: 'ne'>, <Comparator.GT: 'gt'>, <Comparator.GTE: 'gte'>, <Comparator.LT: 'lt'>, <Comparator.LTE: 'lte'>, <Comparator.CONTAIN: 'contain'>, <Comparator.LIKE: 'like'>, <Comparator.IN: 'in'>, <Comparator.NIN: 'nin'>]