3fi! d Z ddlmZ ddlmZmZmZmZ ddlm Z ddl
m Z ddl m
Z
ddlmZ ddlmZ dd lmZ dd
lmZ dd lmZ dd lmZ dd
lmZ dZ dZ eddge Z ddZ e
ddd G d de Z y) z;
Question answering over an RDF or OWL graph using SPARQL.
) annotations)AnyDictListOptional)Chain)LLMChain)
deprecated)CallbackManagerForChainRun)BaseLanguageModel)BasePromptTemplate)PromptTemplate)Field)SPARQL_QA_PROMPT)NeptuneRdfGraphintermediate_stepsa4
Task: Generate a SPARQL SELECT statement for querying a graph database.
For instance, to find all email addresses of John Doe, the following
query in backticks would be suitable:
```
PREFIX foaf:
SELECT ?email
WHERE {{
?person foaf:name "John Doe" .
?person foaf:mbox ?email .
}}
```
Instructions:
Use only the node types and properties provided in the schema.
Do not use any node types and properties that are not explicitly provided.
Include all necessary prefixes.
Examples:
Schema:
{schema}
Note: Be as concise as possible.
Do not include any explanations or apologies in your responses.
Do not respond to any questions that ask for anything else than
for you to construct a SPARQL query.
Do not include any text except the SPARQL query generated.
The question is:
{prompt}schemapromptinput_variablestemplatec | j } | j d }t | dk( r |d } | j d r| dd } | S | j d r| j d r| d d
} | S ) zExtract SPARQL code from a text.
Args:
query: Text to extract SPARQL code from.
Returns:
SPARQL code extracted from the text.
z``` sparql Nzz i)stripsplitlen
startswithendswith)query querytokss p/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_community/chains/graph_qa/neptune_sparql.pyextract_sparqlr& : s}
KKME E"I
9~! H %!"IE L
* %%..*Ea L z0.3.15z1.0z,langchain_aws.create_neptune_sparql_qa_chain)sinceremovalalternative_importc , e Zd ZU dZ ed Zded< ded< ded< d Zd
ed < d Zd
ed
< dZ ded< dZ
ded< dZ ded< dZ ded< dZ
ded< d fd Zed d Zed d Zeeedd d!d Z d" d#d Z xZS )$NeptuneSparqlQAChaina Chain for question-answering against a Neptune graph
by generating SPARQL statements.
*Security note*: Make sure that the database connection uses credentials
that are narrowly-scoped to only include necessary permissions.
Failure to do so may result in data corruption or loss, since the calling
code may attempt commands that would result in deletion, mutation
of data if appropriately prompted or reading sensitive data if such
data is present in the database.
The best way to guard against such negative outcomes is to (as appropriate)
limit the permissions granted to the credentials used with this tool.
See https://python.langchain.com/docs/security for more information.
Example:
.. code-block:: python
chain = NeptuneSparqlQAChain.from_llm(
llm=llm,
graph=graph
)
response = chain.invoke(query)
T)excluder graphr sparql_generation_chainqa_chainr# str input_keyresult
output_key
inttop_kFboolreturn_intermediate_steps
return_directN
Optional[str]extra_instructionsallow_dangerous_requestsc V t | di | | j dur t d y)zInitialize the chain.Ta In order to use this chain, you must acknowledge that it can make dangerous requests by setting `allow_dangerous_requests` to `True`.You must narrowly scope the permissions of the database connection to only include necessary permissions. Failure to do so may result in data corruption or loss or reading sensitive data if such data is present in the database.Only use this chain if you understand the risks and have taken the necessary precautions. See https://python.langchain.com/docs/security for more information.N )super__init__r=
ValueError)selfkwargs __class__s r% rA z NeptuneSparqlQAChain.__init__ s9
"6" ( ( 4 W
5r' c | j gS N)r2 )rC s r%
input_keysz NeptuneSparqlQAChain.input_keys s r' c | j g}|S rG )r4 )rC _output_keyss r% output_keysz NeptuneSparqlQAChain.output_keys s ( r' ) qa_prompt
sparql_promptexamplesc t || }t }|r$|j dd|z }t ddg| }t || } | d|||d|S ) zInitialize from LLM.)llmr z Examples:z
Examples: r r r )r0 r/ rN r? )r SPARQL_GENERATION_TEMPLATEreplacer ) clsrP rL rM rN rD r0 template_to_user/ s r% from_llmz NeptuneSparqlQAChain.from_llm s| I64 - 5 5\H 4 O +!)8 4 M #+s="I
$;
r' c @ |xs t j }|j }|| j }g }| j j || j j d| }t | }|j dd| j |j |dd| j |j d|i | j j | }| j r|} n|j d d| j |j t | dd| j |j d
|i | j ||d | }
|
| j j } | j | i} | j" r || t$ < | S ) zt
Generate SPARQL query, use it to retrieve a response from the gdb and answer
the question.
)r r ) callbackszGenerated SPARQL:
)endverbosegreen)colorrY rZ r# z
Full Context:context)r r] )r get_noop_manager get_childr2 r/ runr.
get_schemar& on_textrZ appendr# r: r1 r0 r4 r9 INTERMEDIATE_STEPS_KEY) rC inputs run_manager _run_managerrW r r generated_sparqlr] final_resultr3 chain_results r% _callzNeptuneSparqlQAChain._call s #S&@&Q&Q&S **, '#% 77;; )>)> ?9 <
**:; 0dDLL Q Gt||
!!7,<"=>**""#34 "L dDLL Q G Gt||
!
% %y'&: ;]]!g6# # F "$--":":;L(, 'F ) )3EL/ 0r' )rD r returnNone)rl z List[str]) rP r rL r
rM r
rN r; rD r rl r, rG )re zDict[str, Any]rf z$Optional[CallbackManagerForChainRun]rl zDict[str, str])__name__
__module__ __qualname____doc__r r. __annotations__r2 r4 r7 r9 r: r< r= rA propertyrH rK classmethodr SPARQL_GENERATION_PROMPTrU rk
__classcell__)rE s @r% r, r, O s( 0 #4 0E?0 %% Is J E3O&+ t+V M4 M(,
,L%* d*
)9,D"&
&
*
> =A3 3 :3
3 r' r, N)r# r1 rl r1 )!rq
__future__r typingr r r r langchain_classic.chains.baser langchain_classic.chains.llmr langchain_core._api.deprecationr
langchain_core.callbacks.managerr langchain_core.language_modelsr langchain_core.prompts.baser
langchain_core.prompts.promptr pydanticr +langchain_community.chains.graph_qa.promptsr langchain_community.graphsr rd rQ ru r& r, r? r' r% r s # , , / 1 6 G < : 8 H 6- < * x(3M
*
E
^ 5 ^
^ r'