langchain.chains.graph_qa.arangodb.ArangoGraphQAChain¶
- class langchain.chains.graph_qa.arangodb.ArangoGraphQAChain(*, memory: Optional[BaseMemory] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, callback_manager: Optional[BaseCallbackManager] = None, verbose: bool = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, graph: ArangoGraph, aql_generation_chain: LLMChain, aql_fix_chain: LLMChain, qa_chain: LLMChain, input_key: str = 'query', output_key: str = 'result', return_aql_query: bool = False, return_aql_result: bool = False, top_k: int = 10, aql_examples: str = '', max_aql_generation_attempts: int = 3)[source]¶
Bases:
ChainChain for question-answering against a graph by generating AQL statements.
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- param callback_manager: Optional[BaseCallbackManager] = None¶
Deprecated, use callbacks instead.
- param callbacks: Callbacks = None¶
Optional list of callback handlers (or callback manager). Defaults to None. Callback handlers are called throughout the lifecycle of a call to a chain, starting with on_chain_start, ending with on_chain_end or on_chain_error. Each custom chain can optionally call additional callback methods, see Callback docs for full details.
- param graph: ArangoGraph [Required]¶
- param memory: Optional[BaseMemory] = None¶
Optional memory object. Defaults to None. Memory is a class that gets called at the start and at the end of every chain. At the start, memory loads variables and passes them along in the chain. At the end, it saves any returned variables. There are many different types of memory - please see memory docs for the full catalog.
- param metadata: Optional[Dict[str, Any]] = None¶
Optional metadata associated with the chain. Defaults to None. This metadata will be associated with each call to this chain, and passed as arguments to the handlers defined in callbacks. You can use these to eg identify a specific instance of a chain with its use case.
- param return_aql_query: bool = False¶
- param return_aql_result: bool = False¶
- param tags: Optional[List[str]] = None¶
Optional list of tags associated with the chain. Defaults to None. These tags will be associated with each call to this chain, and passed as arguments to the handlers defined in callbacks. You can use these to eg identify a specific instance of a chain with its use case.
- param verbose: bool [Optional]¶
Whether or not run in verbose mode. In verbose mode, some intermediate logs will be printed to the console. Defaults to langchain.verbose value.
- __call__(inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, include_run_info: bool = False) Dict[str, Any]¶
Execute the chain.
- Parameters
inputs – Dictionary of inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.
return_only_outputs – Whether to return only outputs in the response. If True, only new keys generated by this chain will be returned. If False, both input keys and new keys generated by this chain will be returned. Defaults to False.
callbacks – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.
tags – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.
metadata – Optional metadata associated with the chain. Defaults to None
include_run_info – Whether to include run info in the response. Defaults to False.
- Returns
- A dict of named outputs. Should contain all outputs specified in
Chain.output_keys.
- async acall(inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, include_run_info: bool = False) Dict[str, Any]¶
Asynchronously execute the chain.
- Parameters
inputs – Dictionary of inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.
return_only_outputs – Whether to return only outputs in the response. If True, only new keys generated by this chain will be returned. If False, both input keys and new keys generated by this chain will be returned. Defaults to False.
callbacks – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.
tags – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.
metadata – Optional metadata associated with the chain. Defaults to None
include_run_info – Whether to include run info in the response. Defaults to False.
- Returns
- A dict of named outputs. Should contain all outputs specified in
Chain.output_keys.
- async ainvoke(input: Dict[str, Any], config: Optional[RunnableConfig] = None) Dict[str, Any]¶
- apply(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None) List[Dict[str, str]]¶
Call the chain on all inputs in the list.
- async arun(*args: Any, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) Any¶
Convenience method for executing chain.
The main difference between this method and Chain.__call__ is that this method expects inputs to be passed directly in as positional arguments or keyword arguments, whereas Chain.__call__ expects a single input dictionary with all the inputs
- Parameters
*args – If the chain expects a single input, it can be passed in as the sole positional argument.
callbacks – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.
tags – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.
**kwargs – If the chain expects multiple inputs, they can be passed in directly as keyword arguments.
- Returns
The chain output.
Example
# Suppose we have a single-input chain that takes a 'question' string: await chain.arun("What's the temperature in Boise, Idaho?") # -> "The temperature in Boise is..." # Suppose we have a multi-input chain that takes a 'question' string # and 'context' string: question = "What's the temperature in Boise, Idaho?" context = "Weather report for Boise, Idaho on 07/03/23..." await chain.arun(question=question, context=context) # -> "The temperature in Boise is..."
- dict(**kwargs: Any) Dict¶
Dictionary representation of chain.
- Expects Chain._chain_type property to be implemented and for memory to be
null.
- Parameters
**kwargs – Keyword arguments passed to default pydantic.BaseModel.dict method.
- Returns
A dictionary representation of the chain.
Example
..code-block:: python
chain.dict(exclude_unset=True) # -> {“_type”: “foo”, “verbose”: False, …}
- classmethod from_llm(llm: BaseLanguageModel, *, qa_prompt: BasePromptTemplate = PromptTemplate(input_variables=['adb_schema', 'user_input', 'aql_query', 'aql_result'], output_parser=None, partial_variables={}, template="Task: Generate a natural language `Summary` from the results of an ArangoDB Query Language query.\n\nYou are an ArangoDB Query Language (AQL) expert responsible for creating a well-written `Summary` from the `User Input` and associated `AQL Result`.\n\nA user has executed an ArangoDB Query Language query, which has returned the AQL Result in JSON format.\nYou are responsible for creating an `Summary` based on the AQL Result.\n\nYou are given the following information:\n- `ArangoDB Schema`: contains a schema representation of the user's ArangoDB Database.\n- `User Input`: the original question/request of the user, which has been translated into an AQL Query.\n- `AQL Query`: the AQL equivalent of the `User Input`, translated by another AI Model. Should you deem it to be incorrect, suggest a different AQL Query.\n- `AQL Result`: the JSON output returned by executing the `AQL Query` within the ArangoDB Database.\n\nRemember to think step by step.\n\nYour `Summary` should sound like it is a response to the `User Input`.\nYour `Summary` should not include any mention of the `AQL Query` or the `AQL Result`.\n\nArangoDB Schema:\n{adb_schema}\n\nUser Input:\n{user_input}\n\nAQL Query:\n{aql_query}\n\nAQL Result:\n{aql_result}\n", template_format='f-string', validate_template=True), aql_generation_prompt: BasePromptTemplate = PromptTemplate(input_variables=['adb_schema', 'aql_examples', 'user_input'], output_parser=None, partial_variables={}, template="Task: Generate an ArangoDB Query Language (AQL) query from a User Input.\n\nYou are an ArangoDB Query Language (AQL) expert responsible for translating a `User Input` into an ArangoDB Query Language (AQL) query.\n\nYou are given an `ArangoDB Schema`. It is a JSON Object containing:\n1. `Graph Schema`: Lists all Graphs within the ArangoDB Database Instance, along with their Edge Relationships.\n2. `Collection Schema`: Lists all Collections within the ArangoDB Database Instance, along with their document/edge properties and a document/edge example.\n\nYou may also be given a set of `AQL Query Examples` to help you create the `AQL Query`. If provided, the `AQL Query Examples` should be used as a reference, similar to how `ArangoDB Schema` should be used.\n\nThings you should do:\n- Think step by step.\n- Rely on `ArangoDB Schema` and `AQL Query Examples` (if provided) to generate the query.\n- Begin the `AQL Query` by the `WITH` AQL keyword to specify all of the ArangoDB Collections required.\n- Return the `AQL Query` wrapped in 3 backticks (```).\n- Use only the provided relationship types and properties in the `ArangoDB Schema` and any `AQL Query Examples` queries.\n- Only answer to requests related to generating an AQL Query.\n- If a request is unrelated to generating AQL Query, say that you cannot help the user.\n\nThings you should not do:\n- Do not use any properties/relationships that can't be inferred from the `ArangoDB Schema` or the `AQL Query Examples`. \n- Do not include any text except the generated AQL Query.\n- Do not provide explanations or apologies in your responses.\n- Do not generate an AQL Query that removes or deletes any data.\n\nUnder no circumstance should you generate an AQL Query that deletes any data whatsoever.\n\nArangoDB Schema:\n{adb_schema}\n\nAQL Query Examples (Optional):\n{aql_examples}\n\nUser Input:\n{user_input}\n\nAQL Query: \n", template_format='f-string', validate_template=True), aql_fix_prompt: BasePromptTemplate = PromptTemplate(input_variables=['adb_schema', 'aql_query', 'aql_error'], output_parser=None, partial_variables={}, template="Task: Address the ArangoDB Query Language (AQL) error message of an ArangoDB Query Language query.\n\nYou are an ArangoDB Query Language (AQL) expert responsible for correcting the provided `AQL Query` based on the provided `AQL Error`. \n\nThe `AQL Error` explains why the `AQL Query` could not be executed in the database.\nThe `AQL Error` may also contain the position of the error relative to the total number of lines of the `AQL Query`.\nFor example, 'error X at position 2:5' denotes that the error X occurs on line 2, column 5 of the `AQL Query`. \n\nYou are also given the `ArangoDB Schema`. It is a JSON Object containing:\n1. `Graph Schema`: Lists all Graphs within the ArangoDB Database Instance, along with their Edge Relationships.\n2. `Collection Schema`: Lists all Collections within the ArangoDB Database Instance, along with their document/edge properties and a document/edge example.\n\nYou will output the `Corrected AQL Query` wrapped in 3 backticks (```). Do not include any text except the Corrected AQL Query.\n\nRemember to think step by step.\n\nArangoDB Schema:\n{adb_schema}\n\nAQL Query:\n{aql_query}\n\nAQL Error:\n{aql_error}\n\nCorrected AQL Query:\n", template_format='f-string', validate_template=True), **kwargs: Any) ArangoGraphQAChain[source]¶
Initialize from LLM.
- invoke(input: Dict[str, Any], config: Optional[RunnableConfig] = None) Dict[str, Any]¶
- prep_inputs(inputs: Union[Dict[str, Any], Any]) Dict[str, str]¶
Validate and prepare chain inputs, including adding inputs from memory.
- Parameters
inputs – Dictionary of raw inputs, or single input if chain expects only one param. Should contain all inputs specified in Chain.input_keys except for inputs that will be set by the chain’s memory.
- Returns
A dictionary of all inputs, including those added by the chain’s memory.
- prep_outputs(inputs: Dict[str, str], outputs: Dict[str, str], return_only_outputs: bool = False) Dict[str, str]¶
Validate and prepare chain outputs, and save info about this run to memory.
- Parameters
inputs – Dictionary of chain inputs, including any inputs added by chain memory.
outputs – Dictionary of initial chain outputs.
return_only_outputs – Whether to only return the chain outputs. If False, inputs are also added to the final outputs.
- Returns
A dict of the final chain outputs.
- validator raise_callback_manager_deprecation » all fields¶
Raise deprecation warning if callback_manager is used.
- run(*args: Any, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) Any¶
Convenience method for executing chain.
The main difference between this method and Chain.__call__ is that this method expects inputs to be passed directly in as positional arguments or keyword arguments, whereas Chain.__call__ expects a single input dictionary with all the inputs
- Parameters
*args – If the chain expects a single input, it can be passed in as the sole positional argument.
callbacks – Callbacks to use for this chain run. These will be called in addition to callbacks passed to the chain during construction, but only these runtime callbacks will propagate to calls to other objects.
tags – List of string tags to pass to all callbacks. These will be passed in addition to tags passed to the chain during construction, but only these runtime tags will propagate to calls to other objects.
**kwargs – If the chain expects multiple inputs, they can be passed in directly as keyword arguments.
- Returns
The chain output.
Example
# Suppose we have a single-input chain that takes a 'question' string: chain.run("What's the temperature in Boise, Idaho?") # -> "The temperature in Boise is..." # Suppose we have a multi-input chain that takes a 'question' string # and 'context' string: question = "What's the temperature in Boise, Idaho?" context = "Weather report for Boise, Idaho on 07/03/23..." chain.run(question=question, context=context) # -> "The temperature in Boise is..."
- save(file_path: Union[Path, str]) None¶
Save the chain.
- Expects Chain._chain_type property to be implemented and for memory to be
null.
- Parameters
file_path – Path to file to save the chain to.
Example
chain.save(file_path="path/chain.yaml")
- validator set_verbose » verbose¶
Set the chain verbosity.
Defaults to the global setting if not specified by the user.
- to_json() Union[SerializedConstructor, SerializedNotImplemented]¶
- to_json_not_implemented() SerializedNotImplemented¶
- property input_keys: List[str]¶
Keys expected to be in the chain input.
- property lc_attributes: Dict¶
Return a list of attribute names that should be included in the serialized kwargs. These attributes must be accepted by the constructor.
- property lc_namespace: List[str]¶
Return the namespace of the langchain object. eg. [“langchain”, “llms”, “openai”]
- property lc_secrets: Dict[str, str]¶
Return a map of constructor argument names to secret ids. eg. {“openai_api_key”: “OPENAI_API_KEY”}
- property lc_serializable: bool¶
Return whether or not the class is serializable.
- property output_keys: List[str]¶
Keys expected to be in the chain output.